Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates from Russell King: "This contains the usual updates from other people (listed below) and the usual random muddle of miscellaneous ARM updates which cover some low priority bug fixes and performance improvements. I've started to put the pull request wording into the merge commits, which are: - NoMMU stuff: 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. - Huge page support These changes bring both HugeTLB support and Transparent HugePage (THP) support to ARM. Only long descriptors (LPAE) are supported in this series. The code has been tested on an Arndale board (Exynos 5250). - LPAE updates Please pull these miscellaneous LPAE fixes I've been collecting for a while now for 3.11. They've been tested and reviewed by quite a few people, and most of the patches are pretty trivial. -- Will Deacon. - arch_timer cleanups Please pull these arch_timer cleanups I've been holding onto for a while. They're the same as my last posting, but have been rebased to v3.10-rc3. - mpidr linearisation (multiprocessor id register - identifies which CPU number we are in the system) This patch series that implements MPIDR linearization through a simple hashing algorithm and updates current cpu_{suspend}/{resume} code to use the newly created hash structures to retrieve context pointers. It represents a stepping stone for the implementation of power management code on forthcoming multi-cluster ARM systems. It has been tested on TC2 (dual cluster A15xA7 system), iMX6q, OMAP4 and Tegra, with processors hitting low-power states requiring warm-boot resume through the cpu_resume code path" * 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (77 commits) ARM: 7775/1: mm: Remove do_sect_fault from LPAE code ARM: 7777/1: Avoid extra calls to the C compiler ARM: 7774/1: Fix dtb dependency to use order-only prerequisites ARM: 7770/1: remove residual ARMv2 support from decompressor ARM: 7769/1: Cortex-A15: fix erratum 798181 implementation ARM: 7768/1: prevent risks of out-of-bound access in ASID allocator ARM: 7767/1: let the ASID allocator handle suspended animation ARM: 7766/1: versatile: don't mark pen as __INIT ARM: 7765/1: perf: Record the user-mode PC in the call chain. ARM: 7735/2: Preserve the user r/w register TPIDRURW on context switch and fork ARM: kernel: implement stack pointer save array through MPIDR hashing ARM: kernel: build MPIDR hash function data structure ARM: mpu: Ensure that MPU depends on CPU_V7 ARM: mpu: protect the vectors page with an MPU region ARM: mpu: Allow enabling of the MPU via kconfig ARM: 7758/1: introduce config HAS_BANDGAP ARM: 7757/1: mm: don't flush icache in switch_mm with hardware broadcasting ARM: 7751/1: zImage: don't overwrite ourself with a page table ARM: 7749/1: spinlock: retry trylock operation if strex fails on free lock ARM: 7748/1: oabi: handle faults when loading swi instruction from userspace ...
2013-07-03 09:46:29 -07:00 · 2013-07-03 09:46:29 -07:00 · fb2af0020a
commit fb2af0020a
parent 790eac5640 3c0c01ab74
88 changed files with 1991 additions and 422 deletions
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@ -16,6 +16,9 @@ Required properties:
     performs the same operation).
 	"marvell,"aurora-outer-cache: Marvell Controller designed to be
 	 compatible with the ARM one with outer cache mode.
+	"bcm,bcm11351-a2-pl310-cache": For Broadcom bcm11351 chipset where an
+	offset needs to be added to the address before passing down to the L2
+	cache controller
 - cache-unified : Specifies the cache is a unified cache.
 - cache-level : Should be set to 2 for a level 2 cache.
 - reg : Physical base address and size of cache controller's memory mapped
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@ -175,6 +175,9 @@ config ARCH_HAS_CPUFREQ
 	  and that the relevant menu configurations are displayed for
 	  it.

+config ARCH_HAS_BANDGAP
+	bool
+
 config GENERIC_HWEIGHT
 	bool
 	default y
@ -1450,7 +1453,7 @@ 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
@ -1471,7 +1474,7 @@ 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.
@ -1744,6 +1747,14 @@ 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
@ -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
@ -550,6 +550,13 @@ 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
@ -789,7 +796,8 @@ config DEBUG_LL_INCLUDE
 	default "debug/u300.S" if DEBUG_U300_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
@ -59,38 +59,44 @@ 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)
+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
 # always available in ARMv7
 ifeq ($(CONFIG_CPU_32v6),y)
-arch-$(CONFIG_CPU_32v6K)	:=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6k,-march=armv5t -Wa$(comma)-march=armv6k)
+arch-$(CONFIG_CPU_32v6K)	=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6k,-march=armv5t -Wa$(comma)-march=armv6k)
 endif
-arch-$(CONFIG_CPU_32v5)		:=-D__LINUX_ARM_ARCH__=5 $(call cc-option,-march=armv5te,-march=armv4t)
-arch-$(CONFIG_CPU_32v4T)	:=-D__LINUX_ARM_ARCH__=4 -march=armv4t
-arch-$(CONFIG_CPU_32v4)		:=-D__LINUX_ARM_ARCH__=4 -march=armv4
-arch-$(CONFIG_CPU_32v3)		:=-D__LINUX_ARM_ARCH__=3 -march=armv3
+arch-$(CONFIG_CPU_32v5)		=-D__LINUX_ARM_ARCH__=5 $(call cc-option,-march=armv5te,-march=armv4t)
+arch-$(CONFIG_CPU_32v4T)	=-D__LINUX_ARM_ARCH__=4 -march=armv4t
+arch-$(CONFIG_CPU_32v4)		=-D__LINUX_ARM_ARCH__=4 -march=armv4
+arch-$(CONFIG_CPU_32v3)		=-D__LINUX_ARM_ARCH__=3 -march=armv3
+
+# Evaluate arch cc-option calls now
+arch-y := $(arch-y)

 # This selects how we optimise for the processor.
-tune-$(CONFIG_CPU_ARM7TDMI)	:=-mtune=arm7tdmi
-tune-$(CONFIG_CPU_ARM720T)	:=-mtune=arm7tdmi
-tune-$(CONFIG_CPU_ARM740T)	:=-mtune=arm7tdmi
-tune-$(CONFIG_CPU_ARM9TDMI)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM940T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM946E)	:=$(call cc-option,-mtune=arm9e,-mtune=arm9tdmi)
-tune-$(CONFIG_CPU_ARM920T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM922T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM925T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM926T)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_FA526)	:=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_SA110)	:=-mtune=strongarm110
-tune-$(CONFIG_CPU_SA1100)	:=-mtune=strongarm1100
-tune-$(CONFIG_CPU_XSCALE)	:=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
-tune-$(CONFIG_CPU_XSC3)		:=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
-tune-$(CONFIG_CPU_FEROCEON)	:=$(call cc-option,-mtune=marvell-f,-mtune=xscale)
-tune-$(CONFIG_CPU_V6)		:=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
-tune-$(CONFIG_CPU_V6K)		:=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
+tune-$(CONFIG_CPU_ARM7TDMI)	=-mtune=arm7tdmi
+tune-$(CONFIG_CPU_ARM720T)	=-mtune=arm7tdmi
+tune-$(CONFIG_CPU_ARM740T)	=-mtune=arm7tdmi
+tune-$(CONFIG_CPU_ARM9TDMI)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM940T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM946E)	=$(call cc-option,-mtune=arm9e,-mtune=arm9tdmi)
+tune-$(CONFIG_CPU_ARM920T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM922T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM925T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM926T)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_FA526)	=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_SA110)	=-mtune=strongarm110
+tune-$(CONFIG_CPU_SA1100)	=-mtune=strongarm1100
+tune-$(CONFIG_CPU_XSCALE)	=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
+tune-$(CONFIG_CPU_XSC3)		=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
+tune-$(CONFIG_CPU_FEROCEON)	=$(call cc-option,-mtune=marvell-f,-mtune=xscale)
+tune-$(CONFIG_CPU_V6)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
+tune-$(CONFIG_CPU_V6K)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
+
+# Evaluate tune cc-option calls now
+tune-y := $(tune-y)

 ifeq ($(CONFIG_AEABI),y)
 CFLAGS_ABI	:=-mabi=aapcs-linux -mno-thumb-interwork
@ -295,9 +301,10 @@ zImage Image xipImage bootpImage uImage: vmlinux
 zinstall uinstall install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@

