Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/pub/linux/arm/kernel/git-cur/linux-2.6-arm

* 'for-linus' of git://ftp.arm.linux.org.uk/pub/linux/arm/kernel/git-cur/linux-2.6-arm: (207 commits)
  ARM: 7267/1: Remove BUILD_BUG_ON from asm/bug.h
  ARM: 7269/1: mach-sa1100: fix sched_clock breakage
  ARM: 7198/1: arm/imx6: add restart support for imx6q
  ARM: restart: remove the now empty arch_reset()
  ARM: restart: remove comments about adding code to arch_reset()
  ARM: restart: lpc32xx & u300: remove unnecessary printk
  ARM: restart: plat-samsung: remove plat/reset.h and s5p_reset_hook
  ARM: restart: w90x900: use new restart hook
  ARM: restart: Versatile Express: use new restart hook
  ARM: restart: versatile: use new restart hook
  ARM: restart: u300: use new restart hook
  ARM: restart: tegra: use new restart hook
  ARM: restart: spear: use new restart hook
  ARM: restart: shark: use new restart hook
  ARM: restart: sa1100: use new restart hook
  ARM: 7252/1: restart: S5PV210: use new restart hook
  ARM: 7251/1: restart: S5PC100: use new restart hook
  ARM: 7250/1: restart: S5P64X0: use new restart hook
  ARM: 7266/1: restart: S3C64XX: use new restart hook
  ARM: 7265/1: restart: S3C24XX: use new restart hook
  ...

Fix up trivial conflict in arch/arm/mm/init.c due to removal of
memblock_init() clashing with the movement of the sorting of the meminfo
array.

31 files changed, 744 insertions, 327 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 29035e86a59d..b6e65dedfd71 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -187,6 +187,17 @@
 #endif
 
 /*
+ * Instruction barrier
+ */
+	.macro	instr_sync
+#if __LINUX_ARM_ARCH__ >= 7
+	isb
+#elif __LINUX_ARM_ARCH__ == 6
+	mcr	p15, 0, r0, c7, c5, 4
+#endif
+	.endm
+
+/*
  * SMP data memory barrier
  */
 	.macro	smp_dmb mode
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index 9abe7a07d5ac..fac79dceb736 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -32,7 +32,6 @@
 
