Merge branch 'devel-stable' into for-next

Conflicts: arch/arm/Makefile arch/arm/include/asm/glue-proc.h
2024-12-29 06:12:08 +00:00 · 2013-06-29 11:44:43 +01:00 · 2013-06-29 11:44:43 +01:00 · 3c0c01ab74
commit 3c0c01ab74
parent cbd379b100 809e660f43
77 changed files with 2243 additions and 306 deletions
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@ -9,7 +9,7 @@ config ARM
 	select BUILDTIME_EXTABLE_SORT if MMU
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN && MMU
-	select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI)
+	select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@ -1441,7 +1441,7 @@ config SMP
 	depends on CPU_V6K || CPU_V7
 	depends on GENERIC_CLOCKEVENTS
 	depends on HAVE_SMP
-	depends on MMU
+	depends on MMU || ARM_MPU
 	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
@ -1462,7 +1462,7 @@ config SMP

 config SMP_ON_UP
 	bool "Allow booting SMP kernel on uniprocessor systems (EXPERIMENTAL)"
-	depends on SMP && !XIP_KERNEL
+	depends on SMP && !XIP_KERNEL && MMU
 	default y
 	help
 	  SMP kernels contain instructions which fail on non-SMP processors.
@ -1612,7 +1612,7 @@ config SCHED_HRTICK

 config THUMB2_KERNEL
 	bool "Compile the kernel in Thumb-2 mode" if !CPU_THUMBONLY
-	depends on CPU_V7 && !CPU_V6 && !CPU_V6K
+	depends on (CPU_V7 || CPU_V7M) && !CPU_V6 && !CPU_V6K
 	default y if CPU_THUMBONLY
 	select AEABI
 	select ARM_ASM_UNIFIED
@ -1734,6 +1734,14 @@ config HW_PERF_EVENTS
 	  Enable hardware performance counter support for perf events. If
 	  disabled, perf events will use software events only.

+config SYS_SUPPORTS_HUGETLBFS
+       def_bool y
+       depends on ARM_LPAE
+
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE
+       def_bool y
+       depends on ARM_LPAE
+
 source "mm/Kconfig"

 config FORCE_MAX_ZONEORDER
--- a/arch/arm/Kconfig-nommu
+++ b/arch/arm/Kconfig-nommu
@ -28,7 +28,7 @@ config FLASH_SIZE
 config PROCESSOR_ID
 	hex 'Hard wire the processor ID'
 	default 0x00007700
-	depends on !CPU_CP15
+	depends on !(CPU_CP15 || CPU_V7M)
 	help
 	  If processor has no CP15 register, this processor ID is
 	  used instead of the auto-probing which utilizes the register.
@ -50,3 +50,15 @@ config REMAP_VECTORS_TO_RAM
 	  Otherwise, say 'y' here.  In this case, the kernel will require
 	  external support to redirect the hardware exception vectors to
 	  the writable versions located at DRAM_BASE.
+
+config ARM_MPU
+       bool 'Use the ARM v7 PMSA Compliant MPU'
+       depends on CPU_V7
+       default y
+       help
+         Some ARM systems without an MMU have instead a Memory Protection
+         Unit (MPU) that defines the type and permissions for regions of
+         memory.
+
+         If your CPU has an MPU then you should choose 'y' here unless you
+         know that you do not want to use the MPU.
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@ -476,6 +476,13 @@ choice
 		  of the tiles using the RS1 memory map, including all new A-class
 		  core tiles, FPGA-based SMMs and software models.

+	config DEBUG_VEXPRESS_UART0_CRX
+		bool "Use PL011 UART0 at 0xb0090000 (Cortex-R compliant tiles)"
+		depends on ARCH_VEXPRESS && !MMU
+		help
+		  This option selects UART0 at 0xb0090000. This is appropriate for
+		  Cortex-R series tiles and SMMs, such as Cortex-R5 and Cortex-R7
+
 	config DEBUG_VT8500_UART0
 		bool "Use UART0 on VIA/Wondermedia SoCs"
 		depends on ARCH_VT8500
@ -645,7 +652,8 @@ config DEBUG_LL_INCLUDE
 	default "debug/tegra.S" if DEBUG_TEGRA_UART
 	default "debug/ux500.S" if DEBUG_UX500_UART
 	default "debug/vexpress.S" if DEBUG_VEXPRESS_UART0_DETECT || \
-		DEBUG_VEXPRESS_UART0_CA9 || DEBUG_VEXPRESS_UART0_RS1
+		DEBUG_VEXPRESS_UART0_CA9 || DEBUG_VEXPRESS_UART0_RS1 || \
+		DEBUG_VEXPRESS_UART0_CRX
 	default "debug/vt8500.S" if DEBUG_VT8500_UART0
 	default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1
 	default "mach/debug-macro.S"
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@ -59,6 +59,7 @@ comma = ,
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
 # testing for a specific architecture or later rather impossible.
+arch-$(CONFIG_CPU_32v7M)	=-D__LINUX_ARM_ARCH__=7 -march=armv7-m -Wa,-march=armv7-m
 arch-$(CONFIG_CPU_32v7)		=-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7-a,-march=armv5t -Wa$(comma)-march=armv7-a)
 arch-$(CONFIG_CPU_32v6)		=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6,-march=armv5t -Wa$(comma)-march=armv6)
 # Only override the compiler option if ARMv6. The ARMv6K extensions are
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@ -80,15 +80,6 @@ static inline u32 arch_timer_get_cntfrq(void)
 	return val;
 }

-static inline u64 arch_counter_get_cntpct(void)
-{
-	u64 cval;
-
-	isb();
-	asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval));
-	return cval;
-}
-
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@ -136,7 +136,11 @@
 * assumes FIQs are enabled, and that the processor is in SVC mode.
 */
 	.macro	save_and_disable_irqs, oldcpsr
+#ifdef CONFIG_CPU_V7M
+	mrs	\oldcpsr, primask
+#else
 	mrs	\oldcpsr, cpsr
+#endif
 	disable_irq
 	.endm

@ -150,7 +154,11 @@
 * guarantee that this will preserve the flags.
 */
 	.macro	restore_irqs_notrace, oldcpsr
+#ifdef CONFIG_CPU_V7M
+	msr	primask, \oldcpsr
+#else
 	msr	cpsr_c, \oldcpsr
+#endif
 	.endm

 	.macro restore_irqs, oldcpsr
@ -229,7 +237,14 @@
 #endif
 	.endm

-#ifdef CONFIG_THUMB2_KERNEL
+#if defined(CONFIG_CPU_V7M)
+	/*
+	 * setmode is used to assert to be in svc mode during boot. For v7-M
+	 * this is done in __v7m_setup, so setmode can be empty here.
+	 */
+	.macro	setmode, mode, reg
+	.endm
+#elif defined(CONFIG_THUMB2_KERNEL)
 	.macro	setmode, mode, reg
 	mov	\reg, #\mode
 	msr	cpsr_c, \reg
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@ -23,6 +23,11 @@
 #define CR_RR	(1 << 14)	/* Round Robin cache replacement	*/
 #define CR_L4	(1 << 15)	/* LDR pc can set T bit			*/
 #define CR_DT	(1 << 16)
+#ifdef CONFIG_MMU
+#define CR_HA	(1 << 17)	/* Hardware management of Access Flag   */
+#else
+#define CR_BR	(1 << 17)	/* MPU Background region enable (PMSA)  */
+#endif
 #define CR_IT	(1 << 18)
 #define CR_ST	(1 << 19)
 #define CR_FI	(1 << 21)	/* Fast interrupt (lower latency mode)	*/
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@ -8,8 +8,25 @@
 #define CPUID_CACHETYPE	1
 #define CPUID_TCM	2
 #define CPUID_TLBTYPE	3
+#define CPUID_MPUIR	4
 #define CPUID_MPIDR	5

+#ifdef CONFIG_CPU_V7M
+#define CPUID_EXT_PFR0	0x40
+#define CPUID_EXT_PFR1	0x44
+#define CPUID_EXT_DFR0	0x48
+#define CPUID_EXT_AFR0	0x4c
+#define CPUID_EXT_MMFR0	0x50
+#define CPUID_EXT_MMFR1	0x54
+#define CPUID_EXT_MMFR2	0x58
+#define CPUID_EXT_MMFR3	0x5c
+#define CPUID_EXT_ISAR0	0x60
+#define CPUID_EXT_ISAR1	0x64
+#define CPUID_EXT_ISAR2	0x68
+#define CPUID_EXT_ISAR3	0x6c
+#define CPUID_EXT_ISAR4	0x70
+#define CPUID_EXT_ISAR5	0x74
+#else
 #define CPUID_EXT_PFR0	"c1, 0"
 #define CPUID_EXT_PFR1	"c1, 1"
 #define CPUID_EXT_DFR0	"c1, 2"
@ -24,6 +41,7 @@
 #define CPUID_EXT_ISAR3	"c2, 3"
 #define CPUID_EXT_ISAR4	"c2, 4"
 #define CPUID_EXT_ISAR5	"c2, 5"
+#endif

 #define MPIDR_SMP_BITMASK (0x3 << 30)
 #define MPIDR_SMP_VALUE (0x2 << 30)
@ -81,7 +99,23 @@ extern unsigned int processor_id;
 		__val;							\
 	})

-#else /* ifdef CONFIG_CPU_CP15 */
+#elif defined(CONFIG_CPU_V7M)
+
+#include <asm/io.h>
+#include <asm/v7m.h>
+
+#define read_cpuid(reg)							\
+	({								\
+		WARN_ON_ONCE(1);					\
+		0;							\
+	})
+
+static inline unsigned int __attribute_const__ read_cpuid_ext(unsigned offset)
+{
+	return readl(BASEADDR_V7M_SCB + offset);
+}
+
+#else /* ifdef CONFIG_CPU_CP15 / elif defined (CONFIG_CPU_V7M) */

 /*
 * read_cpuid and read_cpuid_ext should only ever be called on machines that
@ -108,7 +142,14 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void)
 	return read_cpuid(CPUID_ID);
 }

-#else /* ifdef CONFIG_CPU_CP15 */
+#elif defined(CONFIG_CPU_V7M)
+
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return readl(BASEADDR_V7M_SCB + V7M_SCB_CPUID);
+}
+
+#else /* ifdef CONFIG_CPU_CP15 / elif defined(CONFIG_CPU_V7M) */

 static inline unsigned int __attribute_const__ read_cpuid_id(void)
 {
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@ -117,10 +117,37 @@
 # endif
 #endif

+#if defined(CONFIG_CPU_V7M)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE nop
+# endif
+#endif
+
 #if !defined(_CACHE) && !defined(MULTI_CACHE)
 #error Unknown cache maintenance model
 #endif

+#ifndef __ASSEMBLER__
+extern inline void nop_flush_icache_all(void) { }
+extern inline void nop_flush_kern_cache_all(void) { }
+extern inline void nop_flush_kern_cache_louis(void) { }
+extern inline void nop_flush_user_cache_all(void) { }
+extern inline void nop_flush_user_cache_range(unsigned long a,
+		unsigned long b, unsigned int c) { }
+
+extern inline void nop_coherent_kern_range(unsigned long a, unsigned long b) { }
+extern inline int nop_coherent_user_range(unsigned long a,
+		unsigned long b) { return 0; }
+extern inline void nop_flush_kern_dcache_area(void *a, size_t s) { }
+
+extern inline void nop_dma_flush_range(const void *a, const void *b) { }
+
+extern inline void nop_dma_map_area(const void *s, size_t l, int f) { }
+extern inline void nop_dma_unmap_area(const void *s, size_t l, int f) { }
+#endif
+
 #ifndef MULTI_CACHE
 #define __cpuc_flush_icache_all		__glue(_CACHE,_flush_icache_all)
 #define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
--- a/arch/arm/include/asm/glue-df.h
+++ b/arch/arm/include/asm/glue-df.h
@ -95,6 +95,14 @@
 # endif
 #endif

+#ifdef CONFIG_CPU_ABRT_NOMMU
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER nommu_early_abort
+# endif
+#endif
+
 #ifndef CPU_DABORT_HANDLER
 #error Unknown data abort handler type
 #endif
--- a/arch/arm/include/asm/glue-proc.h
+++ b/arch/arm/include/asm/glue-proc.h
@ -230,6 +230,15 @@
 # endif
 #endif

+#ifdef CONFIG_CPU_V7M
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_v7m
+# endif
+#endif
+
 #ifdef CONFIG_CPU_PJ4B
 # ifdef CPU_NAME
 #  undef  MULTI_CPU
--- a/arch/arm/include/asm/hugetlb-3level.h
+++ b/arch/arm/include/asm/hugetlb-3level.h
@ -0,0 +1,71 @@
+/*
+ * arch/arm/include/asm/hugetlb-3level.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _ASM_ARM_HUGETLB_3LEVEL_H
+#define _ASM_ARM_HUGETLB_3LEVEL_H
+
+
+/*
+ * If our huge pte is non-zero then mark the valid bit.
+ * This allows pte_present(huge_ptep_get(ptep)) to return true for non-zero
+ * ptes.
+ * (The valid bit is automatically cleared by set_pte_at for PROT_NONE ptes).
+ */
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	pte_t retval = *ptep;
+	if (pte_val(retval))
+		pte_val(retval) |= L_PTE_VALID;
+	return retval;
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+	ptep_clear_flush(vma, addr, ptep);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+#endif /* _ASM_ARM_HUGETLB_3LEVEL_H */
--- a/arch/arm/include/asm/hugetlb.h
+++ b/arch/arm/include/asm/hugetlb.h
@ -0,0 +1,84 @@
+/*
+ * arch/arm/include/asm/hugetlb.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _ASM_ARM_HUGETLB_H
+#define _ASM_ARM_HUGETLB_H
+
+#include <asm/page.h>
+#include <asm-generic/hugetlb.h>
+
+#include <asm/hugetlb-3level.h>
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr, unsigned long len)
+{
+	return 0;
+}
+
+static inline int prepare_hugepage_range(struct file *file,
+					 unsigned long addr, unsigned long len)
+{
+	struct hstate *h = hstate_file(file);
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (addr & ~huge_page_mask(h))
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_dcache_clean, &page->flags);
+}
+
+#endif /* _ASM_ARM_HUGETLB_H */
--- a/arch/arm/include/asm/irqflags.h
+++ b/arch/arm/include/asm/irqflags.h
@ -8,6 +8,16 @@
 /*
 * CPU interrupt mask handling.
 */
+#ifdef CONFIG_CPU_V7M
+#define IRQMASK_REG_NAME_R "primask"
+#define IRQMASK_REG_NAME_W "primask"
+#define IRQMASK_I_BIT	1
+#else
+#define IRQMASK_REG_NAME_R "cpsr"
+#define IRQMASK_REG_NAME_W "cpsr_c"
+#define IRQMASK_I_BIT	PSR_I_BIT
+#endif
+
 #if __LINUX_ARM_ARCH__ >= 6

 static inline unsigned long arch_local_irq_save(void)
@ -15,7 +25,7 @@ static inline unsigned long arch_local_irq_save(void)
 	unsigned long flags;

 	asm volatile(
-		"	mrs	%0, cpsr	@ arch_local_irq_save\n"
+		"	mrs	%0, " IRQMASK_REG_NAME_R "	@ arch_local_irq_save\n"
 		"	cpsid	i"
 		: "=r" (flags) : : "memory", "cc");
 	return flags;
@ -129,7 +139,7 @@ static inline unsigned long arch_local_save_flags(void)
 {
 	unsigned long flags;
 	asm volatile(
-		"	mrs	%0, cpsr	@ local_save_flags"
+		"	mrs	%0, " IRQMASK_REG_NAME_R "	@ local_save_flags"
 		: "=r" (flags) : : "memory", "cc");
 	return flags;
 }
@ -140,7 +150,7 @@ static inline unsigned long arch_local_save_flags(void)
 static inline void arch_local_irq_restore(unsigned long flags)
 {
 	asm volatile(
-		"	msr	cpsr_c, %0	@ local_irq_restore"
+		"	msr	" IRQMASK_REG_NAME_W ", %0	@ local_irq_restore"
 		:
 		: "r" (flags)
 		: "memory", "cc");
@ -148,8 +158,8 @@ static inline void arch_local_irq_restore(unsigned long flags)

 static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
-	return flags & PSR_I_BIT;
+	return flags & IRQMASK_I_BIT;
 }

-#endif
-#endif
+#endif /* ifdef __KERNEL__ */
+#endif /* ifndef __ASM_ARM_IRQFLAGS_H */
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@ -8,6 +8,8 @@
 * published by the Free Software Foundation.
 */