-%.dtb: scripts
+%.dtb: | scripts
 	$(Q)$(MAKE) $(build)=$(boot)/dts MACHINE=$(MACHINE) $(boot)/dts/$@

+PHONY += dtbs
 dtbs: scripts
 	$(Q)$(MAKE) $(build)=$(boot)/dts MACHINE=$(MACHINE) dtbs

--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@ -53,6 +53,17 @@ static const void *getprop(const void *fdt, const char *node_path,
 	return fdt_getprop(fdt, offset, property, len);
 }

+static uint32_t get_cell_size(const void *fdt)
+{
+	int len;
+	uint32_t cell_size = 1;
+	const uint32_t *size_len =  getprop(fdt, "/", "#size-cells", &len);
+
+	if (size_len)
+		cell_size = fdt32_to_cpu(*size_len);
+	return cell_size;
+}
+
 static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline)
 {
 	char cmdline[COMMAND_LINE_SIZE];
@ -95,9 +106,11 @@ static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline)
 int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 {
 	struct tag *atag = atag_list;
-	uint32_t mem_reg_property[2 * NR_BANKS];
+	/* In the case of 64 bits memory size, need to reserve 2 cells for
+	 * address and size for each bank */
+	uint32_t mem_reg_property[2 * 2 * NR_BANKS];
 	int memcount = 0;
-	int ret;
+	int ret, memsize;

 	/* make sure we've got an aligned pointer */
 	if ((u32)atag_list & 0x3)
@ -137,8 +150,25 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 				continue;
 			if (!atag->u.mem.size)
 				continue;
-			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start);
-			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size);
+			memsize = get_cell_size(fdt);
+
+			if (memsize == 2) {
+				/* if memsize is 2, that means that
+				 * each data needs 2 cells of 32 bits,
+				 * so the data are 64 bits */
+				uint64_t *mem_reg_prop64 =
+					(uint64_t *)mem_reg_property;
+				mem_reg_prop64[memcount++] =
+					cpu_to_fdt64(atag->u.mem.start);
+				mem_reg_prop64[memcount++] =
+					cpu_to_fdt64(atag->u.mem.size);
+			} else {
+				mem_reg_property[memcount++] =
+					cpu_to_fdt32(atag->u.mem.start);
+				mem_reg_property[memcount++] =
+					cpu_to_fdt32(atag->u.mem.size);
+			}
+
 		} else if (atag->hdr.tag == ATAG_INITRD2) {
 			uint32_t initrd_start, initrd_size;
 			initrd_start = atag->u.initrd.start;
@ -150,8 +180,10 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 		}
 	}

-	if (memcount)
-		setprop(fdt, "/memory", "reg", mem_reg_property, 4*memcount);
+	if (memcount) {
+		setprop(fdt, "/memory", "reg", mem_reg_property,
+			4 * memcount * memsize);
+	}

 	return fdt_pack(fdt);
 }
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@ -142,7 +142,6 @@ start:
 		mov	r7, r1			@ save architecture ID
 		mov	r8, r2			@ save atags pointer

-#ifndef __ARM_ARCH_2__
 		/*
 		 * Booting from Angel - need to enter SVC mode and disable
 		 * FIQs/IRQs (numeric definitions from angel arm.h source).
@ -158,10 +157,6 @@ not_angel:
 		safe_svcmode_maskall r0
 		msr	spsr_cxsf, r9		@ Save the CPU boot mode in
 						@ SPSR
-#else
-		teqp	pc, #0x0c000003		@ turn off interrupts
-#endif
-
 		/*
 		 * Note that some cache flushing and other stuff may
 		 * be needed here - is there an Angel SWI call for this?
@ -183,7 +178,19 @@ not_angel:
 		ldr	r4, =zreladdr
 #endif

-		bl	cache_on
+		/*
+		 * Set up a page table only if it won't overwrite ourself.
+		 * That means r4 < pc && r4 - 16k page directory > &_end.
+		 * Given that r4 > &_end is most unfrequent, we add a rough
+		 * additional 1MB of room for a possible appended DTB.
+		 */
+		mov	r0, pc
+		cmp	r0, r4
+		ldrcc	r0, LC0+32
+		addcc	r0, r0, pc
+		cmpcc	r4, r0
+		orrcc	r4, r4, #1		@ remember we skipped cache_on
+		blcs	cache_on

 restart:	adr	r0, LC0
 		ldmia	r0, {r1, r2, r3, r6, r10, r11, r12}
@ -229,7 +236,7 @@ restart:	adr	r0, LC0
 *   r0  = delta
 *   r2  = BSS start
 *   r3  = BSS end
- *   r4  = final kernel address
+ *   r4  = final kernel address (possibly with LSB set)
 *   r5  = appended dtb size (still unknown)
 *   r6  = _edata
 *   r7  = architecture ID
@ -277,6 +284,7 @@ restart:	adr	r0, LC0
 		 */
 		cmp	r0, #1
 		sub	r0, r4, #TEXT_OFFSET
+		bic	r0, r0, #1
 		add	r0, r0, #0x100
 		mov	r1, r6
 		sub	r2, sp, r6
@ -323,12 +331,13 @@ dtb_check_done:

 /*
 * Check to see if we will overwrite ourselves.
- *   r4  = final kernel address
+ *   r4  = final kernel address (possibly with LSB set)
 *   r9  = size of decompressed image
 *   r10 = end of this image, including  bss/stack/malloc space if non XIP
 * We basically want:
 *   r4 - 16k page directory >= r10 -> OK
 *   r4 + image length <= address of wont_overwrite -> OK
+ * Note: the possible LSB in r4 is harmless here.
 */
 		add	r10, r10, #16384
 		cmp	r4, r10
@ -390,7 +399,8 @@ dtb_check_done:
 		add	sp, sp, r6
 #endif

-		bl	cache_clean_flush
+		tst	r4, #1
+		bleq	cache_clean_flush

 		adr	r0, BSYM(restart)
 		add	r0, r0, r6
@ -402,7 +412,7 @@ wont_overwrite:
 *   r0  = delta
 *   r2  = BSS start
 *   r3  = BSS end
- *   r4  = kernel execution address
+ *   r4  = kernel execution address (possibly with LSB set)
 *   r5  = appended dtb size (0 if not present)
 *   r7  = architecture ID
 *   r8  = atags pointer
@ -465,6 +475,15 @@ not_relocated:	mov	r0, #0
 		cmp	r2, r3
 		blo	1b

+		/*
+		 * Did we skip the cache setup earlier?
+		 * That is indicated by the LSB in r4.
+		 * Do it now if so.
+		 */
+		tst	r4, #1
+		bic	r4, r4, #1
+		blne	cache_on
+
 /*
 * The C runtime environment should now be setup sufficiently.
 * Set up some pointers, and start decompressing.
@ -513,6 +532,7 @@ LC0:		.word	LC0			@ r1
 		.word	_got_start		@ r11
 		.word	_got_end		@ ip
 		.word	.L_user_stack_end	@ sp
+		.word	_end - restart + 16384 + 1024*1024
 		.size	LC0, . - LC0

 #ifdef CONFIG_ARCH_RPC
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@ -50,10 +50,10 @@
 	};

