Merge tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux

Pull ARM updates from Russell King:

 - Rework phys/virt translation

 - Add KASan support

 - Move DT out of linear map region

 - Use more PC-relative addressing in assembly

 - Remove FP emulation handling while in kernel mode

 - Link with '-z norelro'

 - remove old check for GCC <= 4.2 in ARM unwinder code

 - disable big endian if using clang's linker

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (46 commits)
  ARM: 9027/1: head.S: explicitly map DT even if it lives in the first physical section
  ARM: 9038/1: Link with '-z norelro'
  ARM: 9037/1: uncompress: Add OF_DT_MAGIC macro
  ARM: 9036/1: uncompress: Fix dbgadtb size parameter name
  ARM: 9035/1: uncompress: Add be32tocpu macro
  ARM: 9033/1: arm/smp: Drop the macro S(x,s)
  ARM: 9032/1: arm/mm: Convert PUD level pgtable helper macros into functions
  ARM: 9031/1: hyp-stub: remove unused .L__boot_cpu_mode_offset symbol
  ARM: 9044/1: vfp: use undef hook for VFP support detection
  ARM: 9034/1: __div64_32(): straighten up inline asm constraints
  ARM: 9030/1: entry: omit FP emulation for UND exceptions taken in kernel mode
  ARM: 9029/1: Make iwmmxt.S support Clang's integrated assembler
  ARM: 9028/1: disable KASAN in call stack capturing routines
  ARM: 9026/1: unwind: remove old check for GCC <= 4.2
  ARM: 9025/1: Kconfig: CPU_BIG_ENDIAN depends on !LD_IS_LLD
  ARM: 9024/1: Drop useless cast of "u64" to "long long"
  ARM: 9023/1: Spelling s/mmeory/memory/
  ARM: 9022/1: Change arch/arm/lib/mem*.S to use WEAK instead of .weak
  ARM: kvm: replace open coded VA->PA calculations with adr_l call
  ARM: head.S: use PC relative insn sequence to calculate PHYS_OFFSET
  ...

14 files changed, 329 insertions, 45 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index feac2c8b86f2..6ed30421f697 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -259,7 +259,7 @@
  */
 #define ALT_UP(instr...)					\
 	.pushsection ".alt.smp.init", "a"			;\
-	.long	9998b						;\
+	.long	9998b - .					;\
 9997:	instr							;\
 	.if . - 9997b == 2					;\
 		nop						;\
@@ -270,7 +270,7 @@
 	.popsection
 #define ALT_UP_B(label)					\
 	.pushsection ".alt.smp.init", "a"			;\
-	.long	9998b						;\
+	.long	9998b - .					;\
 	W(b)	. + (label - 9998b)					;\
 	.popsection
 #else
@@ -494,4 +494,88 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #define _ASM_NOKPROBE(entry)
 #endif
 