+#include <linux/types.h>
+
 #ifndef __ASSEMBLY__

 struct tag;
@ -16,8 +18,10 @@ struct pt_regs;
 struct smp_operations;
 #ifdef CONFIG_SMP
 #define smp_ops(ops) (&(ops))
+#define smp_init_ops(ops) (&(ops))
 #else
 #define smp_ops(ops) (struct smp_operations *)NULL
+#define smp_init_ops(ops) (bool (*)(void))NULL
 #endif

 struct machine_desc {
@ -41,6 +45,7 @@ struct machine_desc {
 	unsigned char		reserve_lp2 :1;	/* never has lp2	*/
 	char			restart_mode;	/* default restart mode	*/
 	struct smp_operations	*smp;		/* SMP operations	*/
+	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **,
 					 struct meminfo *);
 	void			(*reserve)(void);/* reserve mem blocks	*/
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@ -18,6 +18,8 @@
 #include <linux/types.h>
 #include <linux/sizes.h>

+#include <asm/cache.h>
+
 #ifdef CONFIG_NEED_MACH_MEMORY_H
 #include <mach/memory.h>
 #endif
@ -141,6 +143,20 @@
 #define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
 #define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))

+/*
+ * Minimum guaranted alignment in pgd_alloc().  The page table pointers passed
+ * around in head.S and proc-*.S are shifted by this amount, in order to
+ * leave spare high bits for systems with physical address extension.  This
+ * does not fully accomodate the 40-bit addressing capability of ARM LPAE, but
+ * gives us about 38-bits or so.
+ */
+#ifdef CONFIG_ARM_LPAE
+#define ARCH_PGD_SHIFT		L1_CACHE_SHIFT
+#else
+#define ARCH_PGD_SHIFT		0
+#endif
+#define ARCH_PGD_MASK		((1 << ARCH_PGD_SHIFT) - 1)
+
 #ifndef __ASSEMBLY__

 /*
@ -207,7 +223,7 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 * direct-mapped view.  We assume this is the first page
 * of RAM in the mem_map as well.
 */
-#define PHYS_PFN_OFFSET	(PHYS_OFFSET >> PAGE_SHIFT)
+#define PHYS_PFN_OFFSET	((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT))

 /*
 * These are *only* valid on the kernel direct mapped RAM memory.
--- a/arch/arm/include/asm/mpu.h
+++ b/arch/arm/include/asm/mpu.h
@ -0,0 +1,76 @@
+#ifndef __ARM_MPU_H
+#define __ARM_MPU_H
+
+#ifdef CONFIG_ARM_MPU
+
+/* MPUIR layout */
+#define MPUIR_nU		1
+#define MPUIR_DREGION		8
+#define MPUIR_IREGION		16
+#define MPUIR_DREGION_SZMASK	(0xFF << MPUIR_DREGION)
+#define MPUIR_IREGION_SZMASK	(0xFF << MPUIR_IREGION)
+
+/* ID_MMFR0 data relevant to MPU */
+#define MMFR0_PMSA		(0xF << 4)
+#define MMFR0_PMSAv7		(3 << 4)
+
+/* MPU D/I Size Register fields */
+#define MPU_RSR_SZ		1
+#define MPU_RSR_EN		0
+
+/* The D/I RSR value for an enabled region spanning the whole of memory */
+#define MPU_RSR_ALL_MEM		63
+
+/* Individual bits in the DR/IR ACR */
+#define MPU_ACR_XN		(1 << 12)
+#define MPU_ACR_SHARED		(1 << 2)
+
+/* C, B and TEX[2:0] bits only have semantic meanings when grouped */
+#define MPU_RGN_CACHEABLE	0xB
+#define MPU_RGN_SHARED_CACHEABLE (MPU_RGN_CACHEABLE | MPU_ACR_SHARED)
+#define MPU_RGN_STRONGLY_ORDERED 0
+
+/* Main region should only be shared for SMP */
+#ifdef CONFIG_SMP
+#define MPU_RGN_NORMAL		(MPU_RGN_CACHEABLE | MPU_ACR_SHARED)
+#else
+#define MPU_RGN_NORMAL		MPU_RGN_CACHEABLE
+#endif
+
+/* Access permission bits of ACR (only define those that we use)*/
+#define MPU_AP_PL1RW_PL0RW	(0x3 << 8)
+#define MPU_AP_PL1RW_PL0R0	(0x2 << 8)
+#define MPU_AP_PL1RW_PL0NA	(0x1 << 8)
+
+/* For minimal static MPU region configurations */
+#define MPU_PROBE_REGION	0
+#define MPU_BG_REGION		1
+#define MPU_RAM_REGION		2
+#define MPU_VECTORS_REGION	3
+
+/* Maximum number of regions Linux is interested in */
+#define MPU_MAX_REGIONS		16
+
+#define MPU_DATA_SIDE		0
+#define MPU_INSTR_SIDE		1
+
+#ifndef __ASSEMBLY__
+
+struct mpu_rgn {
+	/* Assume same attributes for d/i-side  */
+	u32 drbar;
+	u32 drsr;
+	u32 dracr;
+};
+
+struct mpu_rgn_info {
+	u32 mpuir;
+	struct mpu_rgn rgns[MPU_MAX_REGIONS];
+};
+extern struct mpu_rgn_info mpu_rgn_info;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_ARM_MPU */
+
+#endif
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@ -13,7 +13,7 @@
 /* PAGE_SHIFT determines the page size */
 #define PAGE_SHIFT		12
 #define PAGE_SIZE		(_AC(1,UL) << PAGE_SHIFT)
-#define PAGE_MASK		(~(PAGE_SIZE-1))
+#define PAGE_MASK		(~((1 << PAGE_SHIFT) - 1))

 #ifndef __ASSEMBLY__

--- a/arch/arm/include/asm/pgtable-3level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@ -30,6 +30,7 @@
 #define PMD_TYPE_FAULT		(_AT(pmdval_t, 0) << 0)
 #define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
+#define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
 #define PMD_BIT4		(_AT(pmdval_t, 0))
 #define PMD_DOMAIN(x)		(_AT(pmdval_t, 0))
 #define PMD_APTABLE_SHIFT	(61)
@ -41,6 +42,8 @@
 */
 #define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
 #define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
+#define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_nG		(_AT(pmdval_t, 1) << 11)
@ -66,6 +69,7 @@
 #define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
 #define PTE_TYPE_FAULT		(_AT(pteval_t, 0) << 0)
 #define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
+#define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
 #define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
 #define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
 #define PTE_EXT_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
@ -79,4 +83,24 @@
 #define PHYS_MASK_SHIFT		(40)
 #define PHYS_MASK		((1ULL << PHYS_MASK_SHIFT) - 1)

+/*
+ * TTBR0/TTBR1 split (PAGE_OFFSET):
+ *   0x40000000: T0SZ = 2, T1SZ = 0 (not used)
+ *   0x80000000: T0SZ = 0, T1SZ = 1
+ *   0xc0000000: T0SZ = 0, T1SZ = 2
+ *
+ * Only use this feature if PHYS_OFFSET <= PAGE_OFFSET, otherwise
+ * booting secondary CPUs would end up using TTBR1 for the identity
+ * mapping set up in TTBR0.
+ */
+#if defined CONFIG_VMSPLIT_2G
+#define TTBR1_OFFSET	16			/* skip two L1 entries */
+#elif defined CONFIG_VMSPLIT_3G
+#define TTBR1_OFFSET	(4096 * (1 + 3))	/* only L2, skip pgd + 3*pmd */
+#else
+#define TTBR1_OFFSET	0
+#endif
+
+#define TTBR1_SIZE	(((PAGE_OFFSET >> 30) - 1) << 16)
+
 #endif
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@ -33,7 +33,7 @@
 #define PTRS_PER_PMD		512
 #define PTRS_PER_PGD		4

-#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
+#define PTE_HWTABLE_PTRS	(0)
 #define PTE_HWTABLE_OFF		(0)
 #define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u64))

@ -48,19 +48,27 @@
 #define PMD_SHIFT		21

 #define PMD_SIZE		(1UL << PMD_SHIFT)
-#define PMD_MASK		(~(PMD_SIZE-1))
+#define PMD_MASK		(~((1 << PMD_SHIFT) - 1))
 #define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+#define PGDIR_MASK		(~((1 << PGDIR_SHIFT) - 1))

 /*
 * section address mask and size definitions.
 */
 #define SECTION_SHIFT		21
 #define SECTION_SIZE		(1UL << SECTION_SHIFT)
-#define SECTION_MASK		(~(SECTION_SIZE-1))
+#define SECTION_MASK		(~((1 << SECTION_SHIFT) - 1))

 #define USER_PTRS_PER_PGD	(PAGE_OFFSET / PGDIR_SIZE)

+/*
+ * Hugetlb definitions.
+ */
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
 /*
 * "Linux" PTE definitions for LPAE.
 *
@ -79,6 +87,11 @@
 #define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)	/* unused */
 #define L_PTE_NONE		(_AT(pteval_t, 1) << 57)	/* PROT_NONE */

+#define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
+#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
+#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
+#define PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+
 /*
 * To be used in assembly code with the upper page attributes.
 */
@ -166,8 +179,83 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 		clean_pmd_entry(pmdp);	\
 	} while (0)

+/*
+ * For 3 levels of paging the PTE_EXT_NG bit will be set for user address ptes
+ * that are written to a page table but not for ptes created with mk_pte.
+ *
+ * In hugetlb_no_page, a new huge pte (new_pte) is generated and passed to
+ * hugetlb_cow, where it is compared with an entry in a page table.
+ * This comparison test fails erroneously leading ultimately to a memory leak.
+ *
+ * To correct this behaviour, we mask off PTE_EXT_NG for any pte that is
+ * present before running the comparison.
+ */
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(pte_a,pte_b)	((pte_present(pte_a) ? pte_val(pte_a) & ~PTE_EXT_NG	\
+					: pte_val(pte_a))				\
+				== (pte_present(pte_b) ? pte_val(pte_b) & ~PTE_EXT_NG	\
+					: pte_val(pte_b)))
+
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))

+#define pte_huge(pte)		(pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
+#define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
+
+#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
+#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#endif
+
+#define PMD_BIT_FUNC(fn,op) \
+static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+
+PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
+PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
+PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
+
+#define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+
+#define pmd_pfn(pmd)		(((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
+
+/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+#define pmd_mknotpresent(pmd)	(__pmd(0))
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY |
+				PMD_SECT_VALID | PMD_SECT_NONE;
+	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
+	return pmd;
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	BUG_ON(addr >= TASK_SIZE);
+
+	/* create a faulting entry if PROT_NONE protected */
+	if (pmd_val(pmd) & PMD_SECT_NONE)
+		pmd_val(pmd) &= ~PMD_SECT_VALID;
+
+	*pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG);
+	flush_pmd_entry(pmdp);
+}
+
+static inline int has_transparent_hugepage(void)
+{
+	return 1;
+}
+
 #endif /* __ASSEMBLY__ */

 #endif /* _ASM_PGTABLE_3LEVEL_H */
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@ -24,6 +24,9 @@
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>

+
+#include <asm/tlbflush.h>
+
 #ifdef CONFIG_ARM_LPAE
 #include <asm/pgtable-3level.h>
 #else
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@ -60,7 +60,7 @@ extern struct processor {
 	/*
 	 * Set the page table
 	 */
-	void (*switch_mm)(unsigned long pgd_phys, struct mm_struct *mm);
+	void (*switch_mm)(phys_addr_t pgd_phys, struct mm_struct *mm);
 	/*
 	 * Set a possibly extended PTE.  Non-extended PTEs should
 	 * ignore 'ext'.
@ -82,7 +82,7 @@ extern void cpu_proc_init(void);
 extern void cpu_proc_fin(void);
 extern int cpu_do_idle(void);
 extern void cpu_dcache_clean_area(void *, int);
-extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
+extern void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
 #ifdef CONFIG_ARM_LPAE
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
 #else
@ -116,13 +116,25 @@ extern void cpu_resume(void);
 #define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)

 #ifdef CONFIG_ARM_LPAE
+
+#define cpu_get_ttbr(nr)					\
+	({							\
+		u64 ttbr;					\
+		__asm__("mrrc	p15, " #nr ", %Q0, %R0, c2"	\
+			: "=r" (ttbr));				\
+		ttbr;						\
+	})
+
+#define cpu_set_ttbr(nr, val)					\
+	do {							\
+		u64 ttbr = val;					\
+		__asm__("mcrr	p15, " #nr ", %Q0, %R0, c2"	\
+			: : "r" (ttbr));			\
+	} while (0)
+
 #define cpu_get_pgd()	\
 	({						\
-		unsigned long pg, pg2;			\
-		__asm__("mrrc	p15, 0, %0, %1, c2"	\
-			: "=r" (pg), "=r" (pg2)		\
-			:				\
-			: "cc");			\
+		u64 pg = cpu_get_ttbr(0);		\
 		pg &= ~(PTRS_PER_PGD*sizeof(pgd_t)-1);	\
 		(pgd_t *)phys_to_virt(pg);		\
 	})
@ -137,6 +149,10 @@ extern void cpu_resume(void);
 	})
 #endif

+#else	/*!CONFIG_MMU */
+
+#define cpu_switch_mm(pgd,mm)	{ }
+
 #endif

 #endif /* __ASSEMBLY__ */
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@ -32,5 +32,14 @@ struct psci_operations {
 };

 extern struct psci_operations psci_ops;
+extern struct smp_operations psci_smp_ops;
+
+#ifdef CONFIG_ARM_PSCI
+void psci_init(void);
+bool psci_smp_available(void);
+#else
+static inline void psci_init(void) { }
+static inline bool psci_smp_available(void) { return false; }
+#endif

 #endif /* __ASM_ARM_PSCI_H */
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@ -45,6 +45,7 @@ struct pt_regs {
 */
 static inline int valid_user_regs(struct pt_regs *regs)
 {
+#ifndef CONFIG_CPU_V7M
 	unsigned long mode = regs->ARM_cpsr & MODE_MASK;

 	/*
@ -67,6 +68,9 @@ static inline int valid_user_regs(struct pt_regs *regs)
 		regs->ARM_cpsr |= USR_MODE;

 	return 0;
+#else /* ifndef CONFIG_CPU_V7M */
+	return 1;
+#endif
 }

 static inline long regs_return_value(struct pt_regs *regs)
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@ -65,7 +65,10 @@ asmlinkage void secondary_start_kernel(void);
 * Initial data for bringing up a secondary CPU.
 */
 struct secondary_data {
-	unsigned long pgdir;
+	union {
+		unsigned long mpu_rgn_szr;
+		unsigned long pgdir;
+	};
 	unsigned long swapper_pg_dir;
 	void *stack;
 };
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@ -26,6 +26,9 @@ static inline bool is_smp(void)
 }

 /* all SMP configurations have the extended CPUID registers */
+#ifndef CONFIG_MMU
+#define tlb_ops_need_broadcast()	0
+#else
 static inline int tlb_ops_need_broadcast(void)
 {
 	if (!is_smp())
@ -33,6 +36,7 @@ static inline int tlb_ops_need_broadcast(void)

 	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
 }
+#endif

 #if !defined(CONFIG_SMP) || __LINUX_ARM_ARCH__ >= 7
 #define cache_ops_need_broadcast()	0
@ -66,4 +70,22 @@ static inline int get_logical_index(u32 mpidr)
 	return -EINVAL;
 }

+/*
+ * NOTE ! Assembly code relies on the following
+ * structure memory layout in order to carry out load
+ * multiple from its base address. For more
+ * information check arch/arm/kernel/sleep.S
+ */
+struct mpidr_hash {
+	u32	mask; /* used by sleep.S */
+	u32	shift_aff[3]; /* used by sleep.S */
+	u32	bits;
+};
+
+extern struct mpidr_hash mpidr_hash;
+
+static inline u32 mpidr_hash_size(void)
+{
+	return 1 << mpidr_hash.bits;
+}
 #endif
--- a/arch/arm/include/asm/suspend.h
+++ b/arch/arm/include/asm/suspend.h
@ -1,6 +1,11 @@
 #ifndef __ASM_ARM_SUSPEND_H
 #define __ASM_ARM_SUSPEND_H

+struct sleep_save_sp {
+	u32 *save_ptr_stash;
+	u32 save_ptr_stash_phys;
+};
+
 extern void cpu_resume(void);
 extern int cpu_suspend(unsigned long, int (*)(unsigned long));

--- a/arch/arm/include/asm/system_info.h
+++ b/arch/arm/include/asm/system_info.h
@ -11,6 +11,7 @@
 #define CPU_ARCH_ARMv5TEJ	7
 #define CPU_ARCH_ARMv6		8
 #define CPU_ARCH_ARMv7		9
+#define CPU_ARCH_ARMv7M		10