 	L2: l2-cache {
-		    compatible = "arm,pl310-cache";
-		    reg = <0x3ff20000 0x1000>;
-		    cache-unified;
-		    cache-level = <2>;
+		compatible = "bcm,bcm11351-a2-pl310-cache";
+		reg = <0x3ff20000 0x1000>;
+		cache-unified;
+		cache-level = <2>;
 	};

 	timer@35006000 {
--- a/arch/arm/common/mcpm_head.S
+++ b/arch/arm/common/mcpm_head.S
@ -32,11 +32,11 @@
 1901:	adr	r0, 1902b
 	bl	printascii
 	mov	r0, r9
-	bl	printhex8
+	bl	printhex2
 	adr	r0, 1903b
 	bl	printascii
 	mov	r0, r10
-	bl	printhex8
+	bl	printhex2
 	adr	r0, 1904b
 	bl	printascii
 #endif
--- a/arch/arm/common/mcpm_platsmp.c
+++ b/arch/arm/common/mcpm_platsmp.c
@ -19,10 +19,6 @@
 #include <asm/smp.h>
 #include <asm/smp_plat.h>

-static void __init simple_smp_init_cpus(void)
-{
-}
-
 static int __cpuinit mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	unsigned int mpidr, pcpu, pcluster, ret;
@ -74,7 +70,6 @@ static void mcpm_cpu_die(unsigned int cpu)
 #endif

 static struct smp_operations __initdata mcpm_smp_ops = {
-	.smp_init_cpus		= simple_smp_init_cpus,
 	.smp_boot_secondary	= mcpm_boot_secondary,
 	.smp_secondary_init	= mcpm_secondary_init,
 #ifdef CONFIG_HOTPLUG_CPU
--- 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/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
@ -8,6 +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
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@ -46,7 +46,7 @@
 	__rem;							\
 })

-#if __GNUC__ < 4
+#if __GNUC__ < 4 || !defined(CONFIG_AEABI)

 /*
 * gcc versions earlier than 4.0 are simply too problematic for the
--- a/arch/arm/include/asm/glue-proc.h
+++ b/arch/arm/include/asm/glue-proc.h
@ -230,15 +230,6 @@
 # endif
 #endif

-#ifdef CONFIG_CPU_PJ4B
-# ifdef CPU_NAME
-#  undef  MULTI_CPU
-#  define MULTI_CPU
-# else
-#  define CPU_NAME cpu_pj4b
-# endif
-#endif
-
 #ifdef CONFIG_CPU_V7M
 # ifdef CPU_NAME
 #  undef  MULTI_CPU
@ -248,6 +239,15 @@
 # endif
 #endif

+#ifdef CONFIG_CPU_PJ4B
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_pj4b
+# endif
+#endif
+
 #ifndef MULTI_CPU
 #define cpu_proc_init			__glue(CPU_NAME,_proc_init)
 #define cpu_proc_fin			__glue(CPU_NAME,_proc_fin)
--- 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/io.h
+++ b/arch/arm/include/asm/io.h
@ -130,16 +130,16 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 */
 extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
 	size_t, unsigned int, void *);
-extern void __iomem *__arm_ioremap_caller(unsigned long, size_t, unsigned int,
+extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
 	void *);

 extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap_exec(unsigned long, size_t, bool cached);
+extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
+extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
 extern void __arm_iounmap(volatile void __iomem *addr);

-extern void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 	unsigned int, void *);
 extern void (*arch_iounmap)(volatile void __iomem *);

--- 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/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@ -18,6 +18,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
+#include <asm/smp_plat.h>
 #include <asm-generic/mm_hooks.h>

 void __check_vmalloc_seq(struct mm_struct *mm);
@ -27,7 +28,15 @@ void __check_vmalloc_seq(struct mm_struct *mm);
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
 #define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })

-DECLARE_PER_CPU(atomic64_t, active_asids);
+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+			     cpumask_t *mask);
+#else  /* !CONFIG_ARM_ERRATA_798181 */
+static inline void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+					   cpumask_t *mask)
+{
+}
+#endif /* CONFIG_ARM_ERRATA_798181 */

 #else	/* !CONFIG_CPU_HAS_ASID */

@ -98,12 +107,16 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 #ifdef CONFIG_MMU
 	unsigned int cpu = smp_processor_id();

-#ifdef CONFIG_SMP
-	/* check for possible thread migration */
-	if (!cpumask_empty(mm_cpumask(next)) &&
+	/*
+	 * __sync_icache_dcache doesn't broadcast the I-cache invalidation,
+	 * so check for possible thread migration and invalidate the I-cache
+	 * if we're new to this CPU.
+	 */
+	if (cache_ops_need_broadcast() &&
+	    !cpumask_empty(mm_cpumask(next)) &&
 	    !cpumask_test_cpu(cpu, mm_cpumask(next)))
 		__flush_icache_all();
-#endif
+
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) {
 		check_and_switch_context(next, tsk);
 		if (cache_is_vivt())
--- 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/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/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@ -97,19 +97,22 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)

 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	unsigned long tmp;
+	unsigned long contended, res;
 	u32 slock;

-	__asm__ __volatile__(
-"	ldrex	%0, [%2]\n"
-"	subs	%1, %0, %0, ror #16\n"
-"	addeq	%0, %0, %3\n"
-"	strexeq	%1, %0, [%2]"
-	: "=&r" (slock), "=&r" (tmp)
-	: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
-	: "cc");
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%3]\n"
+		"	mov	%2, #0\n"
+		"	subs	%1, %0, %0, ror #16\n"
+		"	addeq	%0, %0, %4\n"
+		"	strexeq	%2, %0, [%3]"
+		: "=&r" (slock), "=&r" (contended), "=r" (res)
+		: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
+		: "cc");
+	} while (res);

-	if (tmp == 0) {
+	if (!contended) {
 		smp_mb();
 		return 1;
 	} else {
--- 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/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@ -58,7 +58,7 @@ struct thread_info {
 	struct cpu_context_save	cpu_context;	/* cpu context */
 	__u32			syscall;	/* syscall number */
 	__u8			used_cp[16];	/* thread used copro */
-	unsigned long		tp_value;
+	unsigned long		tp_value[2];	/* TLS registers */
 #ifdef CONFIG_CRUNCH
 	struct crunch_state	crunchstate;
 #endif
--- 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/tls.h
+++ b/arch/arm/include/asm/tls.h
@ -2,27 +2,30 @@
 #define __ASMARM_TLS_H

 #ifdef __ASSEMBLY__
-	.macro set_tls_none, tp, tmp1, tmp2
+#include <asm/asm-offsets.h>
+	.macro switch_tls_none, base, tp, tpuser, tmp1, tmp2
 	.endm

-	.macro set_tls_v6k, tp, tmp1, tmp2
+	.macro switch_tls_v6k, base, tp, tpuser, tmp1, tmp2
+	mrc	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
 	mcr	p15, 0, \tp, c13, c0, 3		@ set TLS register
-	mov	\tmp1, #0
-	mcr	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
+	mcr	p15, 0, \tpuser, c13, c0, 2	@ and the user r/w register
+	str	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
 	.endm

-	.macro set_tls_v6, tp, tmp1, tmp2
+	.macro switch_tls_v6, base, tp, tpuser, tmp1, tmp2
 	ldr	\tmp1, =elf_hwcap
 	ldr	\tmp1, [\tmp1, #0]
 	mov	\tmp2, #0xffff0fff
 	tst	\tmp1, #HWCAP_TLS		@ hardware TLS available?
-	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
-	movne	\tmp1, #0
-	mcrne	p15, 0, \tmp1, c13, c0, 2	@ clear user r/w TLS register
 	streq	\tp, [\tmp2, #-15]		@ set TLS value at 0xffff0ff0
+	mrcne	p15, 0, \tmp2, c13, c0, 2	@ get the user r/w register
+	mcrne	p15, 0, \tp, c13, c0, 3		@ yes, set TLS register
+	mcrne	p15, 0, \tpuser, c13, c0, 2	@ set user r/w register
+	strne	\tmp2, [\base, #TI_TP_VALUE + 4] @ save it
 	.endm