+	.macro		__adldst_l, op, reg, sym, tmp, c
+	.if		__LINUX_ARM_ARCH__ < 7
+	ldr\c		\tmp, .La\@
+	.subsection	1
+	.align		2
+.La\@:	.long		\sym - .Lpc\@
+	.previous
+	.else
+	.ifnb		\c
+ THUMB(	ittt		\c			)
+	.endif
+	movw\c		\tmp, #:lower16:\sym - .Lpc\@
+	movt\c		\tmp, #:upper16:\sym - .Lpc\@
+	.endif
+
+#ifndef CONFIG_THUMB2_KERNEL
+	.set		.Lpc\@, . + 8			// PC bias
+	.ifc		\op, add
+	add\c		\reg, \tmp, pc
+	.else
+	\op\c		\reg, [pc, \tmp]
+	.endif
+#else
+.Lb\@:	add\c		\tmp, \tmp, pc
+	/*
+	 * In Thumb-2 builds, the PC bias depends on whether we are currently
+	 * emitting into a .arm or a .thumb section. The size of the add opcode
+	 * above will be 2 bytes when emitting in Thumb mode and 4 bytes when
+	 * emitting in ARM mode, so let's use this to account for the bias.
+	 */
+	.set		.Lpc\@, . + (. - .Lb\@)
+
+	.ifnc		\op, add
+	\op\c		\reg, [\tmp]
+	.endif
+#endif
+	.endm
+
+	/*
+	 * mov_l - move a constant value or [relocated] address into a register
+	 */
+	.macro		mov_l, dst:req, imm:req
+	.if		__LINUX_ARM_ARCH__ < 7
+	ldr		\dst, =\imm
+	.else
+	movw		\dst, #:lower16:\imm
+	movt		\dst, #:upper16:\imm
+	.endif
+	.endm
+
+	/*
+	 * adr_l - adr pseudo-op with unlimited range
+	 *
+	 * @dst: destination register
+	 * @sym: name of the symbol
+	 * @cond: conditional opcode suffix
+	 */
+	.macro		adr_l, dst:req, sym:req, cond
+	__adldst_l	add, \dst, \sym, \dst, \cond
+	.endm
+
+	/*
+	 * ldr_l - ldr <literal> pseudo-op with unlimited range
+	 *
+	 * @dst: destination register
+	 * @sym: name of the symbol
+	 * @cond: conditional opcode suffix
+	 */
+	.macro		ldr_l, dst:req, sym:req, cond
+	__adldst_l	ldr, \dst, \sym, \dst, \cond
+	.endm
+
+	/*
+	 * str_l - str <literal> pseudo-op with unlimited range
+	 *
+	 * @src: source register
+	 * @sym: name of the symbol
+	 * @tmp: mandatory scratch register
+	 * @cond: conditional opcode suffix
+	 */
+	.macro		str_l, src:req, sym:req, tmp:req, cond
+	__adldst_l	str, \src, \sym, \tmp, \cond
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
index 898e9c78a7e7..595e538f5bfb 100644
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@@ -21,29 +21,20 @@
  * assembly implementation with completely non standard calling convention
  * for arguments and results (beware).
  */
-
-#ifdef __ARMEB__
-#define __xh "r0"
-#define __xl "r1"
-#else
-#define __xl "r0"
-#define __xh "r1"
-#endif
-
 static inline uint32_t __div64_32(uint64_t *n, uint32_t base)
 {
 	register unsigned int __base      asm("r4") = base;
 	register unsigned long long __n   asm("r0") = *n;
 	register unsigned long long __res asm("r2");
-	register unsigned int __rem       asm(__xh);
-	asm(	__asmeq("%0", __xh)
+	unsigned int __rem;
+	asm(	__asmeq("%0", "r0")
 		__asmeq("%1", "r2")
-		__asmeq("%2", "r0")
-		__asmeq("%3", "r4")
+		__asmeq("%2", "r4")
 		"bl	__do_div64"
-		: "=r" (__rem), "=r" (__res)
-		: "r" (__n), "r" (__base)
+		: "+r" (__n), "=r" (__res)
+		: "r" (__base)
 		: "ip", "lr", "cc");
+	__rem = __n >> 32;
 	*n = __res;
 	return __rem;
 }
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 61941f369861..b8102a6ddf16 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -51,6 +51,7 @@ typedef struct user_fp elf_fpregset_t;
 #define R_ARM_NONE		0
 #define R_ARM_PC24		1
 #define R_ARM_ABS32		2
+#define R_ARM_REL32		3
 #define R_ARM_CALL		28
 #define R_ARM_JUMP24		29
 #define R_ARM_TARGET1		38
@@ -58,11 +59,15 @@ typedef struct user_fp elf_fpregset_t;
 #define R_ARM_PREL31		42
 #define R_ARM_MOVW_ABS_NC	43
 #define R_ARM_MOVT_ABS		44
+#define R_ARM_MOVW_PREL_NC	45
+#define R_ARM_MOVT_PREL		46
 
 #define R_ARM_THM_CALL		10
 #define R_ARM_THM_JUMP24	30
 #define R_ARM_THM_MOVW_ABS_NC	47
 #define R_ARM_THM_MOVT_ABS	48
+#define R_ARM_THM_MOVW_PREL_NC	49
+#define R_ARM_THM_MOVT_PREL	50
 
 /*
  * These are used to set parameters in the core dumps.
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index c279a8a463a2..707068f852c2 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_FIXMAP_H
 #define _ASM_FIXMAP_H
 