 #ifndef __ASSEMBLY__

--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@ -204,6 +204,12 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 #endif
 }

+static inline void
+tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
+{
+	tlb_add_flush(tlb, addr);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
 #define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@ -535,8 +535,33 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 }
 #endif

-#endif
-
-#endif /* CONFIG_MMU */
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
+#endif
+
+#elif defined(CONFIG_SMP)	/* !CONFIG_MMU */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/mm_types.h>
+
+static inline void local_flush_tlb_all(void)									{ }
+static inline void local_flush_tlb_mm(struct mm_struct *mm)							{ }
+static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)			{ }
+static inline void local_flush_tlb_kernel_page(unsigned long kaddr)						{ }
+static inline void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)	{ }
+static inline void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)				{ }
+static inline void local_flush_bp_all(void)									{ }
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr);
+extern void flush_tlb_kernel_page(unsigned long kaddr);
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void flush_bp_all(void);
+#endif	/* __ASSEMBLY__ */
+
+#endif

 #endif
--- a/arch/arm/include/asm/v7m.h
+++ b/arch/arm/include/asm/v7m.h
@ -0,0 +1,44 @@
+/*
+ * Common defines for v7m cpus
+ */
+#define V7M_SCS_ICTR			IOMEM(0xe000e004)
+#define V7M_SCS_ICTR_INTLINESNUM_MASK		0x0000000f
+
+#define BASEADDR_V7M_SCB		IOMEM(0xe000ed00)
+
+#define V7M_SCB_CPUID			0x00
+
+#define V7M_SCB_ICSR			0x04
+#define V7M_SCB_ICSR_PENDSVSET			(1 << 28)
+#define V7M_SCB_ICSR_PENDSVCLR			(1 << 27)
+#define V7M_SCB_ICSR_RETTOBASE			(1 << 11)
+
+#define V7M_SCB_VTOR			0x08
+
+#define V7M_SCB_SCR			0x10
+#define V7M_SCB_SCR_SLEEPDEEP			(1 << 2)
+
+#define V7M_SCB_CCR			0x14
+#define V7M_SCB_CCR_STKALIGN			(1 << 9)
+
+#define V7M_SCB_SHPR2			0x1c
+#define V7M_SCB_SHPR3			0x20
+
+#define V7M_SCB_SHCSR			0x24
+#define V7M_SCB_SHCSR_USGFAULTENA		(1 << 18)
+#define V7M_SCB_SHCSR_BUSFAULTENA		(1 << 17)
+#define V7M_SCB_SHCSR_MEMFAULTENA		(1 << 16)
+
+#define V7M_xPSR_FRAMEPTRALIGN			0x00000200
+#define V7M_xPSR_EXCEPTIONNO			0x000001ff
+
+/*
+ * When branching to an address that has bits [31:28] == 0xf an exception return
+ * occurs. Bits [27:5] are reserved (SBOP). If the processor implements the FP
+ * extension Bit [4] defines if the exception frame has space allocated for FP
+ * state information, SBOP otherwise. Bit [3] defines the mode that is returned
+ * to (0 -> handler mode; 1 -> thread mode). Bit [2] defines which sp is used
+ * (0 -> msp; 1 -> psp). Bits [1:0] are fixed to 0b01.
+ */
+#define EXC_RET_STACK_MASK			0x00000004
+#define EXC_RET_THREADMODE_PROCESSSTACK		0xfffffffd
--- a/arch/arm/include/debug/vexpress.S
+++ b/arch/arm/include/debug/vexpress.S
@ -16,6 +16,8 @@
 #define DEBUG_LL_PHYS_BASE_RS1		0x1c000000
 #define DEBUG_LL_UART_OFFSET_RS1	0x00090000

+#define DEBUG_LL_UART_PHYS_CRX		0xb0090000
+
 #define DEBUG_LL_VIRT_BASE		0xf8000000

 #if defined(CONFIG_DEBUG_VEXPRESS_UART0_DETECT)
@ -67,6 +69,14 @@

 #include <asm/hardware/debug-pl01x.S>

+#elif defined(CONFIG_DEBUG_VEXPRESS_UART0_CRX)
+
+		.macro	addruart,rp,tmp,tmp2
+		ldr	\rp, =DEBUG_LL_UART_PHYS_CRX
+		.endm
+
+#include <asm/hardware/debug-pl01x.S>
+
 #else /* CONFIG_DEBUG_LL_UART_NONE */

 		.macro	addruart, rp, rv, tmp
--- a/arch/arm/include/uapi/asm/hwcap.h
+++ b/arch/arm/include/uapi/asm/hwcap.h
@ -25,6 +25,6 @@
 #define HWCAP_IDIVT	(1 << 18)
 #define HWCAP_VFPD32	(1 << 19)	/* set if VFP has 32 regs (not 16) */
 #define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
-
+#define HWCAP_LPAE	(1 << 20)

 #endif /* _UAPI__ASMARM_HWCAP_H */
--- a/arch/arm/include/uapi/asm/ptrace.h
+++ b/arch/arm/include/uapi/asm/ptrace.h
@ -34,28 +34,47 @@

 /*
 * PSR bits
+ * Note on V7M there is no mode contained in the PSR
 */
 #define USR26_MODE	0x00000000
 #define FIQ26_MODE	0x00000001
 #define IRQ26_MODE	0x00000002
 #define SVC26_MODE	0x00000003
+#if defined(__KERNEL__) && defined(CONFIG_CPU_V7M)
+/*
+ * Use 0 here to get code right that creates a userspace
+ * or kernel space thread.
+ */
+#define USR_MODE	0x00000000
+#define SVC_MODE	0x00000000
+#else
 #define USR_MODE	0x00000010
+#define SVC_MODE	0x00000013
+#endif
 #define FIQ_MODE	0x00000011
 #define IRQ_MODE	0x00000012
-#define SVC_MODE	0x00000013
 #define ABT_MODE	0x00000017
 #define HYP_MODE	0x0000001a
 #define UND_MODE	0x0000001b
 #define SYSTEM_MODE	0x0000001f
 #define MODE32_BIT	0x00000010
 #define MODE_MASK	0x0000001f
-#define PSR_T_BIT	0x00000020
-#define PSR_F_BIT	0x00000040
-#define PSR_I_BIT	0x00000080
-#define PSR_A_BIT	0x00000100
-#define PSR_E_BIT	0x00000200
-#define PSR_J_BIT	0x01000000
-#define PSR_Q_BIT	0x08000000
+
+#define V4_PSR_T_BIT	0x00000020	/* >= V4T, but not V7M */
+#define V7M_PSR_T_BIT	0x01000000
+#if defined(__KERNEL__) && defined(CONFIG_CPU_V7M)
+#define PSR_T_BIT	V7M_PSR_T_BIT
+#else
+/* for compatibility */
+#define PSR_T_BIT	V4_PSR_T_BIT
+#endif
+
+#define PSR_F_BIT	0x00000040	/* >= V4, but not V7M */
+#define PSR_I_BIT	0x00000080	/* >= V4, but not V7M */
+#define PSR_A_BIT	0x00000100	/* >= V6, but not V7M */
+#define PSR_E_BIT	0x00000200	/* >= V6, but not V7M */
+#define PSR_J_BIT	0x01000000	/* >= V5J, but not V7M */
+#define PSR_Q_BIT	0x08000000	/* >= V5E, including V7M */
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000
 #define PSR_Z_BIT	0x40000000
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@ -15,7 +15,7 @@ CFLAGS_REMOVE_return_address.o = -pg

 # Object file lists.

-obj-y		:= elf.o entry-armv.o entry-common.o irq.o opcodes.o \
+obj-y		:= elf.o entry-common.o irq.o opcodes.o \
 		   process.o ptrace.o return_address.o sched_clock.o \
 		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o

@ -23,6 +23,12 @@ obj-$(CONFIG_ATAGS)		+= atags_parse.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o

+ifeq ($(CONFIG_CPU_V7M),y)
+obj-y		+= entry-v7m.o
+else
+obj-y		+= entry-armv.o
+endif
+
 obj-$(CONFIG_OC_ETM)		+= etm.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
@ -32,7 +38,10 @@ obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
 obj-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o suspend.o
-obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
+obj-$(CONFIG_SMP)		+= smp.o
+ifdef CONFIG_MMU
+obj-$(CONFIG_SMP)		+= smp_tlb.o
+endif
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
 obj-$(CONFIG_HAVE_ARM_TWD)	+= smp_twd.o
 obj-$(CONFIG_ARM_ARCH_TIMER)	+= arch_timer.o
@ -82,6 +91,9 @@ obj-$(CONFIG_DEBUG_LL)	+= debug.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o

 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
-obj-$(CONFIG_ARM_PSCI)		+= psci.o
+ifeq ($(CONFIG_ARM_PSCI),y)
+obj-y				+= psci.o
+obj-$(CONFIG_SMP)		+= psci_smp.o
+endif

 extra-y := $(head-y) vmlinux.lds
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@ -23,6 +23,7 @@
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/procinfo.h>
+#include <asm/suspend.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <linux/kbuild.h>

@ -144,6 +145,11 @@ int main(void)
 #endif
 #ifdef MULTI_CACHE
  DEFINE(CACHE_FLUSH_KERN_ALL,	offsetof(struct cpu_cache_fns, flush_kern_all));
+#endif
+#ifdef CONFIG_ARM_CPU_SUSPEND
+  DEFINE(SLEEP_SAVE_SP_SZ,	sizeof(struct sleep_save_sp));
+  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
  BLANK();
  DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@ -350,6 +350,9 @@ ENDPROC(ftrace_stub)

 	.align	5
 ENTRY(vector_swi)
+#ifdef CONFIG_CPU_V7M
+	v7m_exception_entry
+#else
 	sub	sp, sp, #S_FRAME_SIZE
 	stmia	sp, {r0 - r12}			@ Calling r0 - r12
 ARM(	add	r8, sp, #S_PC		)
@ -360,6 +363,7 @@ ENTRY(vector_swi)
 	str	lr, [sp, #S_PC]			@ Save calling PC
 	str	r8, [sp, #S_PSR]		@ Save CPSR
 	str	r0, [sp, #S_OLD_R0]		@ Save OLD_R0
+#endif
 	zero_fp

 #ifdef CONFIG_ALIGNMENT_TRAP
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@ -5,6 +5,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/errno.h>
 #include <asm/thread_info.h>
+#include <asm/v7m.h>

@ Bad Abort numbers
@ -----------------
@ -44,6 +45,116 @@
 #endif
 	.endm

+#ifdef CONFIG_CPU_V7M
+/*
+ * ARMv7-M exception entry/exit macros.
+ *
+ * xPSR, ReturnAddress(), LR (R14), R12, R3, R2, R1, and R0 are
+ * automatically saved on the current stack (32 words) before
+ * switching to the exception stack (SP_main).
+ *
+ * If exception is taken while in user mode, SP_main is
+ * empty. Otherwise, SP_main is aligned to 64 bit automatically
+ * (CCR.STKALIGN set).
+ *
+ * Linux assumes that the interrupts are disabled when entering an
+ * exception handler and it may BUG if this is not the case. Interrupts
+ * are disabled during entry and reenabled in the exit macro.
+ *
+ * v7m_exception_slow_exit is used when returning from SVC or PendSV.
+ * When returning to kernel mode, we don't return from exception.
+ */
+	.macro	v7m_exception_entry
+	@ determine the location of the registers saved by the core during
+	@ exception entry. Depending on the mode the cpu was in when the
+	@ exception happend that is either on the main or the process stack.
+	@ Bit 2 of EXC_RETURN stored in the lr register specifies which stack
+	@ was used.
+	tst	lr, #EXC_RET_STACK_MASK
+	mrsne	r12, psp
+	moveq	r12, sp
+
+	@ we cannot rely on r0-r3 and r12 matching the value saved in the
+	@ exception frame because of tail-chaining. So these have to be
+	@ reloaded.
+	ldmia	r12!, {r0-r3}
+
+	@ Linux expects to have irqs off. Do it here before taking stack space
+	cpsid	i
+
+	sub	sp, #S_FRAME_SIZE-S_IP
+	stmdb	sp!, {r0-r11}
+
+	@ load saved r12, lr, return address and xPSR.
+	@ r0-r7 are used for signals and never touched from now on. Clobbering
+	@ r8-r12 is OK.
+	mov	r9, r12
+	ldmia	r9!, {r8, r10-r12}
+
+	@ calculate the original stack pointer value.
+	@ r9 currently points to the memory location just above the auto saved
+	@ xPSR.
+	@ The cpu might automatically 8-byte align the stack. Bit 9
+	@ of the saved xPSR specifies if stack aligning took place. In this case
+	@ another 32-bit value is included in the stack.
+
+	tst	r12, V7M_xPSR_FRAMEPTRALIGN
+	addne	r9, r9, #4
+
+	@ store saved r12 using str to have a register to hold the base for stm
+	str	r8, [sp, #S_IP]
+	add	r8, sp, #S_SP
+	@ store r13-r15, xPSR
+	stmia	r8!, {r9-r12}
+	@ store old_r0
+	str	r0, [r8]
+	.endm
+
+        /*
+	 * PENDSV and SVCALL are configured to have the same exception
+	 * priorities. As a kernel thread runs at SVCALL execution priority it
+	 * can never be preempted and so we will never have to return to a
+	 * kernel thread here.
+         */
+	.macro	v7m_exception_slow_exit ret_r0
+	cpsid	i
+	ldr	lr, =EXC_RET_THREADMODE_PROCESSSTACK
+
+	@ read original r12, sp, lr, pc and xPSR
+	add	r12, sp, #S_IP
+	ldmia	r12, {r1-r5}
+
+	@ an exception frame is always 8-byte aligned. To tell the hardware if
+	@ the sp to be restored is aligned or not set bit 9 of the saved xPSR
+	@ accordingly.
+	tst	r2, #4
+	subne	r2, r2, #4
+	orrne	r5, V7M_xPSR_FRAMEPTRALIGN
+	biceq	r5, V7M_xPSR_FRAMEPTRALIGN
+
+	@ write basic exception frame
+	stmdb	r2!, {r1, r3-r5}
+	ldmia	sp, {r1, r3-r5}
+	.if	\ret_r0
+	stmdb	r2!, {r0, r3-r5}
+	.else
+	stmdb	r2!, {r1, r3-r5}
+	.endif
+
+	@ restore process sp
+	msr	psp, r2
+
+	@ restore original r4-r11
+	ldmia	sp!, {r0-r11}
+
+	@ restore main sp
+	add	sp, sp, #S_FRAME_SIZE-S_IP
+
+	cpsie	i
+	bx	lr
+	.endm
+#endif	/* CONFIG_CPU_V7M */
+
 	@
 	@ Store/load the USER SP and LR registers by switching to the SYS
 	@ mode. Useful in Thumb-2 mode where "stm/ldm rd, {sp, lr}^" is not
@ -165,6 +276,18 @@
 	rfeia	sp!
 	.endm

+#ifdef CONFIG_CPU_V7M
+	/*
+	 * Note we don't need to do clrex here as clearing the local monitor is
+	 * part of each exception entry and exit sequence.
+	 */
+	.macro	restore_user_regs, fast = 0, offset = 0
+	.if	\offset
+	add	sp, #\offset
+	.endif
+	v7m_exception_slow_exit ret_r0 = \fast
+	.endm
+#else	/* ifdef CONFIG_CPU_V7M */
 	.macro	restore_user_regs, fast = 0, offset = 0
 	clrex					@ clear the exclusive monitor
 	mov	r2, sp
@ -181,6 +304,7 @@
 	add	sp, sp, #S_FRAME_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
+#endif	/* ifdef CONFIG_CPU_V7M / else */