-	.macro set_tls_software, tp, tmp1, tmp2
+	.macro switch_tls_software, base, tp, tpuser, tmp1, tmp2
 	mov	\tmp1, #0xffff0fff
 	str	\tp, [\tmp1, #-15]		@ set TLS value at 0xffff0ff0
 	.endm
@ -31,19 +34,30 @@
 #ifdef CONFIG_TLS_REG_EMUL
 #define tls_emu		1
 #define has_tls_reg		1
-#define set_tls		set_tls_none
+#define switch_tls	switch_tls_none
 #elif defined(CONFIG_CPU_V6)
 #define tls_emu		0
 #define has_tls_reg		(elf_hwcap & HWCAP_TLS)
-#define set_tls		set_tls_v6
+#define switch_tls	switch_tls_v6
 #elif defined(CONFIG_CPU_32v6K)
 #define tls_emu		0
 #define has_tls_reg		1
-#define set_tls		set_tls_v6k
+#define switch_tls	switch_tls_v6k
 #else
 #define tls_emu		0
 #define has_tls_reg		0
-#define set_tls		set_tls_software
+#define switch_tls	switch_tls_software
 #endif

+#ifndef __ASSEMBLY__
+static inline unsigned long get_tpuser(void)
+{
+	unsigned long reg = 0;
+
+	if (has_tls_reg && !tls_emu)
+		__asm__("mrc p15, 0, %0, c13, c0, 2" : "=r" (reg));
+
+	return reg;
+}
+#endif
 #endif	/* __ASMARM_TLS_H */
--- 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/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
--- 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-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@ -685,15 +685,16 @@ ENTRY(__switch_to)
 UNWIND(.fnstart	)
 UNWIND(.cantunwind	)
 	add	ip, r1, #TI_CPU_SAVE
-	ldr	r3, [r2, #TI_TP_VALUE]
 ARM(	stmia	ip!, {r4 - sl, fp, sp, lr} )	@ Store most regs on stack
 THUMB(	stmia	ip!, {r4 - sl, fp}	   )	@ Store most regs on stack
 THUMB(	str	sp, [ip], #4		   )
 THUMB(	str	lr, [ip], #4		   )
+	ldr	r4, [r2, #TI_TP_VALUE]
+	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
-	set_tls	r3, r4, r5
+	switch_tls r1, r4, r5, r3, r7
 #if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
 	ldr	r7, [r2, #TI_TASK]
 	ldr	r8, =__stack_chk_guard
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@ -366,6 +366,16 @@ ENTRY(vector_swi)
 #endif
 	zero_fp

+#ifdef CONFIG_ALIGNMENT_TRAP
+	ldr	ip, __cr_alignment
+	ldr	ip, [ip]
+	mcr	p15, 0, ip, c1, c0		@ update control register
+#endif
+
+	enable_irq
+	ct_user_exit
+	get_thread_info tsk
+
 	/*
 	 * Get the system call number.
 	 */
@ -379,9 +389,9 @@ ENTRY(vector_swi)
 #ifdef CONFIG_ARM_THUMB
 	tst	r8, #PSR_T_BIT
 	movne	r10, #0				@ no thumb OABI emulation
-	ldreq	r10, [lr, #-4]			@ get SWI instruction
+ USER(	ldreq	r10, [lr, #-4]		)	@ get SWI instruction
 #else
-	ldr	r10, [lr, #-4]			@ get SWI instruction
+ USER(	ldr	r10, [lr, #-4]		)	@ get SWI instruction
 #endif
 #ifdef CONFIG_CPU_ENDIAN_BE8
 	rev	r10, r10			@ little endian instruction
@ -396,22 +406,13 @@ ENTRY(vector_swi)
 	/* Legacy ABI only, possibly thumb mode. */
 	tst	r8, #PSR_T_BIT			@ this is SPSR from save_user_regs
 	addne	scno, r7, #__NR_SYSCALL_BASE	@ put OS number in
-	ldreq	scno, [lr, #-4]
+ USER(	ldreq	scno, [lr, #-4]		)

 #else
 	/* Legacy ABI only. */
-	ldr	scno, [lr, #-4]			@ get SWI instruction
+ USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif

-#ifdef CONFIG_ALIGNMENT_TRAP
-	ldr	ip, __cr_alignment
-	ldr	ip, [ip]
-	mcr	p15, 0, ip, c1, c0		@ update control register
-#endif
-	enable_irq
-	ct_user_exit
-
-	get_thread_info tsk
 	adr	tbl, sys_call_table		@ load syscall table pointer

 #if defined(CONFIG_OABI_COMPAT)
@ -446,6 +447,21 @@ local_restart:
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
 	bcs	arm_syscall	
 	b	sys_ni_syscall			@ not private func
+
+#if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)
+	/*
+	 * We failed to handle a fault trying to access the page
+	 * containing the swi instruction, but we're not really in a
+	 * position to return -EFAULT. Instead, return back to the
+	 * instruction and re-enter the user fault handling path trying
+	 * to page it in. This will likely result in sending SEGV to the
+	 * current task.
+	 */
+9001:
+	sub	lr, lr, #4
+	str	lr, [sp, #S_PC]
+	b	ret_fast_syscall
+#endif
 ENDPROC(vector_swi)

 	/*
--- 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"
--- 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/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@ -569,6 +569,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		return;
 	}

+	perf_callchain_store(entry, regs->ARM_pc);
 	tail = (struct frame_tail __user *)regs->ARM_fp - 1;

 	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@ -39,6 +39,7 @@
 #include <asm/thread_notify.h>
 #include <asm/stacktrace.h>
 #include <asm/mach/time.h>
+#include <asm/tls.h>

 #ifdef CONFIG_CC_STACKPROTECTOR
 #include <linux/stackprotector.h>
@ -374,7 +375,8 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	clear_ptrace_hw_breakpoint(p);

 	if (clone_flags & CLONE_SETTLS)
-		thread->tp_value = childregs->ARM_r3;
+		thread->tp_value[0] = childregs->ARM_r3;
+	thread->tp_value[1] = get_tpuser();

 	thread_notify(THREAD_NOTIFY_COPY, thread);

--- a/arch/arm/kernel/psci_smp.c
+++ b/arch/arm/kernel/psci_smp.c
@ -68,8 +68,6 @@ void __ref psci_cpu_die(unsigned int cpu)
       /* We should never return */
       panic("psci: cpu %d failed to shutdown\n", cpu);
 }
-#else
-#define psci_cpu_die NULL
 #endif

 bool __init psci_smp_available(void)
@ -80,5 +78,7 @@ bool __init psci_smp_available(void)

 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/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@ -849,7 +849,7 @@ long arch_ptrace(struct task_struct *child, long request,
 #endif

 		case PTRACE_GET_THREAD_AREA:
-			ret = put_user(task_thread_info(child)->tp_value,
+			ret = put_user(task_thread_info(child)->tp_value[0],
 				       datap);
 			break;

--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@ -367,7 +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;
@ -380,6 +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)
@ -470,9 +475,82 @@ void __init smp_setup_processor_id(void)
 	for (i = 1; i < nr_cpu_ids; ++i)
 		cpu_logical_map(i) = i == cpu ? 0 : i;