-#define FIXADDR_START		0xffc00000UL
+#define FIXADDR_START		0xffc80000UL
 #define FIXADDR_END		0xfff00000UL
 #define FIXADDR_TOP		(FIXADDR_END - PAGE_SIZE)
 
diff --git a/arch/arm/include/asm/kasan.h b/arch/arm/include/asm/kasan.h
new file mode 100644
index 000000000000..303c35df3135
--- /dev/null
+++ b/arch/arm/include/asm/kasan.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * arch/arm/include/asm/kasan.h
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ *
+ */
+
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifdef CONFIG_KASAN
+
+#include <asm/kasan_def.h>
+
+#define KASAN_SHADOW_SCALE_SHIFT 3
+
+/*
+ * The compiler uses a shadow offset assuming that addresses start
+ * from 0. Kernel addresses don't start from 0, so shadow
+ * for kernel really starts from 'compiler's shadow offset' +
+ * ('kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT)
+ */
+
+asmlinkage void kasan_early_init(void);
+extern void kasan_init(void);
+
+#else
+static inline void kasan_init(void) { }
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/kasan_def.h b/arch/arm/include/asm/kasan_def.h
new file mode 100644
index 000000000000..5739605aa7cf
--- /dev/null
+++ b/arch/arm/include/asm/kasan_def.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  arch/arm/include/asm/kasan_def.h
+ *
+ *  Copyright (c) 2018 Huawei Technologies Co., Ltd.
+ *
+ *  Author: Abbott Liu <liuwenliang@huawei.com>
+ */
+
+#ifndef __ASM_KASAN_DEF_H
+#define __ASM_KASAN_DEF_H
+
+#ifdef CONFIG_KASAN
+
+/*
+ * Define KASAN_SHADOW_OFFSET,KASAN_SHADOW_START and KASAN_SHADOW_END for
+ * the Arm kernel address sanitizer. We are "stealing" lowmem (the 4GB
+ * addressable by a 32bit architecture) out of the virtual address
+ * space to use as shadow memory for KASan as follows:
+ *
+ * +----+ 0xffffffff
+ * |    |							\
+ * |    | |-> Static kernel image (vmlinux) BSS and page table
+ * |    |/
+ * +----+ PAGE_OFFSET
+ * |    |							\
+ * |    | |->  Loadable kernel modules virtual address space area
+ * |    |/
+ * +----+ MODULES_VADDR = KASAN_SHADOW_END
+ * |    |						\
+ * |    | |-> The shadow area of kernel virtual address.
+ * |    |/
+ * +----+->  TASK_SIZE (start of kernel space) = KASAN_SHADOW_START the
+ * |    |\   shadow address of MODULES_VADDR
+ * |    | |
+ * |    | |
+ * |    | |-> The user space area in lowmem. The kernel address
+ * |    | |   sanitizer do not use this space, nor does it map it.
+ * |    | |
+ * |    | |
+ * |    | |
+ * |    | |
+ * |    |/
+ * ------ 0
+ *
+ * 1) KASAN_SHADOW_START
+ *   This value begins with the MODULE_VADDR's shadow address. It is the
+ *   start of kernel virtual space. Since we have modules to load, we need
+ *   to cover also that area with shadow memory so we can find memory
+ *   bugs in modules.
+ *
+ * 2) KASAN_SHADOW_END
+ *   This value is the 0x100000000's shadow address: the mapping that would
+ *   be after the end of the kernel memory at 0xffffffff. It is the end of
+ *   kernel address sanitizer shadow area. It is also the start of the
+ *   module area.
+ *
+ * 3) KASAN_SHADOW_OFFSET:
+ *   This value is used to map an address to the corresponding shadow
+ *   address by the following formula:
+ *
+ *	shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET;
+ *
+ *  As you would expect, >> 3 is equal to dividing by 8, meaning each
+ *  byte in the shadow memory covers 8 bytes of kernel memory, so one
+ *  bit shadow memory per byte of kernel memory is used.
+ *
+ *  The KASAN_SHADOW_OFFSET is provided in a Kconfig option depending
+ *  on the VMSPLIT layout of the system: the kernel and userspace can
+ *  split up lowmem in different ways according to needs, so we calculate
+ *  the shadow offset depending on this.
+ */
+
+#define KASAN_SHADOW_SCALE_SHIFT	3
+#define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+#define KASAN_SHADOW_END	((UL(1) << (32 - KASAN_SHADOW_SCALE_SHIFT)) \
+				 + KASAN_SHADOW_OFFSET)
+#define KASAN_SHADOW_START      ((KASAN_SHADOW_END >> 3) + KASAN_SHADOW_OFFSET)
+
+#endif
+#endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 99035b5891ef..2f841cb65c30 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -18,6 +18,7 @@
 #ifdef CONFIG_NEED_MACH_MEMORY_H
 #include <mach/memory.h>
 #endif
+#include <asm/kasan_def.h>
 