 #define __BUG(__file, __line, __value)				\
 do {								\
-	BUILD_BUG_ON(sizeof(struct bug_entry) != 12);		\
 	asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n"	\
 		".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
 		"2:\t.asciz " #__file "\n" 			\
diff --git a/arch/arm/include/asm/cti.h b/arch/arm/include/asm/cti.h
new file mode 100644
index 000000000000..a0ada3ea4358
--- /dev/null
+++ b/arch/arm/include/asm/cti.h
@@ -0,0 +1,179 @@
+#ifndef __ASMARM_CTI_H
+#define __ASMARM_CTI_H
+
+#include	<asm/io.h>
+
+/* The registers' definition is from section 3.2 of
+ * Embedded Cross Trigger Revision: r0p0
+ */
+#define		CTICONTROL		0x000
+#define		CTISTATUS		0x004
+#define		CTILOCK			0x008
+#define		CTIPROTECTION		0x00C
+#define		CTIINTACK		0x010
+#define		CTIAPPSET		0x014
+#define		CTIAPPCLEAR		0x018
+#define		CTIAPPPULSE		0x01c
+#define		CTIINEN			0x020
+#define		CTIOUTEN		0x0A0
+#define		CTITRIGINSTATUS		0x130
+#define		CTITRIGOUTSTATUS	0x134
+#define		CTICHINSTATUS		0x138
+#define		CTICHOUTSTATUS		0x13c
+#define		CTIPERIPHID0		0xFE0
+#define		CTIPERIPHID1		0xFE4
+#define		CTIPERIPHID2		0xFE8
+#define		CTIPERIPHID3		0xFEC
+#define		CTIPCELLID0		0xFF0
+#define		CTIPCELLID1		0xFF4
+#define		CTIPCELLID2		0xFF8
+#define		CTIPCELLID3		0xFFC
+
+/* The below are from section 3.6.4 of
+ * CoreSight v1.0 Architecture Specification
+ */
+#define		LOCKACCESS		0xFB0
+#define		LOCKSTATUS		0xFB4
+
+/* write this value to LOCKACCESS will unlock the module, and
+ * other value will lock the module
+ */
+#define		LOCKCODE		0xC5ACCE55
+
+/**
+ * struct cti - cross trigger interface struct
+ * @base: mapped virtual address for the cti base
+ * @irq: irq number for the cti
+ * @trig_out_for_irq: triger out number which will cause
+ *	the @irq happen
+ *
+ * cti struct used to operate cti registers.
+ */
+struct cti {
+	void __iomem *base;
+	int irq;
+	int trig_out_for_irq;
+};
+
+/**
+ * cti_init - initialize the cti instance
+ * @cti: cti instance
+ * @base: mapped virtual address for the cti base
+ * @irq: irq number for the cti
+ * @trig_out: triger out number which will cause
+ *	the @irq happen
+ *
+ * called by machine code to pass the board dependent
+ * @base, @irq and @trig_out to cti.
+ */
+static inline void cti_init(struct cti *cti,
+	void __iomem *base, int irq, int trig_out)
+{
+	cti->base = base;
+	cti->irq  = irq;
+	cti->trig_out_for_irq = trig_out;
+}
+
+/**
+ * cti_map_trigger - use the @chan to map @trig_in to @trig_out
+ * @cti: cti instance
+ * @trig_in: trigger in number
+ * @trig_out: trigger out number
+ * @channel: channel number
+ *
+ * This function maps one trigger in of @trig_in to one trigger
+ * out of @trig_out using the channel @chan.
+ */
+static inline void cti_map_trigger(struct cti *cti,
+	int trig_in, int trig_out, int chan)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + CTIINEN + trig_in * 4);
+	val |= BIT(chan);
+	__raw_writel(val, base + CTIINEN + trig_in * 4);
+
+	val = __raw_readl(base + CTIOUTEN + trig_out * 4);
+	val |= BIT(chan);
+	__raw_writel(val, base + CTIOUTEN + trig_out * 4);
+}
+
+/**
+ * cti_enable - enable the cti module
+ * @cti: cti instance
+ *
+ * enable the cti module
+ */
+static inline void cti_enable(struct cti *cti)
+{
+	__raw_writel(0x1, cti->base + CTICONTROL);
+}
+
+/**
+ * cti_disable - disable the cti module
+ * @cti: cti instance
+ *
+ * enable the cti module
+ */
+static inline void cti_disable(struct cti *cti)
+{
+	__raw_writel(0, cti->base + CTICONTROL);
+}
+
+/**
+ * cti_irq_ack - clear the cti irq
+ * @cti: cti instance
+ *
+ * clear the cti irq
+ */
+static inline void cti_irq_ack(struct cti *cti)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + CTIINTACK);
+	val |= BIT(cti->trig_out_for_irq);
+	__raw_writel(val, base + CTIINTACK);
+}
+
+/**
+ * cti_unlock - unlock cti module
