Merge branch 'ja-nommu-for-rmk-v2' of git://linux-arm.org/linux-ja into devel-stable

This includes the following series sent earlier to the list:
 - nommu-fixes
 - R7 Support
 - MPU support

I've left out the ARCH_MULTIPLATFORM/!MMU stuff that Arnd and I were
discussing today until we've reached a conclusion/that's had some more
review.

This is rebased (and re-tested) on your devel-stable branch because
otherwise there were going to be conflicts with Uwe's V7M work now that
you've merged that. I've included the fix for limiting MPU to CPU_V7.

20 files changed, 646 insertions, 51 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5543d36c2834..ec38cacb3d08 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1414,7 +1414,7 @@ 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
@@ -1435,7 +1435,7 @@ 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.
diff --git a/arch/arm/Kconfig-nommu b/arch/arm/Kconfig-nommu
index c859495da480..aed66d5df7f1 100644
--- a/arch/arm/Kconfig-nommu
+++ b/arch/arm/Kconfig-nommu
@@ -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.
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 1d41908d5cda..f2623b25ff9a 100644
--- 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"
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 1f3262e99d81..a524a23d8627 100644
--- 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)	*/
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index ec635ff32f49..3b704dfb6c58 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -8,6 +8,7 @@
 #define CPUID_CACHETYPE	1
 #define CPUID_TCM	2
 #define CPUID_TLBTYPE	3
+#define CPUID_MPUIR	4
 #define CPUID_MPIDR	5
 
 #ifdef CONFIG_CPU_V7M
diff --git a/arch/arm/include/asm/mpu.h b/arch/arm/include/asm/mpu.h
new file mode 100644
index 000000000000..c3247cc2fe08
--- /dev/null
+++ 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
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index f3628fb3d2b3..a6c99fe62b82 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -137,6 +137,10 @@ extern void cpu_resume(void);
 	})
 #endif
 
+#else	/*!CONFIG_MMU */
+
+#define cpu_switch_mm(pgd,mm)	{ }
+
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index d3a22bebe6ce..a8cae71caceb 100644
--- 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;
 };
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index aaa61b6f50ff..1c7b6f8101ae 100644
--- 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
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index a3625d141c1d..ded7c16f80cc 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -537,6 +537,29 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 
 #endif
 
-#endif /* CONFIG_MMU */
+#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
diff --git a/arch/arm/include/debug/vexpress.S b/arch/arm/include/debug/vexpress.S
index dc8e882a6257..acafb229e2b6 100644
--- 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
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index f4285b5ffb05..fccfbdb03df1 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -38,7 +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
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 8812ce88f7a1..75f14cc3e073 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -17,9 +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.
@@ -63,12 +66,74 @@ ENTRY(stext)
 	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.
  */
@@ -99,10 +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/signal.c b/arch/arm/kernel/signal.c
index 296786bdbb73..1c16c35c271a 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/smp.c b/arch/arm/kernel/smp.c
index 550d63cef68e..e17d9346baee 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
@@ -87,8 +88,14 @@ 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;
+#ifdef CONFIG_ARM_MPU
+	secondary_data.mpu_rgn_szr = mpu_rgn_info.rgns[MPU_RAM_REGION].drsr;
+#endif
+
+#ifdef CONFIG_MMU
 	secondary_data.pgdir = virt_to_phys(idmap_pgd);
 	secondary_data.swapper_pg_dir = virt_to_phys(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 +119,8 @@ 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 c59c97ea8268..38a50676213b 100644
--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@@ -10,6 +10,42 @@
 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
@@ -46,31 +82,3 @@ void __cpu_suspend_save(u32 *ptr, u32 ptrsz, u32 sp, u32 *save_ptr)
 	outer_clean_range(virt_to_phys(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;
-
-	/*
-	 * 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;
-}
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 9e8101ecd63e..6cacdc8dd654 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -392,7 +392,8 @@ 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
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index dd3a6c670f08..c1b494d43ed1 100644
--- 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>
@@ -15,9 +16,260 @@
 #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
@@ -37,7 +289,9 @@ void __init arm_mm_memblock_reserve(void)
 
 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;
 }
 
@@ -48,6 +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();
 }
 
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 919405e20b80..2d1ef87328a1 100644
--- 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
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 2c73a7301ff7..f85ae8cad17f 100644
--- 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
@@ -155,7 +159,8 @@ ENDPROC(cpu_v7_do_resume)
  */
 __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:
@@ -415,6 +420,16 @@ __v7_pj4b_proc_info:
 	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
 
 	/*
+	 * 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.
 	 */
 	.type	__v7_ca7mp_proc_info, #object