 /* PAGE_OFFSET - the virtual address of the start of the kernel image */
 #define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
@@ -28,7 +29,11 @@
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
  */
+#ifndef CONFIG_KASAN
 #define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M))
+#else
+#define TASK_SIZE		(KASAN_SHADOW_START)
+#endif
 #define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
 
 /*
@@ -67,6 +72,10 @@
  */
 #define XIP_VIRT_ADDR(physaddr)  (MODULES_VADDR + ((physaddr) & 0x000fffff))
 
+#define FDT_FIXED_BASE		UL(0xff800000)
+#define FDT_FIXED_SIZE		(2 * SECTION_SIZE)
+#define FDT_VIRT_BASE(physbase)	((void *)(FDT_FIXED_BASE | (physbase) % SECTION_SIZE))
+
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 /*
  * Allow 16MB-aligned ioremap pages
@@ -107,6 +116,7 @@ extern unsigned long vectors_base;
 #define MODULES_VADDR		PAGE_OFFSET
 
 #define XIP_VIRT_ADDR(physaddr)  (physaddr)
+#define FDT_VIRT_BASE(physbase)  ((void *)(physbase))
 
 #endif /* !CONFIG_MMU */
 
@@ -173,6 +183,7 @@ extern unsigned long vectors_base;
  * so that all we need to do is modify the 8-bit constant field.
  */
 #define __PV_BITS_31_24	0x81000000
+#define __PV_BITS_23_16	0x810000
 #define __PV_BITS_7_0	0x81
 
 extern unsigned long __pv_phys_pfn_offset;
@@ -183,43 +194,65 @@ extern const void *__pv_table_begin, *__pv_table_end;
 #define PHYS_OFFSET	((phys_addr_t)__pv_phys_pfn_offset << PAGE_SHIFT)
 #define PHYS_PFN_OFFSET	(__pv_phys_pfn_offset)
 
-#define __pv_stub(from,to,instr,type)			\
+#ifndef CONFIG_THUMB2_KERNEL
+#define __pv_stub(from,to,instr)			\
 	__asm__("@ __pv_stub\n"				\
 	"1:	" instr "	%0, %1, %2\n"		\
+	"2:	" instr "	%0, %0, %3\n"		\
 	"	.pushsection .pv_table,\"a\"\n"		\
-	"	.long	1b\n"				\
+	"	.long	1b - ., 2b - .\n"		\
 	"	.popsection\n"				\
 	: "=r" (to)					\
-	: "r" (from), "I" (type))
+	: "r" (from), "I" (__PV_BITS_31_24),		\
+	  "I"(__PV_BITS_23_16))
 
-#define __pv_stub_mov_hi(t)				\
-	__asm__ volatile("@ __pv_stub_mov\n"		\
-	"1:	mov	%R0, %1\n"			\
+#define __pv_add_carry_stub(x, y)			\
+	__asm__("@ __pv_add_carry_stub\n"		\
+	"0:	movw	%R0, #0\n"			\
+	"	adds	%Q0, %1, %R0, lsl #20\n"	\
+	"1:	mov	%R0, %2\n"			\
+	"	adc	%R0, %R0, #0\n"			\
 	"	.pushsection .pv_table,\"a\"\n"		\
-	"	.long	1b\n"				\
+	"	.long	0b - ., 1b - .\n"		\
 	"	.popsection\n"				\
-	: "=r" (t)					\
-	: "I" (__PV_BITS_7_0))
+	: "=&r" (y)					\
+	: "r" (x), "I" (__PV_BITS_7_0)			\
+	: "cc")
+
+#else
+#define __pv_stub(from,to,instr)			\
+	__asm__("@ __pv_stub\n"				\
+	"0:	movw	%0, #0\n"			\
+	"	lsl	%0, #21\n"			\
+	"	" instr " %0, %1, %0\n"			\
+	"	.pushsection .pv_table,\"a\"\n"		\
+	"	.long	0b - .\n"			\
+	"	.popsection\n"				\
+	: "=&r" (to)					\
+	: "r" (from))
 