+ * @cti: cti instance
+ *
+ * unlock the cti module, or else any writes to the cti
+ * module is not allowed.
+ */
+static inline void cti_unlock(struct cti *cti)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + LOCKSTATUS);
+
+	if (val & 1) {
+		val = LOCKCODE;
+		__raw_writel(val, base + LOCKACCESS);
+	}
+}
+
+/**
+ * cti_lock - lock cti module
+ * @cti: cti instance
+ *
+ * lock the cti module, so any writes to the cti
+ * module will be not allowed.
+ */
+static inline void cti_lock(struct cti *cti)
+{
+	void __iomem *base = cti->base;
+	unsigned long val;
+
+	val = __raw_readl(base + LOCKSTATUS);
+
+	if (!(val & 1)) {
+		val = ~LOCKCODE;
+		__raw_writel(val, base + LOCKACCESS);
+	}
+}
+#endif
diff --git a/arch/arm/include/asm/edac.h b/arch/arm/include/asm/edac.h
new file mode 100644
index 000000000000..0df7a2c1fc3d
--- /dev/null
+++ b/arch/arm/include/asm/edac.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2011 Calxeda, Inc.
+ * Based on PPC version Copyright 2007 MontaVista Software, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef ASM_EDAC_H
+#define ASM_EDAC_H
+/*
+ * ECC atomic, DMA, SMP and interrupt safe scrub function.
+ * Implements the per arch atomic_scrub() that EDAC use for software
+ * ECC scrubbing.  It reads memory and then writes back the original
+ * value, allowing the hardware to detect and correct memory errors.
+ */
+static inline void atomic_scrub(void *va, u32 size)
+{
+#if __LINUX_ARM_ARCH__ >= 6
+	unsigned int *virt_addr = va;
+	unsigned int temp, temp2;
+	unsigned int i;
+
+	for (i = 0; i < size / sizeof(*virt_addr); i++, virt_addr++) {
+		/* Very carefully read and write to memory atomically
+		 * so we are interrupt, DMA and SMP safe.
+		 */
+		__asm__ __volatile__("\n"
+			"1:	ldrex	%0, [%2]\n"
+			"	strex	%1, %0, [%2]\n"
+			"	teq	%1, #0\n"
+			"	bne	1b\n"
+			: "=&r"(temp), "=&r"(temp2)
+			: "r"(virt_addr)
+			: "cc");
+	}
+#endif
+}
+
+#endif
diff --git a/arch/arm/include/asm/entry-macro-vic2.S b/arch/arm/include/asm/entry-macro-vic2.S
deleted file mode 100644
index 3ceb85e43850..000000000000
--- a/arch/arm/include/asm/entry-macro-vic2.S
+++ /dev/null
@@ -1,57 +0,0 @@
-/* arch/arm/include/asm/entry-macro-vic2.S
- *
- * Originally arch/arm/mach-s3c6400/include/mach/entry-macro.S
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * Low-level IRQ helper macros for a device with two VICs
- *
- * This file is licensed under  the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
-*/
-
-/* This should be included from <mach/entry-macro.S> with the necessary
- * defines for virtual addresses and IRQ bases for the two vics.
- *
- * The code needs the following defined:
- *	IRQ_VIC0_BASE	IRQ number of VIC0's first IRQ
- *	IRQ_VIC1_BASE	IRQ number of VIC1's first IRQ
- *	VA_VIC0		Virtual address of VIC0
- *	VA_VIC1		Virtual address of VIC1
- *
- * Note, code assumes VIC0's virtual address is an ARM immediate constant
- * away from VIC1.
-*/
-
-#include <asm/hardware/vic.h>
-
-	.macro	disable_fiq
-	.endm
-
-	.macro	get_irqnr_preamble, base, tmp
-	ldr	\base, =VA_VIC0
-	.endm
-
-	.macro	arch_ret_to_user, tmp1, tmp2
-	.endm
-
-	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-	@ check the vic0
-	mov	\irqnr, #IRQ_VIC0_BASE + 31
-	ldr	\irqstat, [ \base, # VIC_IRQ_STATUS ]
-	teq	\irqstat, #0
-
-	@ otherwise try vic1
-	addeq	\tmp, \base, #(VA_VIC1 - VA_VIC0)
-	addeq	\irqnr, \irqnr, #(IRQ_VIC1_BASE - IRQ_VIC0_BASE)
-	ldreq	\irqstat, [ \tmp, # VIC_IRQ_STATUS ]
-	teqeq	\irqstat, #0
-
-	clzne	\irqstat, \irqstat
-	subne	\irqnr, \irqnr, \irqstat
-	.endm
diff --git a/arch/arm/include/asm/gpio.h b/arch/arm/include/asm/gpio.h
index 11ad0bfbb0ad..7151753b0989 100644
--- a/arch/arm/include/asm/gpio.h
+++ b/arch/arm/include/asm/gpio.h
@@ -1,6 +1,10 @@
 #ifndef _ARCH_ARM_GPIO_H
 #define _ARCH_ARM_GPIO_H
 