 	.macro	get_thread_info, rd
 	mov	\rd, sp
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@ -0,0 +1,143 @@
+/*
+ * linux/arch/arm/kernel/entry-v7m.S
+ *
+ * Copyright (C) 2008 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Low-level vector interface routines for the ARMv7-M architecture
+ */
+#include <asm/memory.h>
+#include <asm/glue.h>
+#include <asm/thread_notify.h>
+#include <asm/v7m.h>
+
+#include <mach/entry-macro.S>
+
+#include "entry-header.S"
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+#error "CONFIG_TRACE_IRQFLAGS not supported on the current ARMv7M implementation"
+#endif
+
+__invalid_entry:
+	v7m_exception_entry
+	adr	r0, strerr
+	mrs	r1, ipsr
+	mov	r2, lr
+	bl	printk
+	mov	r0, sp
+	bl	show_regs
+1:	b	1b
+ENDPROC(__invalid_entry)
+
+strerr:	.asciz	"\nUnhandled exception: IPSR = %08lx LR = %08lx\n"
+
+	.align	2
+__irq_entry:
+	v7m_exception_entry
+
+	@
+	@ Invoke the IRQ handler
+	@
+	mrs	r0, ipsr
+	ldr	r1, =V7M_xPSR_EXCEPTIONNO
+	and	r0, r1
+	sub	r0, #16
+	mov	r1, sp
+	stmdb	sp!, {lr}
+	@ routine called with r0 = irq number, r1 = struct pt_regs *
+	bl	nvic_do_IRQ
+
+	pop	{lr}
+	@
+	@ Check for any pending work if returning to user
+	@
+	ldr	r1, =BASEADDR_V7M_SCB
+	ldr	r0, [r1, V7M_SCB_ICSR]
+	tst	r0, V7M_SCB_ICSR_RETTOBASE
+	beq	2f
+
+	get_thread_info tsk
+	ldr	r2, [tsk, #TI_FLAGS]
+	tst	r2, #_TIF_WORK_MASK
+	beq	2f			@ no work pending
+	mov	r0, #V7M_SCB_ICSR_PENDSVSET
+	str	r0, [r1, V7M_SCB_ICSR]	@ raise PendSV
+
+2:
+	@ registers r0-r3 and r12 are automatically restored on exception
+	@ return. r4-r7 were not clobbered in v7m_exception_entry so for
+	@ correctness they don't need to be restored. So only r8-r11 must be
+	@ restored here. The easiest way to do so is to restore r0-r7, too.
+	ldmia	sp!, {r0-r11}
+	add	sp, #S_FRAME_SIZE-S_IP
+	cpsie	i
+	bx	lr
+ENDPROC(__irq_entry)
+
+__pendsv_entry:
+	v7m_exception_entry
+
+	ldr	r1, =BASEADDR_V7M_SCB
+	mov	r0, #V7M_SCB_ICSR_PENDSVCLR
+	str	r0, [r1, V7M_SCB_ICSR]	@ clear PendSV
+
+	@ execute the pending work, including reschedule
+	get_thread_info tsk
+	mov	why, #0
+	b	ret_to_user
+ENDPROC(__pendsv_entry)
+
+/*
+ * Register switch for ARMv7-M processors.
+ * r0 = previous task_struct, r1 = previous thread_info, r2 = next thread_info
+ * previous and next are guaranteed not to be the same.
+ */
+ENTRY(__switch_to)
+	.fnstart
+	.cantunwind
+	add	ip, r1, #TI_CPU_SAVE
+	stmia	ip!, {r4 - r11}		@ Store most regs on stack
+	str	sp, [ip], #4
+	str	lr, [ip], #4
+	mov	r5, r0
+	add	r4, r2, #TI_CPU_SAVE
+	ldr	r0, =thread_notify_head
+	mov	r1, #THREAD_NOTIFY_SWITCH
+	bl	atomic_notifier_call_chain
+	mov	ip, r4
+	mov	r0, r5
+	ldmia	ip!, {r4 - r11}		@ Load all regs saved previously
+	ldr	sp, [ip]
+	ldr	pc, [ip, #4]!
+	.fnend
+ENDPROC(__switch_to)
+
+	.data
+	.align	8
+/*
+ * Vector table (64 words => 256 bytes natural alignment)
+ */
+ENTRY(vector_table)
+	.long	0			@ 0 - Reset stack pointer
+	.long	__invalid_entry		@ 1 - Reset
+	.long	__invalid_entry		@ 2 - NMI
+	.long	__invalid_entry		@ 3 - HardFault
+	.long	__invalid_entry		@ 4 - MemManage
+	.long	__invalid_entry		@ 5 - BusFault
+	.long	__invalid_entry		@ 6 - UsageFault
+	.long	__invalid_entry		@ 7 - Reserved
+	.long	__invalid_entry		@ 8 - Reserved
+	.long	__invalid_entry		@ 9 - Reserved
+	.long	__invalid_entry		@ 10 - Reserved
+	.long	vector_swi		@ 11 - SVCall
+	.long	__invalid_entry		@ 12 - Debug Monitor
+	.long	__invalid_entry		@ 13 - Reserved
+	.long	__pendsv_entry		@ 14 - PendSV
+	.long	__invalid_entry		@ 15 - SysTick
+	.rept	64 - 16
+	.long	__irq_entry		@ 16..64 - External Interrupts
+	.endr
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@ -17,8 +17,12 @@
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/memory.h>
 #include <asm/cp15.h>
 #include <asm/thread_info.h>
+#include <asm/v7m.h>
+#include <asm/mpu.h>
+#include <asm/page.h>

 /*
 * Kernel startup entry point.
@ -50,20 +54,85 @@ ENTRY(stext)

 	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
+#if defined(CONFIG_CPU_CP15)
+	mrc	p15, 0, r9, c0, c0		@ get processor id
+#elif defined(CONFIG_CPU_V7M)
+	ldr	r9, =BASEADDR_V7M_SCB
+	ldr	r9, [r9, V7M_SCB_CPUID]
+#else
+	ldr	r9, =CONFIG_PROCESSOR_ID
+#endif
+	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
+	movs	r10, r5				@ invalid processor (r5=0)?
+	beq	__error_p				@ yes, error 'p'
+
+#ifdef CONFIG_ARM_MPU
+	/* Calculate the size of a region covering just the kernel */
+	ldr	r5, =PHYS_OFFSET		@ Region start: PHYS_OFFSET
+	ldr     r6, =(_end)			@ Cover whole kernel
+	sub	r6, r6, r5			@ Minimum size of region to map
+	clz	r6, r6				@ Region size must be 2^N...
+	rsb	r6, r6, #31			@ ...so round up region size
+	lsl	r6, r6, #MPU_RSR_SZ		@ Put size in right field
+	orr	r6, r6, #(1 << MPU_RSR_EN)	@ Set region enabled bit
+	bl	__setup_mpu
+#endif
+	ldr	r13, =__mmap_switched		@ address to jump to after
+						@ initialising sctlr
+	adr	lr, BSYM(1f)			@ return (PIC) address
+ ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
+ THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
+ THUMB(	mov	pc, r12				)
+ 1:	b	__after_proc_init
+ENDPROC(stext)
+
+#ifdef CONFIG_SMP
+	__CPUINIT
+ENTRY(secondary_startup)
+	/*
+	 * Common entry point for secondary CPUs.
+	 *
+	 * Ensure that we're in SVC mode, and IRQs are disabled.  Lookup
+	 * the processor type - there is no need to check the machine type
+	 * as it has already been validated by the primary processor.
+	 */
+	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
 #ifndef CONFIG_CPU_CP15
 	ldr	r9, =CONFIG_PROCESSOR_ID
 #else
 	mrc	p15, 0, r9, c0, c0		@ get processor id
 #endif
 	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
-	movs	r10, r5				@ invalid processor (r5=0)?
-	beq	__error_p				@ yes, error 'p'
+	movs	r10, r5				@ invalid processor?
+	beq	__error_p			@ yes, error 'p'

-	adr	lr, BSYM(__after_proc_init)	@ return (PIC) address
+	adr	r4, __secondary_data
+	ldmia	r4, {r7, r12}
+
+#ifdef CONFIG_ARM_MPU
+	/* Use MPU region info supplied by __cpu_up */
+	ldr	r6, [r7]			@ get secondary_data.mpu_szr
+	bl      __setup_mpu			@ Initialize the MPU
+#endif
+
+	adr	lr, BSYM(__after_proc_init)	@ return address
+	mov	r13, r12			@ __secondary_switched address
 ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
 THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
 THUMB(	mov	pc, r12				)
-ENDPROC(stext)
+ENDPROC(secondary_startup)
+
+ENTRY(__secondary_switched)
+	ldr	sp, [r7, #8]			@ set up the stack pointer
+	mov	fp, #0
+	b	secondary_start_kernel
+ENDPROC(__secondary_switched)
+
+	.type	__secondary_data, %object
+__secondary_data:
+	.long	secondary_data
+	.long	__secondary_switched
+#endif /* CONFIG_SMP */

 /*
 * Set the Control Register and Read the process ID.
@ -95,10 +164,97 @@ __after_proc_init:
 #endif
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
 #endif /* CONFIG_CPU_CP15 */
-
-	b	__mmap_switched			@ clear the BSS and jump
-						@ to start_kernel
+	mov	pc, r13
 ENDPROC(__after_proc_init)
 	.ltorg

+#ifdef CONFIG_ARM_MPU
+
+
+/* Set which MPU region should be programmed */
+.macro set_region_nr tmp, rgnr
+	mov	\tmp, \rgnr			@ Use static region numbers
+	mcr	p15, 0, \tmp, c6, c2, 0		@ Write RGNR
+.endm
+
+/* Setup a single MPU region, either D or I side (D-side for unified) */
+.macro setup_region bar, acr, sr, side = MPU_DATA_SIDE
+	mcr	p15, 0, \bar, c6, c1, (0 + \side)	@ I/DRBAR
+	mcr	p15, 0, \acr, c6, c1, (4 + \side)	@ I/DRACR
+	mcr	p15, 0, \sr, c6, c1, (2 + \side)		@ I/DRSR
+.endm
+
+/*
+ * Setup the MPU and initial MPU Regions. We create the following regions:
+ * Region 0: Use this for probing the MPU details, so leave disabled.
+ * Region 1: Background region - covers the whole of RAM as strongly ordered
+ * Region 2: Normal, Shared, cacheable for RAM. From PHYS_OFFSET, size from r6
+ * Region 3: Normal, shared, inaccessible from PL0 to protect the vectors page
+ *
+ * r6: Value to be written to DRSR (and IRSR if required) for MPU_RAM_REGION
+*/
+
+ENTRY(__setup_mpu)
+
+	/* Probe for v7 PMSA compliance */
+	mrc	p15, 0, r0, c0, c1, 4		@ Read ID_MMFR0
+	and	r0, r0, #(MMFR0_PMSA)		@ PMSA field
+	teq	r0, #(MMFR0_PMSAv7)		@ PMSA v7
+	bne	__error_p			@ Fail: ARM_MPU on NOT v7 PMSA
+
+	/* Determine whether the D/I-side memory map is unified. We set the
+	 * flags here and continue to use them for the rest of this function */
+	mrc	p15, 0, r0, c0, c0, 4		@ MPUIR
+	ands	r5, r0, #MPUIR_DREGION_SZMASK	@ 0 size d region => No MPU
+	beq	__error_p			@ Fail: ARM_MPU and no MPU
+	tst	r0, #MPUIR_nU			@ MPUIR_nU = 0 for unified
+
+	/* Setup second region first to free up r6 */
+	set_region_nr r0, #MPU_RAM_REGION
+	isb
+	/* Full access from PL0, PL1, shared for CONFIG_SMP, cacheable */
+	ldr	r0, =PHYS_OFFSET		@ RAM starts at PHYS_OFFSET
+	ldr	r5,=(MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL)
+
+	setup_region r0, r5, r6, MPU_DATA_SIDE	@ PHYS_OFFSET, shared, enabled
+	beq	1f				@ Memory-map not unified
+	setup_region r0, r5, r6, MPU_INSTR_SIDE @ PHYS_OFFSET, shared, enabled
+1:	isb
+
+	/* First/background region */
+	set_region_nr r0, #MPU_BG_REGION
+	isb
+	/* Execute Never,  strongly ordered, inaccessible to PL0, rw PL1  */
+	mov	r0, #0				@ BG region starts at 0x0
+	ldr	r5,=(MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0NA)
+	mov	r6, #MPU_RSR_ALL_MEM		@ 4GB region, enabled
+
+	setup_region r0, r5, r6, MPU_DATA_SIDE	@ 0x0, BG region, enabled
+	beq	2f				@ Memory-map not unified
+	setup_region r0, r5, r6, MPU_INSTR_SIDE @ 0x0, BG region, enabled
+2:	isb
+
+	/* Vectors region */
+	set_region_nr r0, #MPU_VECTORS_REGION
+	isb
+	/* Shared, inaccessible to PL0, rw PL1 */
+	mov	r0, #CONFIG_VECTORS_BASE	@ Cover from VECTORS_BASE
+	ldr	r5,=(MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL)
+	/* Writing N to bits 5:1 (RSR_SZ) --> region size 2^N+1 */
+	mov	r6, #(((PAGE_SHIFT - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN)
+
+	setup_region r0, r5, r6, MPU_DATA_SIDE	@ VECTORS_BASE, PL0 NA, enabled
+	beq	3f				@ Memory-map not unified
+	setup_region r0, r5, r6, MPU_INSTR_SIDE	@ VECTORS_BASE, PL0 NA, enabled
+3:	isb
+
+	/* Enable the MPU */
+	mrc	p15, 0, r0, c1, c0, 0		@ Read SCTLR
+	bic     r0, r0, #CR_BR			@ Disable the 'default mem-map'
+	orr	r0, r0, #CR_M			@ Set SCTRL.M (MPU on)
+	mcr	p15, 0, r0, c1, c0, 0		@ Enable MPU
+	isb
+	mov pc,lr
+ENDPROC(__setup_mpu)
+#endif
 #include "head-common.S"
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@ -156,7 +156,7 @@ ENDPROC(stext)
 *
 * Returns:
 *  r0, r3, r5-r7 corrupted
- *  r4 = physical page table address
+ *  r4 = page table (see ARCH_PGD_SHIFT in asm/memory.h)
 */
 __create_page_tables:
 	pgtbl	r4, r8				@ page table address
@ -331,6 +331,7 @@ __create_page_tables:
 #endif
 #ifdef CONFIG_ARM_LPAE
 	sub	r4, r4, #0x1000		@ point to the PGD table
+	mov	r4, r4, lsr #ARCH_PGD_SHIFT
 #endif
 	mov	pc, lr
 ENDPROC(__create_page_tables)
@ -408,7 +409,7 @@ __secondary_data:
 *  r0  = cp#15 control register
 *  r1  = machine ID
 *  r2  = atags or dtb pointer
- *  r4  = page table pointer
+ *  r4  = page table (see ARCH_PGD_SHIFT in asm/memory.h)
 *  r9  = processor ID
 *  r13 = *virtual* address to jump to upon completion
 */
@ -427,10 +428,7 @@ __enable_mmu:
 #ifdef CONFIG_CPU_ICACHE_DISABLE
 	bic	r0, r0, #CR_I
 #endif
-#ifdef CONFIG_ARM_LPAE
-	mov	r5, #0
-	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
-#else
+#ifndef CONFIG_ARM_LPAE
 	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@ -153,6 +153,13 @@ THUMB(	orr	r7, #(1 << 30)	)	@ HSCTLR.TE
 	mrc	p15, 4, r7, c14, c1, 0	@ CNTHCTL
 	orr	r7, r7, #3		@ PL1PCEN | PL1PCTEN
 	mcr	p15, 4, r7, c14, c1, 0	@ CNTHCTL
+	mov	r7, #0
+	mcrr	p15, 4, r7, r7, c14	@ CNTVOFF
+
+	@ Disable virtual timer in case it was counting
+	mrc	p15, 0, r7, c14, c3, 1	@ CNTV_CTL
+	bic	r7, #1			@ Clear ENABLE
+	mcr	p15, 0, r7, c14, c3, 1	@ CNTV_CTL
 1:
 #endif

--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@ -158,7 +158,7 @@ static const struct of_device_id psci_of_match[] __initconst = {
 	{},
 };

-static int __init psci_init(void)
+void __init psci_init(void)
 {
 	struct device_node *np;
 	const char *method;
@ -166,7 +166,7 @@ static int __init psci_init(void)

 	np = of_find_matching_node(NULL, psci_of_match);
 	if (!np)
-		return 0;
+		return;

 	pr_info("probing function IDs from device-tree\n");