 #define __pv_add_carry_stub(x, y)			\
-	__asm__ volatile("@ __pv_add_carry_stub\n"	\
-	"1:	adds	%Q0, %1, %2\n"			\
+	__asm__("@ __pv_add_carry_stub\n"		\
+	"0:	movw	%R0, #0\n"			\
+	"	lsls	%R0, #21\n"			\
+	"	adds	%Q0, %1, %R0\n"			\
+	"1:	mvn	%R0, #0\n"			\
 	"	adc	%R0, %R0, #0\n"			\
 	"	.pushsection .pv_table,\"a\"\n"		\
-	"	.long	1b\n"				\
+	"	.long	0b - ., 1b - .\n"		\
 	"	.popsection\n"				\
-	: "+r" (y)					\
-	: "r" (x), "I" (__PV_BITS_31_24)		\
+	: "=&r" (y)					\
+	: "r" (x)					\
 	: "cc")
+#endif
 
 static inline phys_addr_t __virt_to_phys_nodebug(unsigned long x)
 {
 	phys_addr_t t;
 
 	if (sizeof(phys_addr_t) == 4) {
-		__pv_stub(x, t, "add", __PV_BITS_31_24);
+		__pv_stub(x, t, "add");
 	} else {
-		__pv_stub_mov_hi(t);
 		__pv_add_carry_stub(x, t);
 	}
 	return t;
@@ -235,7 +268,7 @@ static inline unsigned long __phys_to_virt(phys_addr_t x)
 	 * assembler expression receives 32 bit argument
 	 * in place where 'r' 32 bit operand is expected.
 	 */
-	__pv_stub((unsigned long) x, t, "sub", __PV_BITS_31_24);
+	__pv_stub((unsigned long) x, t, "sub");
 	return t;
 }
 
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 15f4674715f8..fdee1f04f4f3 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -21,6 +21,7 @@
 #define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
 
 #ifdef CONFIG_ARM_LPAE
+#define PGD_SIZE		(PTRS_PER_PGD * sizeof(pgd_t))
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
@@ -28,14 +29,19 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 }
 
 #else	/* !CONFIG_ARM_LPAE */
+#define PGD_SIZE		(PAGE_SIZE << 2)
 
 /*
  * Since we have only two-level page tables, these are trivial
  */
 #define pmd_alloc_one(mm,addr)		({ BUG(); ((pmd_t *)2); })
 #define pmd_free(mm, pmd)		do { } while (0)
+#ifdef CONFIG_KASAN
+/* The KASan core unconditionally calls pud_populate() on all architectures */
+#define pud_populate(mm,pmd,pte)	do { } while (0)
+#else
 #define pud_populate(mm,pmd,pte)	BUG()
-
+#endif
 #endif	/* CONFIG_ARM_LPAE */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index baf7d0204eb5..70fe69bdcce2 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -179,11 +179,28 @@
  * the pud: the pud entry is never bad, always exists, and can't be set or
  * cleared.
  */
-#define pud_none(pud)		(0)
-#define pud_bad(pud)		(0)
-#define pud_present(pud)	(1)
-#define pud_clear(pudp)		do { } while (0)
-#define set_pud(pud,pudp)	do { } while (0)
+static inline int pud_none(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pud_bad(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pud_present(pud_t pud)
+{
+	return 1;
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pud)
+{
+}
 