+#if CONFIG_ARCH_NR_GPIO > 0
+#define ARCH_NR_GPIO CONFIG_ARCH_NR_GPIO
+#endif
+
 /* not all ARM platforms necessarily support this API ... */
 #include <mach/gpio.h>
 
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index ddf07a92a6c8..436e60b2cf7a 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -27,23 +27,6 @@ u64 smp_irq_stat_cpu(unsigned int cpu);
 
 #define arch_irq_stat_cpu	smp_irq_stat_cpu
 
-#if NR_IRQS > 512
-#define HARDIRQ_BITS	10
-#elif NR_IRQS > 256
-#define HARDIRQ_BITS	9
-#else
-#define HARDIRQ_BITS	8
-#endif
-
-/*
- * The hardirq mask has to be large enough to have space
- * for potentially all IRQ sources in the system nesting
- * on a single CPU:
- */
-#if (1 << HARDIRQ_BITS) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
 #endif /* __ASM_HARDIRQ_H */
diff --git a/arch/arm/include/asm/hardware/entry-macro-gic.S b/arch/arm/include/asm/hardware/entry-macro-gic.S
deleted file mode 100644
index 74ebc803904d..000000000000
--- a/arch/arm/include/asm/hardware/entry-macro-gic.S
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * arch/arm/include/asm/hardware/entry-macro-gic.S
- *
- * Low-level IRQ helper macros for GIC
- *
- * This file is licensed under  the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <asm/hardware/gic.h>
-
-#ifndef HAVE_GET_IRQNR_PREAMBLE
-	.macro	get_irqnr_preamble, base, tmp
-	ldr	\base, =gic_cpu_base_addr
-	ldr	\base, [\base]
-	.endm
-#endif
-
-/*
- * The interrupt numbering scheme is defined in the
- * interrupt controller spec.  To wit:
- *
- * Interrupts 0-15 are IPI
- * 16-31 are local.  We allow 30 to be used for the watchdog.
- * 32-1020 are global
- * 1021-1022 are reserved
- * 1023 is "spurious" (no interrupt)
- *
- * A simple read from the controller will tell us the number of the highest
- * priority enabled interrupt.  We then just need to check whether it is in the
- * valid range for an IRQ (30-1020 inclusive).
- */
-
-	.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-
-	ldr     \irqstat, [\base, #GIC_CPU_INTACK]
-	/* bits 12-10 = src CPU, 9-0 = int # */
-
-	ldr	\tmp, =1021
-	bic     \irqnr, \irqstat, #0x1c00
-	cmp     \irqnr, #15
-	cmpcc	\irqnr, \irqnr
-	cmpne	\irqnr, \tmp
-	cmpcs	\irqnr, \irqnr
-	.endm
-
-/* We assume that irqstat (the raw value of the IRQ acknowledge
- * register) is preserved from the macro above.
- * If there is an IPI, we immediately signal end of interrupt on the
- * controller, since this requires the original irqstat value which
- * we won't easily be able to recreate later.
- */
-
-	.macro test_for_ipi, irqnr, irqstat, base, tmp
-	bic	\irqnr, \irqstat, #0x1c00
-	cmp	\irqnr, #16
-	strcc	\irqstat, [\base, #GIC_CPU_EOI]
-	cmpcs	\irqnr, \irqnr
-	.endm
diff --git a/arch/arm/include/asm/hardware/gic.h b/arch/arm/include/asm/hardware/gic.h
index 3e91f22046f5..4bdfe0018696 100644
--- a/arch/arm/include/asm/hardware/gic.h
+++ b/arch/arm/include/asm/hardware/gic.h
@@ -36,30 +36,22 @@
 #include <linux/irqdomain.h>
 struct device_node;
 
-extern void __iomem *gic_cpu_base_addr;
 extern struct irq_chip gic_arch_extn;
 
-void gic_init(unsigned int, int, void __iomem *, void __iomem *);
+void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *,
+		    u32 offset);
 int gic_of_init(struct device_node *node, struct device_node *parent);
 void gic_secondary_init(unsigned int);
+void gic_handle_irq(struct pt_regs *regs);
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq);
 