@ -206,6 +206,5 @@ static int __init psci_init(void)

 out_put_node:
 	of_node_put(np);
-	return 0;
+	return;
 }
-early_initcall(psci_init);
--- a/arch/arm/kernel/psci_smp.c
+++ b/arch/arm/kernel/psci_smp.c
@ -0,0 +1,84 @@
+/*
+ * 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) 2012 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/init.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/smp.h>
+#include <linux/of.h>
+
+#include <asm/psci.h>
+#include <asm/smp_plat.h>
+
+/*
+ * psci_smp assumes that the following is true about PSCI:
+ *
+ * cpu_suspend   Suspend the execution on a CPU
+ * @state        we don't currently describe affinity levels, so just pass 0.
+ * @entry_point  the first instruction to be executed on return
+ * returns 0  success, < 0 on failure
+ *
+ * cpu_off       Power down a CPU
+ * @state        we don't currently describe affinity levels, so just pass 0.
+ * no return on successful call
+ *
+ * cpu_on        Power up a CPU
+ * @cpuid        cpuid of target CPU, as from MPIDR
+ * @entry_point  the first instruction to be executed on return
+ * returns 0  success, < 0 on failure
+ *
+ * migrate       Migrate the context to a different CPU
+ * @cpuid        cpuid of target CPU, as from MPIDR
+ * returns 0  success, < 0 on failure
+ *
+ */
+
+extern void secondary_startup(void);
+
+static int __cpuinit psci_boot_secondary(unsigned int cpu,
+					 struct task_struct *idle)
+{
+	if (psci_ops.cpu_on)
+		return psci_ops.cpu_on(cpu_logical_map(cpu),
+				       __pa(secondary_startup));
+	return -ENODEV;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+void __ref psci_cpu_die(unsigned int cpu)
+{
+       const struct psci_power_state ps = {
+               .type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
+       };
+
+       if (psci_ops.cpu_off)
+               psci_ops.cpu_off(ps);
+
+       /* We should never return */
+       panic("psci: cpu %d failed to shutdown\n", cpu);
+}
+#endif
+
+bool __init psci_smp_available(void)
+{
+	/* is cpu_on available at least? */
+	return (psci_ops.cpu_on != NULL);
+}
+
+struct smp_operations __initdata psci_smp_ops = {
+	.smp_boot_secondary	= psci_boot_secondary,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_die		= psci_cpu_die,
+#endif
+};
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@ -37,6 +37,7 @@
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/procinfo.h>
+#include <asm/psci.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@ -128,7 +129,9 @@ struct stack {
 	u32 und[3];
 } ____cacheline_aligned;

+#ifndef CONFIG_CPU_V7M
 static struct stack stacks[NR_CPUS];
+#endif

 char elf_platform[ELF_PLATFORM_SIZE];
 EXPORT_SYMBOL(elf_platform);
@ -207,7 +210,7 @@ static const char *proc_arch[] = {
 	"5TEJ",
 	"6TEJ",
 	"7",
-	"?(11)",
+	"7M",
 	"?(12)",
 	"?(13)",
 	"?(14)",
@ -216,6 +219,12 @@ static const char *proc_arch[] = {
 	"?(17)",
 };

+#ifdef CONFIG_CPU_V7M
+static int __get_cpu_architecture(void)
+{
+	return CPU_ARCH_ARMv7M;
+}
+#else
 static int __get_cpu_architecture(void)
 {
 	int cpu_arch;
@ -248,6 +257,7 @@ static int __get_cpu_architecture(void)

 	return cpu_arch;
 }
+#endif

 int __pure cpu_architecture(void)
 {
@ -293,7 +303,9 @@ static void __init cacheid_init(void)
 {
 	unsigned int arch = cpu_architecture();

-	if (arch >= CPU_ARCH_ARMv6) {
+	if (arch == CPU_ARCH_ARMv7M) {
+		cacheid = 0;
+	} else if (arch >= CPU_ARCH_ARMv6) {
 		unsigned int cachetype = read_cpuid_cachetype();
 		if ((cachetype & (7 << 29)) == 4 << 29) {
 			/* ARMv7 register format */
@ -355,7 +367,7 @@ void __init early_print(const char *str, ...)

 static void __init cpuid_init_hwcaps(void)
 {
-	unsigned int divide_instrs;
+	unsigned int divide_instrs, vmsa;

 	if (cpu_architecture() < CPU_ARCH_ARMv7)
 		return;
@ -368,6 +380,11 @@ static void __init cpuid_init_hwcaps(void)
 	case 1:
 		elf_hwcap |= HWCAP_IDIVT;
 	}
+
+	/* LPAE implies atomic ldrd/strd instructions */
+	vmsa = (read_cpuid_ext(CPUID_EXT_MMFR0) & 0xf) >> 0;
+	if (vmsa >= 5)
+		elf_hwcap |= HWCAP_LPAE;
 }

 static void __init feat_v6_fixup(void)
@ -392,6 +409,7 @@ static void __init feat_v6_fixup(void)
 */
 void notrace cpu_init(void)
 {
+#ifndef CONFIG_CPU_V7M
 	unsigned int cpu = smp_processor_id();
 	struct stack *stk = &stacks[cpu];

@ -442,6 +460,7 @@ void notrace cpu_init(void)
 	      "I" (offsetof(struct stack, und[0])),
 	      PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
 	    : "r14");
+#endif
 }

 u32 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = MPIDR_INVALID };
@ -466,6 +485,72 @@ void __init smp_setup_processor_id(void)
 	printk(KERN_INFO "Booting Linux on physical CPU 0x%x\n", mpidr);
 }

+struct mpidr_hash mpidr_hash;
+#ifdef CONFIG_SMP
+/**
+ * smp_build_mpidr_hash - Pre-compute shifts required at each affinity
+ *			  level in order to build a linear index from an
+ *			  MPIDR value. Resulting algorithm is a collision
+ *			  free hash carried out through shifting and ORing
+ */
+static void __init smp_build_mpidr_hash(void)
+{
+	u32 i, affinity;
+	u32 fs[3], bits[3], ls, mask = 0;
+	/*
+	 * Pre-scan the list of MPIDRS and filter out bits that do
+	 * not contribute to affinity levels, ie they never toggle.
+	 */
+	for_each_possible_cpu(i)
+		mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
+	pr_debug("mask of set bits 0x%x\n", mask);
+	/*
+	 * Find and stash the last and first bit set at all affinity levels to
+	 * check how many bits are required to represent them.
+	 */
+	for (i = 0; i < 3; i++) {
+		affinity = MPIDR_AFFINITY_LEVEL(mask, i);
+		/*
+		 * Find the MSB bit and LSB bits position
+		 * to determine how many bits are required
+		 * to express the affinity level.
+		 */
+		ls = fls(affinity);
+		fs[i] = affinity ? ffs(affinity) - 1 : 0;
+		bits[i] = ls - fs[i];
+	}
+	/*
+	 * An index can be created from the MPIDR by isolating the
+	 * significant bits at each affinity level and by shifting
+	 * them in order to compress the 24 bits values space to a
+	 * compressed set of values. This is equivalent to hashing
+	 * the MPIDR through shifting and ORing. It is a collision free
+	 * hash though not minimal since some levels might contain a number
+	 * of CPUs that is not an exact power of 2 and their bit
+	 * representation might contain holes, eg MPIDR[7:0] = {0x2, 0x80}.
+	 */
+	mpidr_hash.shift_aff[0] = fs[0];
+	mpidr_hash.shift_aff[1] = MPIDR_LEVEL_BITS + fs[1] - bits[0];
+	mpidr_hash.shift_aff[2] = 2*MPIDR_LEVEL_BITS + fs[2] -
+						(bits[1] + bits[0]);
+	mpidr_hash.mask = mask;
+	mpidr_hash.bits = bits[2] + bits[1] + bits[0];
+	pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] mask[0x%x] bits[%u]\n",
+				mpidr_hash.shift_aff[0],
+				mpidr_hash.shift_aff[1],
+				mpidr_hash.shift_aff[2],
+				mpidr_hash.mask,
+				mpidr_hash.bits);
+	/*
+	 * 4x is an arbitrary value used to warn on a hash table much bigger
+	 * than expected on most systems.
+	 */
+	if (mpidr_hash_size() > 4 * num_possible_cpus())
+		pr_warn("Large number of MPIDR hash buckets detected\n");
+	sync_cache_w(&mpidr_hash);
+}
+#endif
+
 static void __init setup_processor(void)
 {
 	struct proc_info_list *list;
@ -803,10 +888,17 @@ void __init setup_arch(char **cmdline_p)
 	unflatten_device_tree();

 	arm_dt_init_cpu_maps();
+	psci_init();
 #ifdef CONFIG_SMP
 	if (is_smp()) {
-		smp_set_ops(mdesc->smp);
+		if (!mdesc->smp_init || !mdesc->smp_init()) {
+			if (psci_smp_available())
+				smp_set_ops(&psci_smp_ops);
+			else if (mdesc->smp)
+				smp_set_ops(mdesc->smp);
+		}
 		smp_init_cpus();
+		smp_build_mpidr_hash();
 	}
 #endif

@ -879,6 +971,7 @@ static const char *hwcap_str[] = {
 	"vfpv4",
 	"idiva",
 	"idivt",
+	"lpae",
 	NULL
 };

--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@ -392,14 +392,19 @@ setup_return(struct pt_regs *regs, struct ksignal *ksig,
 		if (ksig->ka.sa.sa_flags & SA_SIGINFO)
 			idx += 3;

+		/*
+		 * Put the sigreturn code on the stack no matter which return
+		 * mechanism we use in order to remain ABI compliant
+		 */
 		if (__put_user(sigreturn_codes[idx],   rc) ||
 		    __put_user(sigreturn_codes[idx+1], rc+1))
 			return 1;

-		if (cpsr & MODE32_BIT) {
+		if ((cpsr & MODE32_BIT) && !IS_ENABLED(CONFIG_ARM_MPU)) {
 			/*
 			 * 32-bit code can use the new high-page
-			 * signal return code support.
+			 * signal return code support except when the MPU has
+			 * protected the vectors page from PL0
 			 */
 			retcode = KERN_SIGRETURN_CODE + (idx << 2) + thumb;
 		} else {
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@ -6,6 +6,49 @@
 #include <asm/glue-proc.h>
 	.text

+/*
+ * Implementation of MPIDR hash algorithm through shifting
+ * and OR'ing.
+ *
+ * @dst: register containing hash result
+ * @rs0: register containing affinity level 0 bit shift
+ * @rs1: register containing affinity level 1 bit shift
+ * @rs2: register containing affinity level 2 bit shift
+ * @mpidr: register containing MPIDR value
+ * @mask: register containing MPIDR mask
+ *
+ * Pseudo C-code:
+ *
+ *u32 dst;
+ *
+ *compute_mpidr_hash(u32 rs0, u32 rs1, u32 rs2, u32 mpidr, u32 mask) {
+ *	u32 aff0, aff1, aff2;
+ *	u32 mpidr_masked = mpidr & mask;
+ *	aff0 = mpidr_masked & 0xff;
+ *	aff1 = mpidr_masked & 0xff00;
+ *	aff2 = mpidr_masked & 0xff0000;
+ *	dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2);
+ *}
+ * Input registers: rs0, rs1, rs2, mpidr, mask
+ * Output register: dst
+ * Note: input and output registers must be disjoint register sets
+         (eg: a macro instance with mpidr = r1 and dst = r1 is invalid)
+ */
+	.macro compute_mpidr_hash dst, rs0, rs1, rs2, mpidr, mask
+	and	\mpidr, \mpidr, \mask			@ mask out MPIDR bits
+	and	\dst, \mpidr, #0xff			@ mask=aff0
+ ARM(	mov	\dst, \dst, lsr \rs0		)	@ dst=aff0>>rs0
+ THUMB(	lsr	\dst, \dst, \rs0		)
+	and	\mask, \mpidr, #0xff00			@ mask = aff1
+ ARM(	orr	\dst, \dst, \mask, lsr \rs1	)	@ dst|=(aff1>>rs1)
+ THUMB(	lsr	\mask, \mask, \rs1		)
+ THUMB(	orr	\dst, \dst, \mask		)
+	and	\mask, \mpidr, #0xff0000		@ mask = aff2
+ ARM(	orr	\dst, \dst, \mask, lsr \rs2	)	@ dst|=(aff2>>rs2)
+ THUMB(	lsr	\mask, \mask, \rs2		)
+ THUMB(	orr	\dst, \dst, \mask		)
+	.endm
+
 /*
 * Save CPU state for a suspend.  This saves the CPU general purpose
 * registers, and allocates space on the kernel stack to save the CPU
@ -29,12 +72,18 @@ ENTRY(__cpu_suspend)
 	mov	r1, r4			@ size of save block
 	mov	r2, r5			@ virtual SP
 	ldr	r3, =sleep_save_sp
-#ifdef CONFIG_SMP
-	ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
-	ALT_UP(mov lr, #0)
-	and	lr, lr, #15
+	ldr	r3, [r3, #SLEEP_SAVE_SP_VIRT]
+	ALT_SMP(mrc p15, 0, r9, c0, c0, 5)
+        ALT_UP_B(1f)
+	ldr	r8, =mpidr_hash
+	/*
+	 * This ldmia relies on the memory layout of the mpidr_hash
+	 * struct mpidr_hash.
+	 */
+	ldmia	r8, {r4-r7}	@ r4 = mpidr mask (r5,r6,r7) = l[0,1,2] shifts
+	compute_mpidr_hash	lr, r5, r6, r7, r9, r4
 	add	r3, r3, lr, lsl #2
-#endif
+1:
 	bl	__cpu_suspend_save
 	adr	lr, BSYM(cpu_suspend_abort)
 	ldmfd	sp!, {r0, pc}		@ call suspend fn
@ -81,15 +130,23 @@ ENDPROC(cpu_resume_after_mmu)
 	.data
 	.align
 ENTRY(cpu_resume)
-#ifdef CONFIG_SMP
-	adr	r0, sleep_save_sp
-	ALT_SMP(mrc p15, 0, r1, c0, c0, 5)
-	ALT_UP(mov r1, #0)
-	and	r1, r1, #15
-	ldr	r0, [r0, r1, lsl #2]	@ stack phys addr
-#else
-	ldr	r0, sleep_save_sp	@ stack phys addr
-#endif
+	mov	r1, #0
+	ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
+	ALT_UP_B(1f)
+	adr	r2, mpidr_hash_ptr
+	ldr	r3, [r2]
+	add	r2, r2, r3		@ r2 = struct mpidr_hash phys address
+	/*
+	 * This ldmia relies on the memory layout of the mpidr_hash
+	 * struct mpidr_hash.
+	 */
+	ldmia	r2, { r3-r6 }	@ r3 = mpidr mask (r4,r5,r6) = l[0,1,2] shifts
+	compute_mpidr_hash	r1, r4, r5, r6, r0, r3
+1:
+	adr	r0, _sleep_save_sp
+	ldr	r0, [r0, #SLEEP_SAVE_SP_PHYS]
+	ldr	r0, [r0, r1, lsl #2]
+
 	setmode	PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1  @ set SVC, irqs off
 	@ load phys pgd, stack, resume fn
  ARM(	ldmia	r0!, {r1, sp, pc}	)
@ -98,7 +155,11 @@ THUMB(	mov	sp, r2			)
 THUMB(	bx	r3			)
 ENDPROC(cpu_resume)

-sleep_save_sp:
-	.rept	CONFIG_NR_CPUS
-	.long	0				@ preserve stack phys ptr here
-	.endr
+	.align 2
+mpidr_hash_ptr:
+	.long	mpidr_hash - .			@ mpidr_hash struct offset
+
+	.type	sleep_save_sp, #object
+ENTRY(sleep_save_sp)
+_sleep_save_sp:
+	.space	SLEEP_SAVE_SP_SZ		@ struct sleep_save_sp
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@ -45,6 +45,7 @@
 #include <asm/smp_plat.h>
 #include <asm/virt.h>
 #include <asm/mach/arch.h>
+#include <asm/mpu.h>

 /*
 * as from 2.5, kernels no longer have an init_tasks structure
@ -78,6 +79,13 @@ void __init smp_set_ops(struct smp_operations *ops)
 		smp_ops = *ops;
 };

+static unsigned long get_arch_pgd(pgd_t *pgd)
+{
+	phys_addr_t pgdir = virt_to_phys(pgd);
+	BUG_ON(pgdir & ARCH_PGD_MASK);
+	return pgdir >> ARCH_PGD_SHIFT;
+}
+
 int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int ret;
@ -87,8 +95,14 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 	 * its stack and the page tables.
 	 */
 	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
-	secondary_data.pgdir = virt_to_phys(idmap_pgd);
-	secondary_data.swapper_pg_dir = virt_to_phys(swapper_pg_dir);
+#ifdef CONFIG_ARM_MPU
+	secondary_data.mpu_rgn_szr = mpu_rgn_info.rgns[MPU_RAM_REGION].drsr;
+#endif
+
+#ifdef CONFIG_MMU
+	secondary_data.pgdir = get_arch_pgd(idmap_pgd);
+	secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
+#endif
 	__cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1));

@ -112,9 +126,8 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
 		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
 	}

-	secondary_data.stack = NULL;
-	secondary_data.pgdir = 0;

+	memset(&secondary_data, 0, sizeof(secondary_data));
 	return ret;
 }

--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@ -1,15 +1,54 @@
 #include <linux/init.h>
+#include <linux/slab.h>

+#include <asm/cacheflush.h>
 #include <asm/idmap.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
+#include <asm/smp_plat.h>
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>

 extern int __cpu_suspend(unsigned long, int (*)(unsigned long));
 extern void cpu_resume_mmu(void);