+	/*
+	 * clear __my_cpu_offset on boot CPU to avoid hang caused by
+	 * using percpu variable early, for example, lockdep will
+	 * access percpu variable inside lock_release
+	 */
+	set_my_cpu_offset(0);
+
 	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;
@ -820,6 +898,7 @@ void __init setup_arch(char **cmdline_p)
 				smp_set_ops(mdesc->smp);
 		}
 		smp_init_cpus();
+		smp_build_mpidr_hash();
 	}
 #endif

@ -892,6 +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/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@ -103,7 +103,7 @@ static void broadcast_tlb_a15_erratum(void)

 static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
 {
-	int cpu, this_cpu;
+	int this_cpu;
 	cpumask_t mask = { CPU_BITS_NONE };

 	if (!erratum_a15_798181())
@ -111,21 +111,7 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)

 	dummy_flush_tlb_a15_erratum();
 	this_cpu = get_cpu();
-	for_each_online_cpu(cpu) {
-		if (cpu == this_cpu)
-			continue;
-		/*
-		 * We only need to send an IPI if the other CPUs are running
-		 * the same ASID as the one being invalidated. There is no
-		 * need for locking around the active_asids check since the
-		 * switch_mm() function has at least one dmb() (as required by
-		 * this workaround) in case a context switch happens on
-		 * another CPU after the condition below.
-		 */
-		if (atomic64_read(&mm->context.id) ==
-		    atomic64_read(&per_cpu(active_asids, cpu)))
-			cpumask_set_cpu(cpu, &mask);
-	}
+	a15_erratum_get_cpumask(this_cpu, mm, &mask);
 	smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);
 	put_cpu();
 }
--- 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
@ -581,7 +581,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 		return regs->ARM_r0;

 	case NR(set_tls):
-		thread->tp_value = regs->ARM_r0;
+		thread->tp_value[0] = regs->ARM_r0;
 		if (tls_emu)
 			return 0;
 		if (has_tls_reg) {
@ -699,7 +699,7 @@ static int get_tp_trap(struct pt_regs *regs, unsigned int instr)
 	int reg = (instr >> 12) & 15;
 	if (reg == 15)
 		return 1;
-	regs->uregs[reg] = current_thread_info()->tp_value;
+	regs->uregs[reg] = current_thread_info()->tp_value[0];
 	regs->ARM_pc += 4;
 	return 0;
 }
--- 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-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@ -116,7 +116,7 @@ static void __init ebsa110_map_io(void)
 	iotable_init(ebsa110_io_desc, ARRAY_SIZE(ebsa110_io_desc));
 }

-static void __iomem *ebsa110_ioremap_caller(unsigned long cookie, size_t size,
+static void __iomem *ebsa110_ioremap_caller(phys_addr_t cookie, size_t size,
 					    unsigned int flags, void *caller)
 {
 	return (void __iomem *)cookie;
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@ -93,7 +93,7 @@ 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 MIGHT_HAVE_PCI
 	select PCI_DOMAINS if PCI
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@ -65,7 +65,7 @@ static void imx3_idle(void)
 		: "=r" (reg));
 }

-static void __iomem *imx3_ioremap_caller(unsigned long phys_addr, size_t size,
+static void __iomem *imx3_ioremap_caller(phys_addr_t phys_addr, size_t size,
 					 unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
--- a/arch/arm/mach-iop13xx/io.c
+++ b/arch/arm/mach-iop13xx/io.c
@ -23,7 +23,7 @@

 #include "pci.h"

-static void __iomem *__iop13xx_ioremap_caller(unsigned long cookie,
+static void __iomem *__iop13xx_ioremap_caller(phys_addr_t cookie,
 	size_t size, unsigned int mtype, void *caller)
 {
 	void __iomem * retval;
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@ -559,7 +559,7 @@ void ixp4xx_restart(char mode, const char *cmd)
 * fallback to the default.
 */

-static void __iomem *ixp4xx_ioremap_caller(unsigned long addr, size_t size,
+static void __iomem *ixp4xx_ioremap_caller(phys_addr_t addr, size_t size,
 					   unsigned int mtype, void *caller)
 {
 	if (!is_pci_memory(addr))
--- a/arch/arm/mach-msm/common.h
+++ b/arch/arm/mach-msm/common.h
@ -23,7 +23,7 @@ extern void msm_map_msm8x60_io(void);
 extern void msm_map_msm8960_io(void);
 extern void msm_map_qsd8x50_io(void);

-extern void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+extern void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 					  unsigned int mtype, void *caller);

 extern struct smp_operations msm_smp_ops;
--- a/arch/arm/mach-msm/io.c
+++ b/arch/arm/mach-msm/io.c
@ -168,7 +168,7 @@ void __init msm_map_msm7x30_io(void)
 }
 #endif /* CONFIG_ARCH_MSM7X30 */

-void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
 	if (mtype == MT_DEVICE) {
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@ -4,6 +4,7 @@ config ARCH_OMAP
 config ARCH_OMAP2PLUS
 	bool "TI OMAP2/3/4/5 SoCs with device tree support" if (ARCH_MULTI_V6 || ARCH_MULTI_V7)
 	select ARCH_HAS_CPUFREQ
+	select ARCH_HAS_BANDGAP
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
 	select ARCH_REQUIRE_GPIOLIB
--- 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

@ -59,7 +59,7 @@ 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/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
--- 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
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@ -523,6 +523,147 @@ static void aurora_flush_range(unsigned long start, unsigned long end)
 	}
 }

+/*
+ * For certain Broadcom SoCs, depending on the address range, different offsets
+ * need to be added to the address before passing it to L2 for
+ * invalidation/clean/flush
+ *
+ * Section Address Range              Offset        EMI
+ *   1     0x00000000 - 0x3FFFFFFF    0x80000000    VC
+ *   2     0x40000000 - 0xBFFFFFFF    0x40000000    SYS
+ *   3     0xC0000000 - 0xFFFFFFFF    0x80000000    VC
+ *
+ * When the start and end addresses have crossed two different sections, we
+ * need to break the L2 operation into two, each within its own section.
+ * For example, if we need to invalidate addresses starts at 0xBFFF0000 and
+ * ends at 0xC0001000, we need do invalidate 1) 0xBFFF0000 - 0xBFFFFFFF and 2)
+ * 0xC0000000 - 0xC0001000
+ *
+ * Note 1:
+ * By breaking a single L2 operation into two, we may potentially suffer some
+ * performance hit, but keep in mind the cross section case is very rare
+ *
+ * Note 2:
+ * We do not need to handle the case when the start address is in
+ * Section 1 and the end address is in Section 3, since it is not a valid use
+ * case
+ *
+ * Note 3:
+ * Section 1 in practical terms can no longer be used on rev A2. Because of
+ * that the code does not need to handle section 1 at all.
+ *
+ */
+#define BCM_SYS_EMI_START_ADDR        0x40000000UL
+#define BCM_VC_EMI_SEC3_START_ADDR    0xC0000000UL
+
+#define BCM_SYS_EMI_OFFSET            0x40000000UL
+#define BCM_VC_EMI_OFFSET             0x80000000UL
+
+static inline int bcm_addr_is_sys_emi(unsigned long addr)
+{
+	return (addr >= BCM_SYS_EMI_START_ADDR) &&
+		(addr < BCM_VC_EMI_SEC3_START_ADDR);
+}
+
+static inline unsigned long bcm_l2_phys_addr(unsigned long addr)
+{
+	if (bcm_addr_is_sys_emi(addr))
+		return addr + BCM_SYS_EMI_OFFSET;
+	else
+		return addr + BCM_VC_EMI_OFFSET;
+}
+
+static void bcm_inv_range(unsigned long start, unsigned long end)
+{
+	unsigned long new_start, new_end;
+
+	BUG_ON(start < BCM_SYS_EMI_START_ADDR);
+
+	if (unlikely(end <= start))
+		return;
+
+	new_start = bcm_l2_phys_addr(start);
+	new_end = bcm_l2_phys_addr(end);
+
+	/* normal case, no cross section between start and end */
+	if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
+		l2x0_inv_range(new_start, new_end);
+		return;
+	}
+
+	/* They cross sections, so it can only be a cross from section
+	 * 2 to section 3
+	 */
+	l2x0_inv_range(new_start,
+		bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
+	l2x0_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+		new_end);
+}
+
+static void bcm_clean_range(unsigned long start, unsigned long end)
+{
+	unsigned long new_start, new_end;
+
+	BUG_ON(start < BCM_SYS_EMI_START_ADDR);
+
+	if (unlikely(end <= start))
+		return;
+
+	if ((end - start) >= l2x0_size) {
+		l2x0_clean_all();
+		return;
+	}
+
+	new_start = bcm_l2_phys_addr(start);
+	new_end = bcm_l2_phys_addr(end);
+
+	/* normal case, no cross section between start and end */
+	if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
+		l2x0_clean_range(new_start, new_end);
+		return;
+	}
+
+	/* They cross sections, so it can only be a cross from section
+	 * 2 to section 3
+	 */
+	l2x0_clean_range(new_start,
+		bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
+	l2x0_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+		new_end);
+}
+
+static void bcm_flush_range(unsigned long start, unsigned long end)
+{
+	unsigned long new_start, new_end;
+
+	BUG_ON(start < BCM_SYS_EMI_START_ADDR);
+
+	if (unlikely(end <= start))
+		return;
+
+	if ((end - start) >= l2x0_size) {
+		l2x0_flush_all();
+		return;
+	}
+
+	new_start = bcm_l2_phys_addr(start);
+	new_end = bcm_l2_phys_addr(end);
+
+	/* normal case, no cross section between start and end */
+	if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
+		l2x0_flush_range(new_start, new_end);
+		return;
+	}
+
+	/* They cross sections, so it can only be a cross from section
+	 * 2 to section 3
+	 */
+	l2x0_flush_range(new_start,
+		bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
+	l2x0_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+		new_end);
+}
+
 static void __init l2x0_of_setup(const struct device_node *np,
 				 u32 *aux_val, u32 *aux_mask)
 {
@ -765,6 +906,21 @@ static const struct l2x0_of_data aurora_no_outer_data = {
 	},
 };