-struct gic_chip_data {
-	void __iomem *dist_base;
-	void __iomem *cpu_base;
-#ifdef CONFIG_CPU_PM
-	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
-	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
-	u32 saved_spi_target[DIV_ROUND_UP(1020, 4)];
-	u32 __percpu *saved_ppi_enable;
-	u32 __percpu *saved_ppi_conf;
-#endif
-#ifdef CONFIG_IRQ_DOMAIN
-	struct irq_domain domain;
-#endif
-	unsigned int gic_irqs;
-};
+static inline void gic_init(unsigned int nr, int start,
+			    void __iomem *dist , void __iomem *cpu)
+{
+	gic_init_bases(nr, start, dist, cpu, 0);
+}
+
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h
index 5daea2961d48..077c32326c63 100644
--- a/arch/arm/include/asm/hardware/iop3xx.h
+++ b/arch/arm/include/asm/hardware/iop3xx.h
@@ -234,6 +234,7 @@ extern int iop3xx_get_init_atu(void);
 void iop3xx_map_io(void);
 void iop_init_cp6_handler(void);
 void iop_init_time(unsigned long tickrate);
+void iop3xx_restart(char, const char *);
 
 static inline u32 read_tmr0(void)
 {
diff --git a/arch/arm/include/asm/hardware/vic.h b/arch/arm/include/asm/hardware/vic.h
index 5d72550a8097..f42ebd619590 100644
--- a/arch/arm/include/asm/hardware/vic.h
+++ b/arch/arm/include/asm/hardware/vic.h
@@ -41,7 +41,15 @@
 #define VIC_PL192_VECT_ADDR		0xF00
 
 #ifndef __ASSEMBLY__
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+struct device_node;
+struct pt_regs;
+
 void vic_init(void __iomem *base, unsigned int irq_start, u32 vic_sources, u32 resume_sources);
-#endif
+int vic_of_init(struct device_node *node, struct device_node *parent);
+void vic_handle_irq(struct pt_regs *regs);
 
+#endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/arm/include/asm/idmap.h b/arch/arm/include/asm/idmap.h
new file mode 100644
index 000000000000..bf863edb517d
--- /dev/null
+++ b/arch/arm/include/asm/idmap.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_IDMAP_H
+#define __ASM_IDMAP_H
+
+#include <linux/compiler.h>
+#include <asm/pgtable.h>
+
+/* Tag a function as requiring to be executed via an identity mapping. */
+#define __idmap __section(.idmap.text) noinline notrace
+
+extern pgd_t *idmap_pgd;
+
+void setup_mm_for_reboot(void);
+
+#endif	/* __ASM_IDMAP_H */
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 2b0efc3104ac..bcb0c883e21e 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -31,10 +31,10 @@ struct machine_desc {
 	unsigned int		video_start;	/* start of video RAM	*/
 	unsigned int		video_end;	/* end of video RAM	*/
 
-	unsigned int		reserve_lp0 :1;	/* never has lp0	*/
-	unsigned int		reserve_lp1 :1;	/* never has lp1	*/
-	unsigned int		reserve_lp2 :1;	/* never has lp2	*/
-	unsigned int		soft_reboot :1;	/* soft reboot		*/
+	unsigned char		reserve_lp0 :1;	/* never has lp0	*/
+	unsigned char		reserve_lp1 :1;	/* never has lp1	*/
+	unsigned char		reserve_lp2 :1;	/* never has lp2	*/
+	char			restart_mode;	/* default restart mode	*/
 	void			(*fixup)(struct tag *, char **,
 					 struct meminfo *);
 	void			(*reserve)(void);/* reserve mem blocks	*/
@@ -46,6 +46,7 @@ struct machine_desc {
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	void			(*handle_irq)(struct pt_regs *);
 #endif
+	void			(*restart)(char, const char *);
 };
 