+#ifdef CONFIG_MMU
+/*
+ * Hide the first two arguments to __cpu_suspend - these are an implementation
+ * detail which platform code shouldn't have to know about.
+ */
+int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+	struct mm_struct *mm = current->active_mm;
+	int ret;
+
+	if (!idmap_pgd)
+		return -EINVAL;
+
+	/*
+	 * Provide a temporary page table with an identity mapping for
+	 * the MMU-enable code, required for resuming.  On successful
+	 * resume (indicated by a zero return code), we need to switch
+	 * back to the correct page tables.
+	 */
+	ret = __cpu_suspend(arg, fn);
+	if (ret == 0) {
+		cpu_switch_mm(mm->pgd, mm);
+		local_flush_bp_all();
+		local_flush_tlb_all();
+	}
+
+	return ret;
+}
+#else
+int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+	return __cpu_suspend(arg, fn);
+}
+#define	idmap_pgd	NULL
+#endif
+
 /*
 * This is called by __cpu_suspend() to save the state, and do whatever
 * flushing is required to ensure that when the CPU goes to sleep we have
@ -47,30 +86,19 @@ void __cpu_suspend_save(u32 *ptr, u32 ptrsz, u32 sp, u32 *save_ptr)
 			  virt_to_phys(save_ptr) + sizeof(*save_ptr));
 }

-/*
- * Hide the first two arguments to __cpu_suspend - these are an implementation
- * detail which platform code shouldn't have to know about.
- */
-int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+extern struct sleep_save_sp sleep_save_sp;
+
+static int cpu_suspend_alloc_sp(void)
 {
-	struct mm_struct *mm = current->active_mm;
-	int ret;
+	void *ctx_ptr;
+	/* ctx_ptr is an array of physical addresses */
+	ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(u32), GFP_KERNEL);

-	if (!idmap_pgd)
-		return -EINVAL;
-
-	/*
-	 * Provide a temporary page table with an identity mapping for
-	 * the MMU-enable code, required for resuming.  On successful
-	 * resume (indicated by a zero return code), we need to switch
-	 * back to the correct page tables.
-	 */
-	ret = __cpu_suspend(arg, fn);
-	if (ret == 0) {
-		cpu_switch_mm(mm->pgd, mm);
-		local_flush_bp_all();
-		local_flush_tlb_all();
-	}
-
-	return ret;
+	if (WARN_ON(!ctx_ptr))
+		return -ENOMEM;
+	sleep_save_sp.save_ptr_stash = ctx_ptr;
+	sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
+	sync_cache_w(&sleep_save_sp);
+	return 0;
 }
+early_initcall(cpu_suspend_alloc_sp);
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@ -812,6 +812,7 @@ static void __init kuser_get_tls_init(unsigned long vectors)

 void __init early_trap_init(void *vectors_base)
 {
+#ifndef CONFIG_CPU_V7M
 	unsigned long vectors = (unsigned long)vectors_base;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
@ -843,4 +844,11 @@ void __init early_trap_init(void *vectors_base)

 	flush_icache_range(vectors, vectors + PAGE_SIZE);
 	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
+#else /* ifndef CONFIG_CPU_V7M */
+	/*
+	 * on V7-M there is no need to copy the vector table to a dedicated
+	 * memory area. The address is configurable and so a table in the kernel
+	 * image can be used.
+	 */
+#endif
 }
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@ -497,6 +497,10 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	add	r5, vcpu, r4
 	strd	r2, r3, [r5]

+	@ Ensure host CNTVCT == CNTPCT
+	mov	r2, #0
+	mcrr	p15, 4, r2, r2, c14	@ CNTVOFF
+
 1:
 #endif
 	@ Allow physical timer/counter access for the host
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@ -76,7 +76,7 @@ config SOC_EXYNOS5440
 	default y
 	depends on ARCH_EXYNOS5
 	select ARCH_HAS_OPP
-	select ARM_ARCH_TIMER
+	select HAVE_ARM_ARCH_TIMER
 	select AUTO_ZRELADDR
 	select PINCTRL
 	select PINCTRL_EXYNOS5440
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@ -23,7 +23,7 @@ config ARCH_R8A73A4
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_GIC
 	select CPU_V7
-	select ARM_ARCH_TIMER
+	select HAVE_ARM_ARCH_TIMER
 	select SH_CLK_CPG
 	select RENESAS_IRQC

@ -56,7 +56,7 @@ config ARCH_R8A7790
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_GIC
 	select CPU_V7
-	select ARM_ARCH_TIMER
+	select HAVE_ARM_ARCH_TIMER
 	select SH_CLK_CPG
 	select RENESAS_IRQC

--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@ -60,7 +60,7 @@ config ARCH_TEGRA_3x_SOC

 config ARCH_TEGRA_114_SOC
 	bool "Enable support for Tegra114 family"
-	select ARM_ARCH_TIMER
+	select HAVE_ARM_ARCH_TIMER
 	select ARM_GIC
 	select ARM_L1_CACHE_SHIFT_6
 	select CPU_FREQ_TABLE if CPU_FREQ
--- a/arch/arm/mach-virt/Kconfig
+++ b/arch/arm/mach-virt/Kconfig
@ -2,7 +2,7 @@ config ARCH_VIRT
 	bool "Dummy Virtual Machine" if ARCH_MULTI_V7
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARM_GIC
-	select ARM_ARCH_TIMER
+	select HAVE_ARM_ARCH_TIMER
 	select ARM_PSCI
 	select HAVE_SMP
 	select CPU_V7
--- a/arch/arm/mach-virt/Makefile
+++ b/arch/arm/mach-virt/Makefile
@ -3,4 +3,3 @@
 #

 obj-y					:= virt.o
-obj-$(CONFIG_SMP)			+= platsmp.o
--- a/arch/arm/mach-virt/platsmp.c
+++ b/arch/arm/mach-virt/platsmp.c
@ -1,50 +0,0 @@
-/*
- * Dummy Virtual Machine - does what it says on the tin.
- *
- * Copyright (C) 2012 ARM Ltd
- * Author: Will Deacon <will.deacon@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/of.h>
-
-#include <asm/psci.h>
-#include <asm/smp_plat.h>
-
-extern void secondary_startup(void);
-
-static void __init virt_smp_init_cpus(void)
-{
-}
-
-static void __init virt_smp_prepare_cpus(unsigned int max_cpus)
-{
-}
-
-static int __cpuinit virt_boot_secondary(unsigned int cpu,
-					 struct task_struct *idle)
-{
-	if (psci_ops.cpu_on)
-		return psci_ops.cpu_on(cpu_logical_map(cpu),
-				       __pa(secondary_startup));
-	return -ENODEV;
-}
-
-struct smp_operations __initdata virt_smp_ops = {
-	.smp_init_cpus		= virt_smp_init_cpus,
-	.smp_prepare_cpus	= virt_smp_prepare_cpus,
-	.smp_boot_secondary	= virt_boot_secondary,
-};
--- a/arch/arm/mach-virt/virt.c
+++ b/arch/arm/mach-virt/virt.c
@ -36,11 +36,8 @@ static const char *virt_dt_match[] = {
 	NULL
 };

-extern struct smp_operations virt_smp_ops;
-
 DT_MACHINE_START(VIRT, "Dummy Virtual Machine")
 	.init_irq	= irqchip_init,
 	.init_machine	= virt_init,
-	.smp		= smp_ops(virt_smp_ops),
 	.dt_compat	= virt_dt_match,
 MACHINE_END
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@ -392,11 +392,21 @@ config CPU_V7
 	select CPU_CACHE_V7
 	select CPU_CACHE_VIPT
 	select CPU_COPY_V6 if MMU
-	select CPU_CP15_MMU
+	select CPU_CP15_MMU if MMU
+	select CPU_CP15_MPU if !MMU
 	select CPU_HAS_ASID if MMU
 	select CPU_PABRT_V7
 	select CPU_TLB_V7 if MMU

+# ARMv7M
+config CPU_V7M
+	bool
+	select CPU_32v7M
+	select CPU_ABRT_NOMMU
+	select CPU_CACHE_NOP
+	select CPU_PABRT_LEGACY
+	select CPU_THUMBONLY
+
 config CPU_THUMBONLY
 	bool
 	# There are no CPUs available with MMU that don't implement an ARM ISA:
@ -441,6 +451,9 @@ config CPU_32v6K
 config CPU_32v7
 	bool

+config CPU_32v7M
+	bool
+
 # The abort model
 config CPU_ABRT_NOMMU
 	bool
@ -491,6 +504,9 @@ config CPU_CACHE_V6
 config CPU_CACHE_V7
 	bool

+config CPU_CACHE_NOP
+	bool
+
 config CPU_CACHE_VIVT
 	bool

@ -613,7 +629,11 @@ config ARCH_DMA_ADDR_T_64BIT

 config ARM_THUMB
 	bool "Support Thumb user binaries" if !CPU_THUMBONLY
-	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
+	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || \
+		CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || \
+		CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || \
+		CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || \
+		CPU_V7 || CPU_FEROCEON || CPU_V7M
 	default y
 	help
 	  Say Y if you want to include kernel support for running user space
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@ -16,6 +16,7 @@ obj-$(CONFIG_MODULES)		+= proc-syms.o

 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
+obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o

 obj-$(CONFIG_CPU_ABRT_NOMMU)	+= abort-nommu.o
 obj-$(CONFIG_CPU_ABRT_EV4)	+= abort-ev4.o
@ -39,6 +40,7 @@ obj-$(CONFIG_CPU_CACHE_V4WB)	+= cache-v4wb.o
 obj-$(CONFIG_CPU_CACHE_V6)	+= cache-v6.o
 obj-$(CONFIG_CPU_CACHE_V7)	+= cache-v7.o
 obj-$(CONFIG_CPU_CACHE_FA)	+= cache-fa.o
+obj-$(CONFIG_CPU_CACHE_NOP)	+= cache-nop.o

 AFLAGS_cache-v6.o	:=-Wa,-march=armv6
 AFLAGS_cache-v7.o	:=-Wa,-march=armv7-a
@ -87,6 +89,7 @@ obj-$(CONFIG_CPU_FEROCEON)	+= proc-feroceon.o
 obj-$(CONFIG_CPU_V6)		+= proc-v6.o
 obj-$(CONFIG_CPU_V6K)		+= proc-v6.o
 obj-$(CONFIG_CPU_V7)		+= proc-v7.o
+obj-$(CONFIG_CPU_V7M)		+= proc-v7m.o

 AFLAGS_proc-v6.o	:=-Wa,-march=armv6
 AFLAGS_proc-v7.o	:=-Wa,-march=armv7-a
--- a/arch/arm/mm/cache-nop.S
+++ b/arch/arm/mm/cache-nop.S
@ -0,0 +1,50 @@
+/*
+ * 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/linkage.h>
+#include <linux/init.h>
+
+#include "proc-macros.S"
+
+ENTRY(nop_flush_icache_all)
+	mov	pc, lr
+ENDPROC(nop_flush_icache_all)
+
+	.globl nop_flush_kern_cache_all
+	.equ nop_flush_kern_cache_all, nop_flush_icache_all
+
+	.globl nop_flush_kern_cache_louis
+	.equ nop_flush_kern_cache_louis, nop_flush_icache_all
+
+	.globl nop_flush_user_cache_all
+	.equ nop_flush_user_cache_all, nop_flush_icache_all
+
+	.globl nop_flush_user_cache_range
+	.equ nop_flush_user_cache_range, nop_flush_icache_all
+
+	.globl nop_coherent_kern_range
+	.equ nop_coherent_kern_range, nop_flush_icache_all
+
+ENTRY(nop_coherent_user_range)
+	mov	r0, 0
+	mov	pc, lr
+ENDPROC(nop_coherent_user_range)
+
+	.globl nop_flush_kern_dcache_area
+	.equ nop_flush_kern_dcache_area, nop_flush_icache_all
+
+	.globl nop_dma_flush_range
+	.equ nop_dma_flush_range, nop_flush_icache_all
+
+	.globl nop_dma_map_area
+	.equ nop_dma_map_area, nop_flush_icache_all
+
+	.globl nop_dma_unmap_area
+	.equ nop_dma_unmap_area, nop_flush_icache_all
+
+	__INITDATA
+
+	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
+	define_cache_functions nop
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@ -20,6 +20,7 @@
 #include <asm/smp_plat.h>
 #include <asm/thread_notify.h>
 #include <asm/tlbflush.h>
+#include <asm/proc-fns.h>

 /*
 * On ARMv6, we have the following structure in the Context ID:
@ -79,17 +80,11 @@ void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
 #ifdef CONFIG_ARM_LPAE
 static void cpu_set_reserved_ttbr0(void)
 {
-	unsigned long ttbl = __pa(swapper_pg_dir);
-	unsigned long ttbh = 0;
-
 	/*
 	 * Set TTBR0 to swapper_pg_dir which contains only global entries. The
 	 * ASID is set to 0.
 	 */
-	asm volatile(
-	"	mcrr	p15, 0, %0, %1, c2		@ set TTBR0\n"
-	:
-	: "r" (ttbl), "r" (ttbh));
+	cpu_set_ttbr(0, __pa(swapper_pg_dir));
 	isb();
 }
 #else
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@ -250,7 +250,7 @@ static void __dma_free_buffer(struct page *page, size_t size)

 #ifdef CONFIG_MMU
 #ifdef CONFIG_HUGETLB_PAGE
-#error ARM Coherent DMA allocator does not (yet) support huge TLB
+#warning ARM Coherent DMA allocator does not (yet) support huge TLB
 #endif

 static void *__alloc_from_contiguous(struct device *dev, size_t size,
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@ -491,12 +491,14 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 * Some section permission faults need to be handled gracefully.
 * They can happen due to a __{get,put}_user during an oops.
 */
+#ifndef CONFIG_ARM_LPAE
 static int
 do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
 	do_bad_area(addr, fsr, regs);
 	return 0;
 }
+#endif /* CONFIG_ARM_LPAE */

 /*
 * This abort handler always returns "fault".
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@ -17,6 +17,7 @@
 #include <asm/highmem.h>
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
+#include <linux/hugetlb.h>

 #include "mm.h"

@ -168,19 +169,23 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 	 * coherent with the kernels mapping.
 	 */
 	if (!PageHighMem(page)) {
-		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+		size_t page_size = PAGE_SIZE << compound_order(page);
+		__cpuc_flush_dcache_area(page_address(page), page_size);
 	} else {
-		void *addr;
-
+		unsigned long i;
 		if (cache_is_vipt_nonaliasing()) {
-			addr = kmap_atomic(page);
-			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-			kunmap_atomic(addr);
-		} else {
-			addr = kmap_high_get(page);
-			if (addr) {
+			for (i = 0; i < (1 << compound_order(page)); i++) {
+				void *addr = kmap_atomic(page);
 				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-				kunmap_high(page);
+				kunmap_atomic(addr);
+			}
+		} else {
+			for (i = 0; i < (1 << compound_order(page)); i++) {
+				void *addr = kmap_high_get(page);
+				if (addr) {
+					__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+					kunmap_high(page);
+				}
 			}
 		}
 	}
--- a/arch/arm/mm/fsr-3level.c
+++ b/arch/arm/mm/fsr-3level.c
@ -9,11 +9,11 @@ static struct fsr_info fsr_info[] = {
 	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
-	{ do_sect_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
 	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
 	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@ -0,0 +1,101 @@
+/*
+ * arch/arm/mm/hugetlbpage.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h and Bill Carson's patches
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <asm/mman.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
+/*
+ * On ARM, huge pages are backed by pmd's rather than pte's, so we do a lot
+ * of type casting from pmd_t * to pte_t *.
+ */
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd = NULL;
+
+	pgd = pgd_offset(mm, addr);
+	if (pgd_present(*pgd)) {
+		pud = pud_offset(pgd, addr);
+		if (pud_present(*pud))
+			pmd = pmd_offset(pud, addr);
+	}
+
+	return (pte_t *)pmd;
+}
+
+struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
+			      int write)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+	return 0;
+}
+
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pte_t *pte = NULL;
+
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (pud)
+		pte = (pte_t *)pmd_alloc(mm, pud, addr);
+
+	return pte;
+}
+
+struct page *
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+		pmd_t *pmd, int write)
+{
+	struct page *page;
+
+	page = pte_page(*(pte_t *)pmd);
+	if (page)
+		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+	return page;
+}
+
+int pmd_huge(pmd_t pmd)
+{
+	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
+}
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@ -36,12 +36,13 @@

 #include "mm.h"