+static const struct l2x0_of_data bcm_l2x0_data = {
+	.setup = pl310_of_setup,
+	.save  = pl310_save,
+	.outer_cache = {
+		.resume      = pl310_resume,
+		.inv_range   = bcm_inv_range,
+		.clean_range = bcm_clean_range,
+		.flush_range = bcm_flush_range,
+		.sync        = l2x0_cache_sync,
+		.flush_all   = l2x0_flush_all,
+		.inv_all     = l2x0_inv_all,
+		.disable     = l2x0_disable,
+	},
+};
+
 static const struct of_device_id l2x0_ids[] __initconst = {
 	{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
 	{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
@ -773,6 +929,8 @@ static const struct of_device_id l2x0_ids[] __initconst = {
 	  .data = (void *)&aurora_no_outer_data},
 	{ .compatible = "marvell,aurora-outer-cache",
 	  .data = (void *)&aurora_with_outer_data},
+	{ .compatible = "bcm,bcm11351-a2-pl310-cache",
+	  .data = (void *)&bcm_l2x0_data},
 	{}
 };

--- 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:
@ -39,33 +40,51 @@
 * non 64-bit operations.
 */
 #define ASID_FIRST_VERSION	(1ULL << ASID_BITS)
-#define NUM_USER_ASIDS		(ASID_FIRST_VERSION - 1)
-
-#define ASID_TO_IDX(asid)	((asid & ~ASID_MASK) - 1)
-#define IDX_TO_ASID(idx)	((idx + 1) & ~ASID_MASK)
+#define NUM_USER_ASIDS		ASID_FIRST_VERSION

 static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
 static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
 static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);

-DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(atomic64_t, active_asids);
 static DEFINE_PER_CPU(u64, reserved_asids);
 static cpumask_t tlb_flush_pending;

+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+			     cpumask_t *mask)
+{
+	int cpu;
+	unsigned long flags;
+	u64 context_id, asid;
+
+	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+	context_id = mm->context.id.counter;
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+		/*
+		 * We only need to send an IPI if the other CPUs are
+		 * running the same ASID as the one being invalidated.
+		 */
+		asid = per_cpu(active_asids, cpu).counter;
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, cpu);
+		if (context_id == asid)
+			cpumask_set_cpu(cpu, mask);
+	}
+	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+}
+#endif
+
 #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
@ -128,7 +147,16 @@ static void flush_context(unsigned int cpu)
 			asid = 0;
 		} else {
 			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			__set_bit(ASID_TO_IDX(asid), asid_map);
+			/*
+			 * If this CPU has already been through a
+			 * rollover, but hasn't run another task in
+			 * the meantime, we must preserve its reserved
+			 * ASID, as this is the only trace we have of
+			 * the process it is still running.
+			 */
+			if (asid == 0)
+				asid = per_cpu(reserved_asids, i);
+			__set_bit(asid & ~ASID_MASK, asid_map);
 		}
 		per_cpu(reserved_asids, i) = asid;
 	}
@ -167,17 +195,19 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 		/*
 		 * Allocate a free ASID. If we can't find one, take a
 		 * note of the currently active ASIDs and mark the TLBs
-		 * as requiring flushes.
+		 * as requiring flushes. We always count from ASID #1,
+		 * as we reserve ASID #0 to switch via TTBR0 and indicate
+		 * rollover events.
 		 */
-		asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+		asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 		if (asid == NUM_USER_ASIDS) {
 			generation = atomic64_add_return(ASID_FIRST_VERSION,
 							 &asid_generation);
 			flush_context(cpu);
-			asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+			asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 		}
 		__set_bit(asid, asid_map);
-		asid = generation | IDX_TO_ASID(asid);
+		asid |= generation;
 		cpumask_clear(mm_cpumask(mm));
 	}

--- 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,
@ -880,10 +880,24 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
 	dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);

 	/*
-	 * Mark the D-cache clean for this page to avoid extra flushing.
+	 * Mark the D-cache clean for these pages to avoid extra flushing.
 	 */
-	if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
-		set_bit(PG_dcache_clean, &page->flags);
+	if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) {
+		unsigned long pfn;
+		size_t left = size;
+
+		pfn = page_to_pfn(page) + off / PAGE_SIZE;
+		off %= PAGE_SIZE;
+		if (off) {
+			pfn++;
+			left -= PAGE_SIZE - off;
+		}
+		while (left >= PAGE_SIZE) {
+			page = pfn_to_page(pfn++);
+			set_bit(PG_dcache_clean, &page->flags);
+			left -= PAGE_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);
+				}
 			}
 		}
 	}
@ -287,7 +292,7 @@ void flush_dcache_page(struct page *page)
 	mapping = page_mapping(page);

 	if (!cache_ops_need_broadcast() &&
-	    mapping && !mapping_mapped(mapping))
+	    mapping && !page_mapped(page))
 		clear_bit(PG_dcache_clean, &page->flags);
 	else {
 		__flush_dcache_page(mapping, 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/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@ -331,10 +331,10 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	return (void __iomem *) (offset + addr);
 }

-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 	unsigned int mtype, void *caller)
 {
-	unsigned long last_addr;
+	phys_addr_t last_addr;
 	unsigned long offset = phys_addr & ~PAGE_MASK;
 	unsigned long pfn = __phys_to_pfn(phys_addr);

@ -367,12 +367,12 @@ __arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);