 /*
diff --git a/arch/arm/include/asm/opcodes.h b/arch/arm/include/asm/opcodes.h
new file mode 100644
index 000000000000..c0efdd60966f
--- /dev/null
+++ b/arch/arm/include/asm/opcodes.h
@@ -0,0 +1,20 @@
+/*
+ *  arch/arm/include/asm/opcodes.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.
+ */
+
+#ifndef __ASM_ARM_OPCODES_H
+#define __ASM_ARM_OPCODES_H
+
+#ifndef __ASSEMBLY__
+extern asmlinkage unsigned int arm_check_condition(u32 opcode, u32 psr);
+#endif
+
+#define ARM_OPCODE_CONDTEST_FAIL   0
+#define ARM_OPCODE_CONDTEST_PASS   1
+#define ARM_OPCODE_CONDTEST_UNCOND 2
+
+#endif /* __ASM_ARM_OPCODES_H */
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index ca94653f1ecb..97b440c25c58 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -151,7 +151,11 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-types.h>
+#else
 #include <asm/pgtable-2level-types.h>
+#endif
 
 #endif /* CONFIG_MMU */
 
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index 0f8e3827a89b..99cfe3607989 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -32,7 +32,4 @@ enum arm_perf_pmu_ids {
 extern enum arm_perf_pmu_ids
 armpmu_get_pmu_id(void);
 
-extern int
-armpmu_get_max_events(void);
-
 #endif /* __ARM_PERF_EVENT_H__ */
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 3e08fd3fbb6b..943504f53f57 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -25,12 +25,34 @@
 #define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_USER))
 #define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
 
+#ifdef CONFIG_ARM_LPAE
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	free_page((unsigned long)pmd);
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE));
+}
+
+#else	/* !CONFIG_ARM_LPAE */
+
 /*
  * Since we have only two-level page tables, these are trivial
  */
 #define pmd_alloc_one(mm,addr)		({ BUG(); ((pmd_t *)2); })
 #define pmd_free(mm, pmd)		do { } while (0)
-#define pgd_populate(mm,pmd,pte)	BUG()
+#define pud_populate(mm,pmd,pte)	BUG()
+
+#endif	/* CONFIG_ARM_LPAE */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
@@ -109,7 +131,9 @@ static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
 {
 	pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot;
 	pmdp[0] = __pmd(pmdval);
+#ifndef CONFIG_ARM_LPAE
 	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
+#endif
 	flush_pmd_entry(pmdp);
 }
 
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index 470457e1cfc5..2317a71c8f8e 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -140,4 +140,45 @@
 #define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
 #define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
 