-static unsigned long phys_initrd_start __initdata = 0;
+static phys_addr_t phys_initrd_start __initdata = 0;
 static unsigned long phys_initrd_size __initdata = 0;

 static int __init early_initrd(char *p)
 {
-	unsigned long start, size;
+	phys_addr_t start;
+	unsigned long size;
 	char *endp;

 	start = memparse(p, &endp);
@ -350,14 +351,14 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (phys_initrd_size &&
 	    !memblock_is_region_memory(phys_initrd_start, phys_initrd_size)) {
-		pr_err("INITRD: 0x%08lx+0x%08lx is not a memory region - disabling initrd\n",
-		       phys_initrd_start, phys_initrd_size);
+		pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region - disabling initrd\n",
+		       (u64)phys_initrd_start, phys_initrd_size);
 		phys_initrd_start = phys_initrd_size = 0;
 	}
 	if (phys_initrd_size &&
 	    memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) {
-		pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n",
-		       phys_initrd_start, phys_initrd_size);
+		pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region - disabling initrd\n",
+		       (u64)phys_initrd_start, phys_initrd_size);
 		phys_initrd_start = phys_initrd_size = 0;
 	}
 	if (phys_initrd_size) {
@ -442,7 +443,7 @@ static inline void
 free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 {
 	struct page *start_pg, *end_pg;
-	unsigned long pg, pgend;
+	phys_addr_t pg, pgend;

 	/*
 	 * Convert start_pfn/end_pfn to a struct page pointer.
@ -454,8 +455,8 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 	 * Convert to physical addresses, and
 	 * round start upwards and end downwards.
 	 */
-	pg = (unsigned long)PAGE_ALIGN(__pa(start_pg));
-	pgend = (unsigned long)__pa(end_pg) & PAGE_MASK;
+	pg = PAGE_ALIGN(__pa(start_pg));
+	pgend = __pa(end_pg) & PAGE_MASK;

 	/*
 	 * If there are free pages between these,
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@ -675,7 +675,8 @@ 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, unsigned long phys, const struct mem_type *type)
+				  unsigned long end, phys_addr_t phys,
+				  const struct mem_type *type)
 {
 	pud_t *pud = pud_offset(pgd, addr);
 	unsigned long next;
@ -989,27 +990,28 @@ phys_addr_t arm_lowmem_limit __initdata = 0;
 void __init sanity_check_meminfo(void)
 {
 	int i, j, highmem = 0;
+	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;

 	for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
 		struct membank *bank = &meminfo.bank[j];
+		phys_addr_t size_limit;
+
 		*bank = meminfo.bank[i];
+		size_limit = bank->size;

-		if (bank->start > ULONG_MAX)
-			highmem = 1;
-
-#ifdef CONFIG_HIGHMEM
-		if (__va(bank->start) >= vmalloc_min ||
-		    __va(bank->start) < (void *)PAGE_OFFSET)
+		if (bank->start >= vmalloc_limit)
 			highmem = 1;
+		else
+			size_limit = vmalloc_limit - bank->start;

 		bank->highmem = highmem;

+#ifdef CONFIG_HIGHMEM
 		/*
 		 * Split those memory banks which are partially overlapping
 		 * the vmalloc area greatly simplifying things later.
 		 */
-		if (!highmem && __va(bank->start) < vmalloc_min &&
-		    bank->size > vmalloc_min - __va(bank->start)) {
+		if (!highmem && bank->size > size_limit) {
 			if (meminfo.nr_banks >= NR_BANKS) {
 				printk(KERN_CRIT "NR_BANKS too low, "
 						 "ignoring high memory\n");
@ -1018,16 +1020,14 @@ void __init sanity_check_meminfo(void)
 					(meminfo.nr_banks - i) * sizeof(*bank));
 				meminfo.nr_banks++;
 				i++;
-				bank[1].size -= vmalloc_min - __va(bank->start);
-				bank[1].start = __pa(vmalloc_min - 1) + 1;
+				bank[1].size -= size_limit;
+				bank[1].start = vmalloc_limit;
 				bank[1].highmem = highmem = 1;
 				j++;
 			}
-			bank->size = vmalloc_min - __va(bank->start);
+			bank->size = size_limit;
 		}
 #else
-		bank->highmem = highmem;
-
 		/*
 		 * Highmem banks not allowed with !CONFIG_HIGHMEM.
 		 */
@ -1039,32 +1039,17 @@ void __init sanity_check_meminfo(void)
 			continue;
 		}

-		/*
-		 * Check whether this memory bank would entirely overlap
-		 * the vmalloc area.
-		 */
-		if (__va(bank->start) >= vmalloc_min ||
-		    __va(bank->start) < (void *)PAGE_OFFSET) {
-			printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
-			       "(vmalloc region overlap).\n",
-			       (unsigned long long)bank->start,
-			       (unsigned long long)bank->start + bank->size - 1);
-			continue;
-		}
-
 		/*
 		 * Check whether this memory bank would partially overlap
 		 * the vmalloc area.
 		 */
-		if (__va(bank->start + bank->size - 1) >= vmalloc_min ||
-		    __va(bank->start + bank->size - 1) <= __va(bank->start)) {
-			unsigned long newsize = vmalloc_min - __va(bank->start);
+		if (bank->size > size_limit) {
 			printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
 			       "to -%.8llx (vmalloc region overlap).\n",
 			       (unsigned long long)bank->start,
 			       (unsigned long long)bank->start + bank->size - 1,
-			       (unsigned long long)bank->start + newsize - 1);
-			bank->size = newsize;
+			       (unsigned long long)bank->start + size_limit - 1);
+			bank->size = size_limit;
 		}
 #endif
 		if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit)
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@ -8,6 +8,7 @@
 #include <linux/pagemap.h>
 #include <linux/io.h>
 #include <linux/memblock.h>
+#include <linux/kernel.h>

 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@ -15,22 +16,282 @@
 #include <asm/setup.h>
 #include <asm/traps.h>
 #include <asm/mach/arch.h>
+#include <asm/cputype.h>
+#include <asm/mpu.h>

 #include "mm.h"

+#ifdef CONFIG_ARM_MPU
+struct mpu_rgn_info mpu_rgn_info;
+
+/* Region number */
+static void rgnr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c2, 0" : : "r" (v));
+}
+
+/* Data-side / unified region attributes */
+
+/* Region access control register */
+static void dracr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 4" : : "r" (v));
+}
+
+/* Region size register */
+static void drsr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 2" : : "r" (v));
+}
+
+/* Region base address register */
+static void drbar_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 0" : : "r" (v));
+}
+
+static u32 drbar_read(void)
+{
+	u32 v;
+	asm("mrc        p15, 0, %0, c6, c1, 0" : "=r" (v));
+	return v;
+}
+/* Optional instruction-side region attributes */
+
+/* I-side Region access control register */
+static void iracr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 5" : : "r" (v));
+}
+
+/* I-side Region size register */
+static void irsr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 3" : : "r" (v));
+}
+
+/* I-side Region base address register */
+static void irbar_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 1" : : "r" (v));
+}
+
+static unsigned long irbar_read(void)
+{
+	unsigned long v;
+	asm("mrc        p15, 0, %0, c6, c1, 1" : "=r" (v));
+	return v;
+}
+
+/* MPU initialisation functions */
+void __init sanity_check_meminfo_mpu(void)
+{
+	int i;
+	struct membank *bank = meminfo.bank;
+	phys_addr_t phys_offset = PHYS_OFFSET;
+	phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
+
+	/* Initially only use memory continuous from PHYS_OFFSET */
+	if (bank_phys_start(&bank[0]) != phys_offset)
+		panic("First memory bank must be contiguous from PHYS_OFFSET");
+
+	/* Banks have already been sorted by start address */
+	for (i = 1; i < meminfo.nr_banks; i++) {
+		if (bank[i].start <= bank_phys_end(&bank[0]) &&
+		    bank_phys_end(&bank[i]) > bank_phys_end(&bank[0])) {
+			bank[0].size = bank_phys_end(&bank[i]) - bank[0].start;
+		} else {
+			pr_notice("Ignoring RAM after 0x%.8lx. "
+			"First non-contiguous (ignored) bank start: 0x%.8lx\n",
+				(unsigned long)bank_phys_end(&bank[0]),
+				(unsigned long)bank_phys_start(&bank[i]));
+			break;
+		}
+	}
+	/* All contiguous banks are now merged in to the first bank */
+	meminfo.nr_banks = 1;
+	specified_mem_size = bank[0].size;
+
+	/*
+	 * MPU has curious alignment requirements: Size must be power of 2, and
+	 * region start must be aligned to the region size
+	 */
+	if (phys_offset != 0)
+		pr_info("PHYS_OFFSET != 0 => MPU Region size constrained by alignment requirements\n");
+
+	/*
+	 * Maximum aligned region might overflow phys_addr_t if phys_offset is
+	 * 0. Hence we keep everything below 4G until we take the smaller of
+	 * the aligned_region_size and rounded_mem_size, one of which is
+	 * guaranteed to be smaller than the maximum physical address.
+	 */
+	aligned_region_size = (phys_offset - 1) ^ (phys_offset);
+	/* Find the max power-of-two sized region that fits inside our bank */
+	rounded_mem_size = (1 <<  __fls(bank[0].size)) - 1;
+
+	/* The actual region size is the smaller of the two */
+	aligned_region_size = aligned_region_size < rounded_mem_size
+				? aligned_region_size + 1
+				: rounded_mem_size + 1;
+
+	if (aligned_region_size != specified_mem_size)
+		pr_warn("Truncating memory from 0x%.8lx to 0x%.8lx (MPU region constraints)",
+				(unsigned long)specified_mem_size,
+				(unsigned long)aligned_region_size);
+
+	meminfo.bank[0].size = aligned_region_size;
+	pr_debug("MPU Region from 0x%.8lx size 0x%.8lx (end 0x%.8lx))\n",
+		(unsigned long)phys_offset,
+		(unsigned long)aligned_region_size,
+		(unsigned long)bank_phys_end(&bank[0]));
+
+}
+
+static int mpu_present(void)
+{
+	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
+}
+
+static int mpu_max_regions(void)
+{
+	/*
+	 * We don't support a different number of I/D side regions so if we
+	 * have separate instruction and data memory maps then return
+	 * whichever side has a smaller number of supported regions.
+	 */
+	u32 dregions, iregions, mpuir;
+	mpuir = read_cpuid(CPUID_MPUIR);
+
+	dregions = iregions = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
+
+	/* Check for separate d-side and i-side memory maps */
+	if (mpuir & MPUIR_nU)
+		iregions = (mpuir & MPUIR_IREGION_SZMASK) >> MPUIR_IREGION;
+
+	/* Use the smallest of the two maxima */
+	return min(dregions, iregions);
+}
+
+static int mpu_iside_independent(void)
+{
+	/* MPUIR.nU specifies whether there is *not* a unified memory map */
+	return read_cpuid(CPUID_MPUIR) & MPUIR_nU;
+}
+
+static int mpu_min_region_order(void)
+{
+	u32 drbar_result, irbar_result;
+	/* We've kept a region free for this probing */
+	rgnr_write(MPU_PROBE_REGION);
+	isb();
+	/*
+	 * As per ARM ARM, write 0xFFFFFFFC to DRBAR to find the minimum
+	 * region order
+	*/
+	drbar_write(0xFFFFFFFC);
+	drbar_result = irbar_result = drbar_read();
+	drbar_write(0x0);
+	/* If the MPU is non-unified, we use the larger of the two minima*/
+	if (mpu_iside_independent()) {
+		irbar_write(0xFFFFFFFC);
+		irbar_result = irbar_read();
+		irbar_write(0x0);
+	}
+	isb(); /* Ensure that MPU region operations have completed */
+	/* Return whichever result is larger */
+	return __ffs(max(drbar_result, irbar_result));
+}
+
+static int mpu_setup_region(unsigned int number, phys_addr_t start,
+			unsigned int size_order, unsigned int properties)
+{
+	u32 size_data;
+
+	/* We kept a region free for probing resolution of MPU regions*/
+	if (number > mpu_max_regions() || number == MPU_PROBE_REGION)
+		return -ENOENT;
+
+	if (size_order > 32)
+		return -ENOMEM;
+
+	if (size_order < mpu_min_region_order())
+		return -ENOMEM;
+
+	/* Writing N to bits 5:1 (RSR_SZ)  specifies region size 2^N+1 */
+	size_data = ((size_order - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN;
+
+	dsb(); /* Ensure all previous data accesses occur with old mappings */
+	rgnr_write(number);
+	isb();
+	drbar_write(start);
+	dracr_write(properties);
+	isb(); /* Propagate properties before enabling region */
+	drsr_write(size_data);
+
+	/* Check for independent I-side registers */
+	if (mpu_iside_independent()) {
+		irbar_write(start);
+		iracr_write(properties);
+		isb();
+		irsr_write(size_data);
+	}
+	isb();
+
+	/* Store region info (we treat i/d side the same, so only store d) */
+	mpu_rgn_info.rgns[number].dracr = properties;
+	mpu_rgn_info.rgns[number].drbar = start;
+	mpu_rgn_info.rgns[number].drsr = size_data;
+	return 0;
+}
+
+/*
+* Set up default MPU regions, doing nothing if there is no MPU
+*/
+void __init mpu_setup(void)
+{
+	int region_err;
+	if (!mpu_present())
+		return;
+
+	region_err = mpu_setup_region(MPU_RAM_REGION, PHYS_OFFSET,
+					ilog2(meminfo.bank[0].size),
+					MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
+	if (region_err) {
+		panic("MPU region initialization failure! %d", region_err);
+	} else {
+		pr_info("Using ARMv7 PMSA Compliant MPU. "
+			 "Region independence: %s, Max regions: %d\n",
+			mpu_iside_independent() ? "Yes" : "No",
+			mpu_max_regions());
+	}
+}
+#else
+static void sanity_check_meminfo_mpu(void) {}
+static void __init mpu_setup(void) {}
+#endif /* CONFIG_ARM_MPU */
+
 void __init arm_mm_memblock_reserve(void)
 {
+#ifndef CONFIG_CPU_V7M
 	/*
 	 * Register the exception vector page.
 	 * some architectures which the DRAM is the exception vector to trap,
 	 * alloc_page breaks with error, although it is not NULL, but "0."
 	 */
 	memblock_reserve(CONFIG_VECTORS_BASE, PAGE_SIZE);
+#else /* ifndef CONFIG_CPU_V7M */
+	/*
+	 * There is no dedicated vector page on V7-M. So nothing needs to be
+	 * reserved here.
+	 */
+#endif
 }

 void __init sanity_check_meminfo(void)
 {
-	phys_addr_t end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
+	phys_addr_t end;
+	sanity_check_meminfo_mpu();
+	end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
 	high_memory = __va(end - 1) + 1;
 }

@ -41,6 +302,7 @@ void __init sanity_check_meminfo(void)
 void __init paging_init(struct machine_desc *mdesc)
 {
 	early_trap_init((void *)CONFIG_VECTORS_BASE);
+	mpu_setup();
 	bootmem_init();
 }

--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@ -140,8 +140,10 @@ ENTRY(cpu_v6_set_pte_ext)
 ENTRY(cpu_v6_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
+#ifdef CONFIG_MMU
 	mrc	p15, 0, r5, c3, c0, 0	@ Domain ID
 	mrc	p15, 0, r6, c2, c0, 1	@ Translation table base 1
+#endif
 	mrc	p15, 0, r7, c1, c0, 1	@ auxiliary control register
 	mrc	p15, 0, r8, c1, c0, 2	@ co-processor access control
 	mrc	p15, 0, r9, c1, c0, 0	@ control register
@ -158,14 +160,16 @@ ENTRY(cpu_v6_do_resume)
 	mcr	p15, 0, ip, c13, c0, 1	@ set reserved context ID
 	ldmia	r0, {r4 - r9}
 	mcr	p15, 0, r4, c13, c0, 0	@ FCSE/PID
+#ifdef CONFIG_MMU
 	mcr	p15, 0, r5, c3, c0, 0	@ Domain ID
 	ALT_SMP(orr	r1, r1, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r1, r1, #TTB_FLAGS_UP)
 	mcr	p15, 0, r1, c2, c0, 0	@ Translation table base 0
 	mcr	p15, 0, r6, c2, c0, 1	@ Translation table base 1
+	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
+#endif
 	mcr	p15, 0, r7, c1, c0, 1	@ auxiliary control register
 	mcr	p15, 0, r8, c1, c0, 2	@ co-processor access control
-	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
 	mcr	p15, 0, ip, c7, c5, 4	@ ISB
 	mov	r0, r9			@ control register
 	b	cpu_resume_mmu
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@ -39,6 +39,14 @@
 #define TTB_FLAGS_SMP	(TTB_IRGN_WBWA|TTB_S|TTB_RGN_OC_WBWA)
 #define PMD_FLAGS_SMP	(PMD_SECT_WBWA|PMD_SECT_S)