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 {
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index b9241051e5cb..9e6b97286307 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -96,7 +96,7 @@ unsigned long get_wchan(struct task_struct *p);
 #define __ALT_SMP_ASM(smp, up)						\
 	"9998:	" smp "\n"						\
 	"	.pushsection \".alt.smp.init\", \"a\"\n"		\
-	"	.long	9998b\n"					\
+	"	.long	9998b - .\n"					\
 	"	" up "\n"						\
 	"	.popsection\n"
 #else
diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h
index 1e36c40533c1..402e3f34c7ed 100644
--- a/arch/arm/include/asm/prom.h
+++ b/arch/arm/include/asm/prom.h
@@ -9,12 +9,12 @@
 
 #ifdef CONFIG_OF
 
-extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
+extern const struct machine_desc *setup_machine_fdt(void *dt_virt);
 extern void __init arm_dt_init_cpu_maps(void);
 
 #else /* CONFIG_OF */
 
-static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
+static inline const struct machine_desc *setup_machine_fdt(void *dt_virt)
 {
 	return NULL;
 }
diff --git a/arch/arm/include/asm/string.h b/arch/arm/include/asm/string.h
index 111a1d8a41dd..6c607c68f3ad 100644
--- a/arch/arm/include/asm/string.h
+++ b/arch/arm/include/asm/string.h
@@ -5,6 +5,9 @@
 /*
  * We don't do inline string functions, since the
  * optimised inline asm versions are not small.
+ *
+ * The __underscore versions of some functions are for KASan to be able
+ * to replace them with instrumented versions.
  */
 
 #define __HAVE_ARCH_STRRCHR
@@ -15,15 +18,18 @@ extern char * strchr(const char * s, int c);
 
 #define __HAVE_ARCH_MEMCPY
 extern void * memcpy(void *, const void *, __kernel_size_t);
+extern void *__memcpy(void *dest, const void *src, __kernel_size_t n);
 
 #define __HAVE_ARCH_MEMMOVE
 extern void * memmove(void *, const void *, __kernel_size_t);
+extern void *__memmove(void *dest, const void *src, __kernel_size_t n);
 
 #define __HAVE_ARCH_MEMCHR
 extern void * memchr(const void *, int, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMSET
 extern void * memset(void *, int, __kernel_size_t);
+extern void *__memset(void *s, int c, __kernel_size_t n);
 
 #define __HAVE_ARCH_MEMSET32
 extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
@@ -39,4 +45,24 @@ static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n)
 	return __memset64(p, v, n * 8, v >> 32);
 }
 
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * must use non-instrumented versions of the mem*
+ * functions named __memcpy() etc. All such kernel code has
+ * been tagged with KASAN_SANITIZE_file.o = n, which means
+ * that the address sanitization argument isn't passed to the
+ * compiler, and __SANITIZE_ADDRESS__ is not set. As a result
+ * these defines kick in.
+ */
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+#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
+
 #endif
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index eb7ce2747eb0..70d4cbc49ae1 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -13,7 +13,15 @@
 #include <asm/fpstate.h>
 #include <asm/page.h>
 
+#ifdef CONFIG_KASAN
+/*
+ * KASan uses a lot of extra stack space so the thread size order needs to
+ * be increased.
+ */
+#define THREAD_SIZE_ORDER	2
+#else
 #define THREAD_SIZE_ORDER	1
+#endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 #define THREAD_START_SP		(THREAD_SIZE - 8)
 
diff --git a/arch/arm/include/asm/uaccess-asm.h b/arch/arm/include/asm/uaccess-asm.h
index 907571fd05c6..e6eb7a2aaf1e 100644
--- a/arch/arm/include/asm/uaccess-asm.h
+++ b/arch/arm/include/asm/uaccess-asm.h
@@ -85,7 +85,7 @@
 	 */
 	.macro	uaccess_entry, tsk, tmp0, tmp1, tmp2, disable
 	ldr	\tmp1, [\tsk, #TI_ADDR_LIMIT]
-	mov	\tmp2, #TASK_SIZE
+	ldr	\tmp2, =TASK_SIZE
 	str	\tmp2, [\tsk, #TI_ADDR_LIMIT]
  DACR(	mrc	p15, 0, \tmp0, c3, c0, 0)
  DACR(	str	\tmp0, [sp, #SVC_DACR])