+#ifndef __ASSEMBLY__
+
+/*
+ * The "pud_xxx()" functions here are trivial when the pmd is folded into
+ * the pud: the pud entry is never bad, always exists, and can't be set or
+ * cleared.
+ */
+#define pud_none(pud)		(0)
+#define pud_bad(pud)		(0)
+#define pud_present(pud)	(1)
+#define pud_clear(pudp)		do { } while (0)
+#define set_pud(pud,pudp)	do { } while (0)
+
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+	return (pmd_t *)pud;
+}
+
+#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
+
+#define copy_pmd(pmdpd,pmdps)		\
+	do {				\
+		pmdpd[0] = pmdps[0];	\
+		pmdpd[1] = pmdps[1];	\
+		flush_pmd_entry(pmdpd);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		pmdp[0] = __pmd(0);	\
+		pmdp[1] = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+/* we don't need complex calculations here as the pmd is folded into the pgd */
+#define pmd_addr_end(addr,end) (end)
+
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* _ASM_PGTABLE_2LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
new file mode 100644
index 000000000000..d7952824c5c4
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -0,0 +1,77 @@
+/*
+ * arch/arm/include/asm/pgtable-3level-hwdef.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_HWDEF_H
+#define _ASM_PGTABLE_3LEVEL_HWDEF_H
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1/2 descriptor
+ *   - common
+ */
+#define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
+#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_BIT4		(_AT(pmdval_t, 0))
+#define PMD_DOMAIN(x)		(_AT(pmdval_t, 0))
+
+/*
+ *   - section
+ */
+#define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#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)
+#define PMD_SECT_XN		(_AT(pmdval_t, 1) << 54)
+#define PMD_SECT_AP_WRITE	(_AT(pmdval_t, 0))
+#define PMD_SECT_AP_READ	(_AT(pmdval_t, 0))
+#define PMD_SECT_TEX(x)		(_AT(pmdval_t, 0))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PMD_SECT_UNCACHED	(_AT(pmdval_t, 0) << 2)	/* strongly ordered */
+#define PMD_SECT_BUFFERED	(_AT(pmdval_t, 1) << 2)	/* normal non-cacheable */
+#define PMD_SECT_WT		(_AT(pmdval_t, 2) << 2)	/* normal inner write-through */
+#define PMD_SECT_WB		(_AT(pmdval_t, 3) << 2)	/* normal inner write-back */
+#define PMD_SECT_WBWA		(_AT(pmdval_t, 7) << 2)	/* normal inner write-alloc */
+
+/*
+ * + Level 3 descriptor (PTE)
+ */
+#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_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 */
+#define PTE_EXT_AF		(_AT(pteval_t, 1) << 10)	/* Access Flag */
+#define PTE_EXT_NG		(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_EXT_XN		(_AT(pteval_t, 1) << 54)	/* XN */
+
+/*
+ * 40-bit physical address supported.
+ */
+#define PHYS_MASK_SHIFT		(40)
+#define PHYS_MASK		((1ULL << PHYS_MASK_SHIFT) - 1)
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-3level-types.h b/arch/arm/include/asm/pgtable-3level-types.h
new file mode 100644
index 000000000000..921aa30259c4
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level-types.h
@@ -0,0 +1,70 @@
+/*
+ * arch/arm/include/asm/pgtable-3level-types.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_TYPES_H
+#define _ASM_PGTABLE_3LEVEL_TYPES_H
+
+#include <asm/types.h>
+
+typedef u64 pteval_t;
+typedef u64 pmdval_t;
+typedef u64 pgdval_t;
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+typedef struct { pmdval_t pmd; } pmd_t;
+typedef struct { pgdval_t pgd; } pgd_t;
+typedef struct { pteval_t pgprot; } pgprot_t;
+
+#define pte_val(x)      ((x).pte)
+#define pmd_val(x)      ((x).pmd)
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)   ((x).pgprot)
+
+#define __pte(x)        ((pte_t) { (x) } )
+#define __pmd(x)        ((pmd_t) { (x) } )
+#define __pgd(x)	((pgd_t) { (x) } )
+#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+#else	/* !STRICT_MM_TYPECHECKS */
+
+typedef pteval_t pte_t;
+typedef pmdval_t pmd_t;
+typedef pgdval_t pgd_t;
+typedef pteval_t pgprot_t;
+
+#define pte_val(x)	(x)
+#define pmd_val(x)	(x)
+#define pgd_val(x)	(x)
+#define pgprot_val(x)	(x)
+
+#define __pte(x)	(x)
+#define __pmd(x)	(x)
+#define __pgd(x)	(x)
+#define __pgprot(x)	(x)
+
+#endif	/* STRICT_MM_TYPECHECKS */
+
+#endif	/* _ASM_PGTABLE_3LEVEL_TYPES_H */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
new file mode 100644
index 000000000000..759af70f9a0a
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -0,0 +1,155 @@
+/*
+ * arch/arm/include/asm/pgtable-3level.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_H
+#define _ASM_PGTABLE_3LEVEL_H
+
+/*
+ * With LPAE, there are 3 levels of page tables. Each level has 512 entries of
+ * 8 bytes each, occupying a 4K page. The first level table covers a range of