+#ifndef __ARMEB__
+#  define rpgdl	r0
+#  define rpgdh	r1
+#else
+#  define rpgdl	r1
+#  define rpgdh	r0
+#endif
+
 /*
 * cpu_v7_switch_mm(pgd_phys, tsk)
 *
@ -47,10 +55,10 @@
 */
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
-	mmid	r1, r1				@ get mm->context.id
-	asid	r3, r1
-	mov	r3, r3, lsl #(48 - 32)		@ ASID
-	mcrr	p15, 0, r0, r3, c2		@ set TTB 0
+	mmid	r2, r2
+	asid	r2, r2
+	orr	rpgdh, rpgdh, r2, lsl #(48 - 32)	@ upper 32-bits of pgd
+	mcrr	p15, 0, rpgdl, rpgdh, c2		@ set TTB 0
 	isb
 #endif
 	mov	pc, lr
@ -106,7 +114,8 @@ ENDPROC(cpu_v7_set_pte_ext)
 	 */
 	.macro	v7_ttb_setup, zero, ttbr0, ttbr1, tmp
 	ldr	\tmp, =swapper_pg_dir		@ swapper_pg_dir virtual address
-	cmp	\ttbr1, \tmp			@ PHYS_OFFSET > PAGE_OFFSET? (branch below)
+	mov	\tmp, \tmp, lsr #ARCH_PGD_SHIFT
+	cmp	\ttbr1, \tmp			@ PHYS_OFFSET > PAGE_OFFSET?
 	mrc	p15, 0, \tmp, c2, c0, 2		@ TTB control register
 	orr	\tmp, \tmp, #TTB_EAE
 	ALT_SMP(orr	\tmp, \tmp, #TTB_FLAGS_SMP)
@ -114,27 +123,21 @@ ENDPROC(cpu_v7_set_pte_ext)
 	ALT_SMP(orr	\tmp, \tmp, #TTB_FLAGS_SMP << 16)
 	ALT_UP(orr	\tmp, \tmp, #TTB_FLAGS_UP << 16)
 	/*
-	 * TTBR0/TTBR1 split (PAGE_OFFSET):
-	 *   0x40000000: T0SZ = 2, T1SZ = 0 (not used)
-	 *   0x80000000: T0SZ = 0, T1SZ = 1
-	 *   0xc0000000: T0SZ = 0, T1SZ = 2
-	 *
-	 * Only use this feature if PHYS_OFFSET <= PAGE_OFFSET, otherwise
-	 * booting secondary CPUs would end up using TTBR1 for the identity
-	 * mapping set up in TTBR0.
+	 * Only use split TTBRs if PHYS_OFFSET <= PAGE_OFFSET (cmp above),
+	 * otherwise booting secondary CPUs would end up using TTBR1 for the
+	 * identity mapping set up in TTBR0.
 	 */
-	bhi	9001f				@ PHYS_OFFSET > PAGE_OFFSET?
-	orr	\tmp, \tmp, #(((PAGE_OFFSET >> 30) - 1) << 16) @ TTBCR.T1SZ
-#if defined CONFIG_VMSPLIT_2G
-	/* PAGE_OFFSET == 0x80000000, T1SZ == 1 */
-	add	\ttbr1, \ttbr1, #1 << 4		@ skip two L1 entries
-#elif defined CONFIG_VMSPLIT_3G
-	/* PAGE_OFFSET == 0xc0000000, T1SZ == 2 */
-	add	\ttbr1, \ttbr1, #4096 * (1 + 3)	@ only L2 used, skip pgd+3*pmd
-#endif
-	/* CONFIG_VMSPLIT_1G does not need TTBR1 adjustment */
-9001:	mcr	p15, 0, \tmp, c2, c0, 2		@ TTB control register
-	mcrr	p15, 1, \ttbr1, \zero, c2	@ load TTBR1
+	orrls	\tmp, \tmp, #TTBR1_SIZE				@ TTBCR.T1SZ
+	mcr	p15, 0, \tmp, c2, c0, 2				@ TTBCR
+	mov	\tmp, \ttbr1, lsr #(32 - ARCH_PGD_SHIFT)	@ upper bits
+	mov	\ttbr1, \ttbr1, lsl #ARCH_PGD_SHIFT		@ lower bits
+	addls	\ttbr1, \ttbr1, #TTBR1_OFFSET
+	mcrr	p15, 1, \ttbr1, \zero, c2			@ load TTBR1
+	mov	\tmp, \ttbr0, lsr #(32 - ARCH_PGD_SHIFT)	@ upper bits
+	mov	\ttbr0, \ttbr0, lsl #ARCH_PGD_SHIFT		@ lower bits
+	mcrr	p15, 0, \ttbr0, \zero, c2			@ load TTBR0
+	mcrr	p15, 1, \ttbr1, \zero, c2			@ load TTBR1
+	mcrr	p15, 0, \ttbr0, \zero, c2			@ load TTBR0
 	.endm

 	__CPUINIT
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@ -98,9 +98,11 @@ ENTRY(cpu_v7_do_suspend)
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
 	mrc	p15, 0, r5, c13, c0, 3	@ User r/o thread ID
 	stmia	r0!, {r4 - r5}
+#ifdef CONFIG_MMU
 	mrc	p15, 0, r6, c3, c0, 0	@ Domain ID
 	mrc	p15, 0, r7, c2, c0, 1	@ TTB 1
 	mrc	p15, 0, r11, c2, c0, 2	@ TTB control register
+#endif
 	mrc	p15, 0, r8, c1, c0, 0	@ Control register
 	mrc	p15, 0, r9, c1, c0, 1	@ Auxiliary control register
 	mrc	p15, 0, r10, c1, c0, 2	@ Co-processor access control
@ -110,13 +112,14 @@ ENDPROC(cpu_v7_do_suspend)

 ENTRY(cpu_v7_do_resume)
 	mov	ip, #0
-	mcr	p15, 0, ip, c8, c7, 0	@ invalidate TLBs
 	mcr	p15, 0, ip, c7, c5, 0	@ invalidate I cache
 	mcr	p15, 0, ip, c13, c0, 1	@ set reserved context ID
 	ldmia	r0!, {r4 - r5}
 	mcr	p15, 0, r4, c13, c0, 0	@ FCSE/PID
 	mcr	p15, 0, r5, c13, c0, 3	@ User r/o thread ID
 	ldmia	r0, {r6 - r11}
+#ifdef CONFIG_MMU
+	mcr	p15, 0, ip, c8, c7, 0	@ invalidate TLBs
 	mcr	p15, 0, r6, c3, c0, 0	@ Domain ID
 #ifndef CONFIG_ARM_LPAE
 	ALT_SMP(orr	r1, r1, #TTB_FLAGS_SMP)
@ -125,14 +128,15 @@ ENTRY(cpu_v7_do_resume)
 	mcr	p15, 0, r1, c2, c0, 0	@ TTB 0
 	mcr	p15, 0, r7, c2, c0, 1	@ TTB 1
 	mcr	p15, 0, r11, c2, c0, 2	@ TTB control register
-	mrc	p15, 0, r4, c1, c0, 1	@ Read Auxiliary control register
-	teq	r4, r9			@ Is it already set?
-	mcrne	p15, 0, r9, c1, c0, 1	@ No, so write it
-	mcr	p15, 0, r10, c1, c0, 2	@ Co-processor access control
 	ldr	r4, =PRRR		@ PRRR
 	ldr	r5, =NMRR		@ NMRR
 	mcr	p15, 0, r4, c10, c2, 0	@ write PRRR
 	mcr	p15, 0, r5, c10, c2, 1	@ write NMRR
+#endif	/* CONFIG_MMU */
+	mrc	p15, 0, r4, c1, c0, 1	@ Read Auxiliary control register
+	teq	r4, r9			@ Is it already set?
+	mcrne	p15, 0, r9, c1, c0, 1	@ No, so write it
+	mcr	p15, 0, r10, c1, c0, 2	@ Co-processor access control
 	isb
 	dsb
 	mov	r0, r8			@ control register
@ -178,7 +182,8 @@ ENDPROC(cpu_pj4b_do_idle)
 */
 __v7_ca5mp_setup:
 __v7_ca9mp_setup:
-	mov	r10, #(1 << 0)			@ TLB ops broadcasting
+__v7_cr7mp_setup:
+	mov	r10, #(1 << 0)			@ Cache/TLB ops broadcasting
 	b	1f
 __v7_ca7mp_setup:
 __v7_ca15mp_setup:
@ -442,6 +447,16 @@ __v7_pj4b_proc_info:
 	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
 #endif

+	/*
+	 * ARM Ltd. Cortex R7 processor.
+	 */
+	.type	__v7_cr7mp_proc_info, #object
+__v7_cr7mp_proc_info:
+	.long	0x410fc170
+	.long	0xff0ffff0
+	__v7_proc __v7_cr7mp_setup
+	.size	__v7_cr7mp_proc_info, . - __v7_cr7mp_proc_info
+
 	/*
 	 * ARM Ltd. Cortex A7 processor.
 	 */
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@ -0,0 +1,157 @@
+/*
+ *  linux/arch/arm/mm/proc-v7m.S
+ *
+ *  Copyright (C) 2008 ARM Ltd.
+ *  Copyright (C) 2001 Deep Blue Solutions Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  This is the "shell" of the ARMv7-M processor support.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/v7m.h>
+#include "proc-macros.S"
+
+ENTRY(cpu_v7m_proc_init)
+	mov	pc, lr
+ENDPROC(cpu_v7m_proc_init)
+
+ENTRY(cpu_v7m_proc_fin)
+	mov	pc, lr
+ENDPROC(cpu_v7m_proc_fin)
+
+/*
+ *	cpu_v7m_reset(loc)
+ *
+ *	Perform a soft reset of the system.  Put the CPU into the
+ *	same state as it would be if it had been reset, and branch
+ *	to what would be the reset vector.
+ *
+ *	- loc   - location to jump to for soft reset
+ */
+	.align	5
+ENTRY(cpu_v7m_reset)
+	mov	pc, r0
+ENDPROC(cpu_v7m_reset)
+
+/*
+ *	cpu_v7m_do_idle()
+ *
+ *	Idle the processor (eg, wait for interrupt).
+ *
+ *	IRQs are already disabled.
+ */
+ENTRY(cpu_v7m_do_idle)
+	wfi
+	mov	pc, lr
+ENDPROC(cpu_v7m_do_idle)
+
+ENTRY(cpu_v7m_dcache_clean_area)
+	mov	pc, lr
+ENDPROC(cpu_v7m_dcache_clean_area)
+
+/*
+ * There is no MMU, so here is nothing to do.
+ */
+ENTRY(cpu_v7m_switch_mm)
+	mov	pc, lr
+ENDPROC(cpu_v7m_switch_mm)
+
+.globl	cpu_v7m_suspend_size
+.equ	cpu_v7m_suspend_size, 0
+
+#ifdef CONFIG_ARM_CPU_SUSPEND
+ENTRY(cpu_v7m_do_suspend)
+	mov	pc, lr
+ENDPROC(cpu_v7m_do_suspend)
+
+ENTRY(cpu_v7m_do_resume)
+	mov	pc, lr
+ENDPROC(cpu_v7m_do_resume)
+#endif
+
+	.section ".text.init", #alloc, #execinstr
+
+/*
+ *	__v7m_setup
+ *
+ *	This should be able to cover all ARMv7-M cores.
+ */
+__v7m_setup:
+	@ Configure the vector table base address
+	ldr	r0, =BASEADDR_V7M_SCB
+	ldr	r12, =vector_table
+	str	r12, [r0, V7M_SCB_VTOR]
+
+	@ enable UsageFault, BusFault and MemManage fault.
+	ldr	r5, [r0, #V7M_SCB_SHCSR]
+	orr	r5, #(V7M_SCB_SHCSR_USGFAULTENA | V7M_SCB_SHCSR_BUSFAULTENA | V7M_SCB_SHCSR_MEMFAULTENA)
+	str	r5, [r0, #V7M_SCB_SHCSR]
+
+	@ Lower the priority of the SVC and PendSV exceptions
+	mov	r5, #0x80000000
+	str	r5, [r0, V7M_SCB_SHPR2]	@ set SVC priority
+	mov	r5, #0x00800000
+	str	r5, [r0, V7M_SCB_SHPR3]	@ set PendSV priority
+
+	@ SVC to run the kernel in this mode
+	adr	r1, BSYM(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
+	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
+	msr	control, r1		@ Thread mode has unpriviledged access
+
+	@ Configure the System Control Register to ensure 8-byte stack alignment
+	@ Note the STKALIGN bit is either RW or RAO.
+	ldr	r12, [r0, V7M_SCB_CCR]	@ system control register
+	orr	r12, #V7M_SCB_CCR_STKALIGN
+	str	r12, [r0, V7M_SCB_CCR]
+	mov	pc, lr
+ENDPROC(__v7m_setup)
+
+	define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1
+
+	.section ".rodata"
+	string cpu_arch_name, "armv7m"
+	string cpu_elf_name "v7m"
+	string cpu_v7m_name "ARMv7-M"
+
+	.section ".proc.info.init", #alloc, #execinstr
+
+	/*
+	 * Match any ARMv7-M processor core.
+	 */
+	.type	__v7m_proc_info, #object
+__v7m_proc_info:
+	.long	0x000f0000		@ Required ID value
+	.long	0x000f0000		@ Mask for ID
+	.long   0			@ proc_info_list.__cpu_mm_mmu_flags
+	.long   0			@ proc_info_list.__cpu_io_mmu_flags
+	b	__v7m_setup		@ proc_info_list.__cpu_flush
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT
+	.long	cpu_v7m_name
+	.long	v7m_processor_functions	@ proc_info_list.proc
+	.long	0			@ proc_info_list.tlb
+	.long	0			@ proc_info_list.user
+	.long	nop_cache_fns		@ proc_info_list.cache
+	.size	__v7m_proc_info, . - __v7m_proc_info
+
+__v7m_setup_stack:
+	.space	4 * 8				@ 8 registers
+__v7m_setup_stack_top:
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@ -110,16 +110,6 @@ static inline void __cpuinit arch_counter_set_user_access(void)
 	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
 }

-static inline u64 arch_counter_get_cntpct(void)
-{
-	u64 cval;
-
-	isb();
-	asm volatile("mrs %0, cntpct_el0" : "=r" (cval));
-
-	return cval;
-}
-
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@ -186,27 +186,19 @@ u32 arch_timer_get_rate(void)
 	return arch_timer_rate;
 }

-/*
- * Some external users of arch_timer_read_counter (e.g. sched_clock) may try to
- * call it before it has been initialised. Rather than incur a performance
- * penalty checking for initialisation, provide a default implementation that
- * won't lead to time appearing to jump backwards.
- */
-static u64 arch_timer_read_zero(void)
+u64 arch_timer_read_counter(void)
 {
-	return 0;
+	return arch_counter_get_cntvct();
 }

-u64 (*arch_timer_read_counter)(void) = arch_timer_read_zero;
-
 static cycle_t arch_counter_read(struct clocksource *cs)
 {
-	return arch_timer_read_counter();
+	return arch_counter_get_cntvct();
 }

 static cycle_t arch_counter_read_cc(const struct cyclecounter *cc)
 {
-	return arch_timer_read_counter();
+	return arch_counter_get_cntvct();
 }

 static struct clocksource clocksource_counter = {
@ -287,7 +279,7 @@ static int __init arch_timer_register(void)
 	cyclecounter.mult = clocksource_counter.mult;
 	cyclecounter.shift = clocksource_counter.shift;
 	timecounter_init(&timecounter, &cyclecounter,
-			 arch_counter_get_cntpct());
+			 arch_counter_get_cntvct());

 	if (arch_timer_use_virtual) {
 		ppi = arch_timer_ppi[VIRT_PPI];
@ -376,11 +368,6 @@ static void __init arch_timer_init(struct device_node *np)
 		}
 	}

-	if (arch_timer_use_virtual)
-		arch_timer_read_counter = arch_counter_get_cntvct;
-	else
-		arch_timer_read_counter = arch_counter_get_cntpct;
-
 	arch_timer_register();
 	arch_timer_arch_init();
 }
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@ -32,7 +32,7 @@
 #ifdef CONFIG_ARM_ARCH_TIMER

 extern u32 arch_timer_get_rate(void);
-extern u64 (*arch_timer_read_counter)(void);
+extern u64 arch_timer_read_counter(void);
 extern struct timecounter *arch_timer_get_timecounter(void);

 #else