-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 				      unsigned int, void *) =
 	__arm_ioremap_caller;

 void __iomem *
-__arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
+__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
 {
 	return arch_ioremap_caller(phys_addr, size, mtype,
 		__builtin_return_address(0));
@ -387,7 +387,7 @@ EXPORT_SYMBOL(__arm_ioremap);
 * CONFIG_GENERIC_ALLOCATOR for allocating external memory.
 */
 void __iomem *
-__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
+__arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached)
 {
 	unsigned int mtype;

--- 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>
@ -15,9 +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();
 }

@ -94,16 +349,16 @@ void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
 	return __arm_ioremap_pfn(pfn, offset, size, mtype);
 }

-void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
 			    unsigned int mtype)
 {
 	return (void __iomem *)phys_addr;
 }
 EXPORT_SYMBOL(__arm_ioremap);

-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, unsigned int, void *);
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);

-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
 	return __arm_ioremap(phys_addr, size, mtype);
--- 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/plat-versatile/headsmp.S
+++ b/arch/arm/plat-versatile/headsmp.S
@ -11,8 +11,6 @@
 #include <linux/linkage.h>
 #include <linux/init.h>

-	__INIT
-
 /*
 * Realview/Versatile Express specific entry point for secondary CPUs.
 * This provides a "holding pen" into which all secondary cores are held
--- 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/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@ -61,6 +61,7 @@ static unsigned int fmax = 515633;
 * @pwrreg_powerup: power up value for MMCIPOWER register
 * @signal_direction: input/out direction of bus signals can be indicated
 * @pwrreg_clkgate: MMCIPOWER register must be used to gate the clock
+ * @busy_detect: true if busy detection on dat0 is supported
 */
 struct variant_data {
 	unsigned int		clkreg;
@ -74,6 +75,7 @@ struct variant_data {
 	u32			pwrreg_powerup;
 	bool			signal_direction;
 	bool			pwrreg_clkgate;
+	bool			busy_detect;
 };

 static struct variant_data variant_arm = {
@ -132,6 +134,7 @@ static struct variant_data variant_ux500 = {
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
+	.busy_detect		= true,
 };

 static struct variant_data variant_ux500v2 = {
@ -146,8 +149,28 @@ static struct variant_data variant_ux500v2 = {
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
+	.busy_detect		= true,
 };

+static int mmci_card_busy(struct mmc_host *mmc)
+{
+	struct mmci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	int busy = 0;
+
+	pm_runtime_get_sync(mmc_dev(mmc));
+
+	spin_lock_irqsave(&host->lock, flags);
+	if (readl(host->base + MMCISTATUS) & MCI_ST_CARDBUSY)
+		busy = 1;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	pm_runtime_mark_last_busy(mmc_dev(mmc));
+	pm_runtime_put_autosuspend(mmc_dev(mmc));
+
+	return busy;
+}
+
 /*
 * Validate mmc prerequisites
 */
@ -188,6 +211,20 @@ static void mmci_write_pwrreg(struct mmci_host *host, u32 pwr)
 	}
 }

+/*
+ * This must be called with host->lock held
+ */
+static void mmci_write_datactrlreg(struct mmci_host *host, u32 datactrl)
+{
+	/* Keep ST Micro busy mode if enabled */
+	datactrl |= host->datactrl_reg & MCI_ST_DPSM_BUSYMODE;
+
+	if (host->datactrl_reg != datactrl) {
+		host->datactrl_reg = datactrl;
+		writel(datactrl, host->base + MMCIDATACTRL);
+	}
+}
+
 /*
 * This must be called with host->lock held
 */
@ -196,6 +233,9 @@ static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
 	struct variant_data *variant = host->variant;
 	u32 clk = variant->clkreg;

+	/* Make sure cclk reflects the current calculated clock */
+	host->cclk = 0;
+
 	if (desired) {
 		if (desired >= host->mclk) {
 			clk = MCI_CLK_BYPASS;
@ -230,6 +270,9 @@ static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
 		/* clk |= MCI_CLK_PWRSAVE; */
 	}

+	/* Set actual clock for debug */
+	host->mmc->actual_clock = host->cclk;
+
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_4)
 		clk |= MCI_4BIT_BUS;
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_8)
@ -275,7 +318,7 @@ static void mmci_set_mask1(struct mmci_host *host, unsigned int mask)

 static void mmci_stop_data(struct mmci_host *host)
 {
-	writel(0, host->base + MMCIDATACTRL);
+	mmci_write_datactrlreg(host, 0);
 	mmci_set_mask1(host, 0);
 	host->data = NULL;
 }
@ -304,10 +347,8 @@ static void mmci_dma_setup(struct mmci_host *host)
 	const char *rxname, *txname;
 	dma_cap_mask_t mask;

-	if (!plat || !plat->dma_filter) {
-		dev_info(mmc_dev(host->mmc), "no DMA platform data\n");
-		return;
-	}
+	host->dma_rx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "rx");
+	host->dma_tx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "tx");

 	/* initialize pre request cookie */
 	host->next_data.cookie = 1;
@ -316,29 +357,32 @@ static void mmci_dma_setup(struct mmci_host *host)
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);

+	if (plat && plat->dma_filter) {
+		if (!host->dma_rx_channel && plat->dma_rx_param) {
+			host->dma_rx_channel = dma_request_channel(mask,
+							   plat->dma_filter,
+							   plat->dma_rx_param);
+			/* E.g if no DMA hardware is present */
+			if (!host->dma_rx_channel)
+				dev_err(mmc_dev(host->mmc), "no RX DMA channel\n");
+		}
+
+		if (!host->dma_tx_channel && plat->dma_tx_param) {
+			host->dma_tx_channel = dma_request_channel(mask,
+							   plat->dma_filter,
+							   plat->dma_tx_param);
+			if (!host->dma_tx_channel)
+				dev_warn(mmc_dev(host->mmc), "no TX DMA channel\n");
+		}
+	}
+
 	/*
 	 * If only an RX channel is specified, the driver will
 	 * attempt to use it bidirectionally, however if it is
 	 * is specified but cannot be located, DMA will be disabled.
 	 */
-	if (plat->dma_rx_param) {
-		host->dma_rx_channel = dma_request_channel(mask,
-							   plat->dma_filter,
-							   plat->dma_rx_param);
-		/* E.g if no DMA hardware is present */
-		if (!host->dma_rx_channel)
-			dev_err(mmc_dev(host->mmc), "no RX DMA channel\n");
-	}
-
-	if (plat->dma_tx_param) {
-		host->dma_tx_channel = dma_request_channel(mask,
-							   plat->dma_filter,
-							   plat->dma_tx_param);
-		if (!host->dma_tx_channel)
-			dev_warn(mmc_dev(host->mmc), "no TX DMA channel\n");
-	} else {
+	if (host->dma_rx_channel && !host->dma_tx_channel)
 		host->dma_tx_channel = host->dma_rx_channel;
-	}

 	if (host->dma_rx_channel)
 		rxname = dma_chan_name(host->dma_rx_channel);
@ -552,7 +596,7 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 	datactrl |= MCI_DPSM_DMAENABLE;

 	/* Trigger the DMA transfer */
-	writel(datactrl, host->base + MMCIDATACTRL);
+	mmci_write_datactrlreg(host, datactrl);

 	/*
 	 * Let the MMCI say when the data is ended and it's time
@ -750,7 +794,7 @@ static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 		irqmask = MCI_TXFIFOHALFEMPTYMASK;
 	}

-	writel(datactrl, base + MMCIDATACTRL);
+	mmci_write_datactrlreg(host, datactrl);
 	writel(readl(base + MMCIMASK0) & ~MCI_DATAENDMASK, base + MMCIMASK0);
 	mmci_set_mask1(host, irqmask);
 }
@ -842,7 +886,7 @@ mmci_data_irq(struct mmci_host *host, struct mmc_data *data,
 			/* The error clause is handled above, success! */
 			data->bytes_xfered = data->blksz * data->blocks;

