Merge branch 'devel-stable' into for-next

Conflicts:
	arch/arm/Makefile
	arch/arm/include/asm/glue-proc.h

16 files changed, 813 insertions, 72 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5f3338eacad..fccfbdb03df 100644
--- 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
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index ee68cce6b48..ded041711be 100644
--- 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>
 
@@ -145,6 +146,11 @@ int main(void)
 #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);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 4bc816a74a2..94104bf6971 100644
--- 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
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 160f3376ba6..de23a9beed1 100644
--- 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
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
new file mode 100644
index 00000000000..e00621f1403
--- /dev/null
+++ 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
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 6a2e09c952c..75f14cc3e07 100644
--- 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.
@@ -50,21 +54,86 @@ ENTRY(stext)
 
 	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
-#ifndef CONFIG_CPU_CP15
-	ldr	r9, =CONFIG_PROCESSOR_ID
-#else
+#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'
 
-	adr	lr, BSYM(__after_proc_init)	@ return (PIC) address
+#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?
+	beq	__error_p			@ yes, error 'p'
+
+	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(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"
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 8bac553fe21..45e8935cae4 100644
--- 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) | \
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 1315c4ccfa5..4910232c483 100644
--- 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
 
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index 36531643cc2..46931880093 100644
--- 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);
diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c
new file mode 100644
index 00000000000..219f1d73572
--- /dev/null
+++ 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
+};
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 0cde326f554..9b653278c9e 100644
--- 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
 };
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 296786bdbb7..1c16c35c271 100644
--- 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 {
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 987dcf33415..db1536b8b30 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -7,6 +7,49 @@
 	.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
  * specific registers and some other data for resume.
@@ -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
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 5919eb451bb..c5fb5469054 100644
--- 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;
 }
 
diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
index c59c97ea826..41cf3cbf756 100644
--- 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))
-{
-	struct mm_struct *mm = current->active_mm;
-	int ret;
-
-	if (!idmap_pgd)
-		return -EINVAL;
+extern struct sleep_save_sp sleep_save_sp;
 
-	/*
-	 * 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();
-	}
+static int cpu_suspend_alloc_sp(void)
+{
+	void *ctx_ptr;
+	/* ctx_ptr is an array of physical addresses */
+	ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(u32), GFP_KERNEL);
 
-	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);
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 517bfd4da1c..cab094c234e 100644
--- 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
 }