-		if (!data->stop) {
+		if (!data->stop || host->mrq->sbc) {
 			mmci_request_end(host, data->mrq);
 		} else {
 			mmci_start_command(host, data->stop, 0);
@ -855,6 +899,7 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 	     unsigned int status)
 {
 	void __iomem *base = host->base;
+	bool sbc = (cmd == host->mrq->sbc);

 	host->cmd = NULL;

@ -869,7 +914,7 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 		cmd->resp[3] = readl(base + MMCIRESPONSE3);
 	}

-	if (!cmd->data || cmd->error) {
+	if ((!sbc && !cmd->data) || cmd->error) {
 		if (host->data) {
 			/* Terminate the DMA transfer */
 			if (dma_inprogress(host)) {
@ -878,7 +923,9 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 			}
 			mmci_stop_data(host);
 		}
-		mmci_request_end(host, cmd->mrq);
+		mmci_request_end(host, host->mrq);
+	} else if (sbc) {
+		mmci_start_command(host, host->mrq->cmd, 0);
 	} else if (!(cmd->data->flags & MMC_DATA_READ)) {
 		mmci_start_data(host, cmd->data);
 	}
@ -1119,7 +1166,10 @@ static void mmci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	if (mrq->data && mrq->data->flags & MMC_DATA_READ)
 		mmci_start_data(host, mrq->data);

-	mmci_start_command(host, mrq->cmd, 0);
+	if (mrq->sbc)
+		mmci_start_command(host, mrq->sbc, 0);
+	else
+		mmci_start_command(host, mrq->cmd, 0);

 	spin_unlock_irqrestore(&host->lock, flags);
 }
@ -1143,9 +1193,10 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		if (!IS_ERR(mmc->supply.vmmc))
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);

-		if (!IS_ERR(mmc->supply.vqmmc) &&
-		    regulator_is_enabled(mmc->supply.vqmmc))
+		if (!IS_ERR(mmc->supply.vqmmc) && host->vqmmc_enabled) {
 			regulator_disable(mmc->supply.vqmmc);
+			host->vqmmc_enabled = false;
+		}

 		break;
 	case MMC_POWER_UP:
@ -1161,12 +1212,13 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)

 		break;
 	case MMC_POWER_ON:
-		if (!IS_ERR(mmc->supply.vqmmc) &&
-		    !regulator_is_enabled(mmc->supply.vqmmc)) {
+		if (!IS_ERR(mmc->supply.vqmmc) && !host->vqmmc_enabled) {
 			ret = regulator_enable(mmc->supply.vqmmc);
 			if (ret < 0)
 				dev_err(mmc_dev(mmc),
 					"failed to enable vqmmc regulator\n");
+			else
+				host->vqmmc_enabled = true;
 		}

 		pwr |= MCI_PWR_ON;
@ -1251,6 +1303,39 @@ static int mmci_get_cd(struct mmc_host *mmc)
 	return status;
 }

+static int mmci_sig_volt_switch(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	int ret = 0;
+
+	if (!IS_ERR(mmc->supply.vqmmc)) {
+
+		pm_runtime_get_sync(mmc_dev(mmc));
+
+		switch (ios->signal_voltage) {
+		case MMC_SIGNAL_VOLTAGE_330:
+			ret = regulator_set_voltage(mmc->supply.vqmmc,
+						2700000, 3600000);
+			break;
+		case MMC_SIGNAL_VOLTAGE_180:
+			ret = regulator_set_voltage(mmc->supply.vqmmc,
+						1700000, 1950000);
+			break;
+		case MMC_SIGNAL_VOLTAGE_120:
+			ret = regulator_set_voltage(mmc->supply.vqmmc,
+						1100000, 1300000);
+			break;
+		}
+
+		if (ret)
+			dev_warn(mmc_dev(mmc), "Voltage switch failed\n");
+
+		pm_runtime_mark_last_busy(mmc_dev(mmc));
+		pm_runtime_put_autosuspend(mmc_dev(mmc));
+	}
+
+	return ret;
+}
+
 static irqreturn_t mmci_cd_irq(int irq, void *dev_id)
 {
 	struct mmci_host *host = dev_id;
@ -1260,13 +1345,14 @@ static irqreturn_t mmci_cd_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }

-static const struct mmc_host_ops mmci_ops = {
+static struct mmc_host_ops mmci_ops = {
 	.request	= mmci_request,
 	.pre_req	= mmci_pre_request,
 	.post_req	= mmci_post_request,
 	.set_ios	= mmci_set_ios,
 	.get_ro		= mmci_get_ro,
 	.get_cd		= mmci_get_cd,
+	.start_signal_voltage_switch = mmci_sig_volt_switch,
 };

 #ifdef CONFIG_OF
@ -1362,16 +1448,15 @@ static int mmci_probe(struct amba_device *dev,
 	dev_dbg(mmc_dev(mmc), "designer ID = 0x%02x\n", host->hw_designer);
 	dev_dbg(mmc_dev(mmc), "revision = 0x%01x\n", host->hw_revision);

-	host->clk = clk_get(&dev->dev, NULL);
+	host->clk = devm_clk_get(&dev->dev, NULL);
 	if (IS_ERR(host->clk)) {
 		ret = PTR_ERR(host->clk);
-		host->clk = NULL;
 		goto host_free;
 	}

 	ret = clk_prepare_enable(host->clk);
 	if (ret)
-		goto clk_free;
+		goto host_free;

 	host->plat = plat;
 	host->variant = variant;
@ -1396,6 +1481,11 @@ static int mmci_probe(struct amba_device *dev,
 		goto clk_disable;
 	}

+	if (variant->busy_detect) {
+		mmci_ops.card_busy = mmci_card_busy;
+		mmci_write_datactrlreg(host, MCI_ST_DPSM_BUSYMODE);
+	}
+
 	mmc->ops = &mmci_ops;
 	/*
 	 * The ARM and ST versions of the block have slightly different
@ -1576,8 +1666,6 @@ static int mmci_probe(struct amba_device *dev,
 	iounmap(host->base);
 clk_disable:
 	clk_disable_unprepare(host->clk);
- clk_free:
-	clk_put(host->clk);
 host_free:
 	mmc_free_host(mmc);
 rel_regions:
@ -1623,7 +1711,6 @@ static int mmci_remove(struct amba_device *dev)

 		iounmap(host->base);
 		clk_disable_unprepare(host->clk);
-		clk_put(host->clk);

 		mmc_free_host(mmc);

--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@ -94,6 +94,7 @@
 /* Extended status bits for the ST Micro variants */
 #define MCI_ST_SDIOIT		(1 << 22)
 #define MCI_ST_CEATAEND		(1 << 23)
+#define MCI_ST_CARDBUSY		(1 << 24)

 #define MMCICLEAR		0x038
 #define MCI_CMDCRCFAILCLR	(1 << 0)
@ -110,6 +111,7 @@
 /* Extended status bits for the ST Micro variants */
 #define MCI_ST_SDIOITC		(1 << 22)
 #define MCI_ST_CEATAENDC	(1 << 23)
+#define MCI_ST_BUSYENDC		(1 << 24)

 #define MMCIMASK0		0x03c
 #define MCI_CMDCRCFAILMASK	(1 << 0)
@ -183,6 +185,8 @@ struct mmci_host {
 	unsigned int		cclk;
 	u32			pwr_reg;
 	u32			clk_reg;
+	u32			datactrl_reg;
+	bool			vqmmc_enabled;
 	struct mmci_platform_data *plat;
 	struct variant_data	*variant;

--- 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