+ * 512GB, each entry representing 1GB. Since we are limited to 4GB input
+ * address range, only 4 entries in the PGD are used.
+ *
+ * There are enough spare bits in a page table entry for the kernel specific
+ * state.
+ */
+#define PTRS_PER_PTE		512
+#define PTRS_PER_PMD		512
+#define PTRS_PER_PGD		4
+
+#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
+#define PTE_HWTABLE_OFF		(0)
+#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u64))
+
+/*
+ * PGDIR_SHIFT determines the size a top-level page table entry can map.
+ */
+#define PGDIR_SHIFT		30
+
+/*
+ * PMD_SHIFT determines the size a middle-level page table entry can map.
+ */
+#define PMD_SHIFT		21
+
+#define PMD_SIZE		(1UL << PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE-1))
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+
+/*
+ * section address mask and size definitions.
+ */
+#define SECTION_SHIFT		21
+#define SECTION_SIZE		(1UL << SECTION_SHIFT)
+#define SECTION_MASK		(~(SECTION_SIZE-1))
+
+#define USER_PTRS_PER_PGD	(PAGE_OFFSET / PGDIR_SIZE)
+
+/*
+ * "Linux" PTE definitions for LPAE.
+ *
+ * These bits overlap with the hardware bits but the naming is preserved for
+ * consistency with the classic page table format.
+ */
+#define L_PTE_PRESENT		(_AT(pteval_t, 3) << 0)		/* Valid */
+#define L_PTE_FILE		(_AT(pteval_t, 1) << 2)		/* only when !PRESENT */
+#define L_PTE_BUFFERABLE	(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
+#define L_PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
+#define L_PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
+#define L_PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
+#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 10)	/* AF */
+#define L_PTE_XN		(_AT(pteval_t, 1) << 54)	/* XN */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)	/* unused */
+#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)	/* unused */
+
+/*
+ * To be used in assembly code with the upper page attributes.
+ */
+#define L_PTE_XN_HIGH		(1 << (54 - 32))
+#define L_PTE_DIRTY_HIGH	(1 << (55 - 32))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0) << 2)	/* strongly ordered */
+#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 1) << 2)	/* normal non-cacheable */
+#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 2) << 2)	/* normal inner write-through */
+#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 3) << 2)	/* normal inner write-back */
+#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 7) << 2)	/* normal inner write-alloc */
+#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 4) << 2)	/* device */
+#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 4) << 2)	/* device */
+#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 1) << 2)	/* normal non-cacheable */
+#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 3) << 2)	/* normal inner write-back */
+#define L_PTE_MT_MASK		(_AT(pteval_t, 7) << 2)
+
+/*
+ * Software PGD flags.
+ */
+#define L_PGD_SWAPPER		(_AT(pgdval_t, 1) << 55)	/* swapper_pg_dir entry */
+
+#ifndef __ASSEMBLY__
+
+#define pud_none(pud)		(!pud_val(pud))
+#define pud_bad(pud)		(!(pud_val(pud) & 2))
+#define pud_present(pud)	(pud_val(pud))
+
+#define pud_clear(pudp)			\
+	do {				\
+		*pudp = __pud(0);	\
+		clean_pmd_entry(pudp);	\
+	} while (0)
+
+#define set_pud(pudp, pud)		\
+	do {				\
+		*pudp = pud;		\
+		flush_pmd_entry(pudp);	\
+	} while (0)
+
+static inline pmd_t *pud_page_vaddr(pud_t pud)
+{
+	return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
+}
+
+/* Find an entry in the second-level page table.. */
+#define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+
+#define pmd_bad(pmd)		(!(pmd_val(pmd) & 2))
+
+#define copy_pmd(pmdpd,pmdps)		\
+	do {				\
+		*pmdpd = *pmdps;	\
+		flush_pmd_entry(pmdpd);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		*pmdp = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PGTABLE_3LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable-hwdef.h b/arch/arm/include/asm/pgtable-hwdef.h
index 183111164ce9..8426229ba292 100644
--- a/arch/arm/include/asm/pgtable-hwdef.h
+++ b/arch/arm/include/asm/pgtable-hwdef.h
@@ -10,6 +10,10 @@
 #ifndef _ASMARM_PGTABLE_HWDEF_H
 #define _ASMARM_PGTABLE_HWDEF_H
 
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-hwdef.h>
+#else
 #include <asm/pgtable-2level-hwdef.h>
+#endif
 
 #endif
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 9451dce3a553..f66626d71e7d 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -11,20 +11,24 @@
 #define _ASMARM_PGTABLE_H
 
 #include <linux/const.h>
-#include <asm-generic/4level-fixup.h>
 #include <asm/proc-fns.h>
 
 #ifndef CONFIG_MMU
 
+#include <asm-generic/4level-fixup.h>
 #include "pgtable-nommu.h"
 
 #else
 
+#include <asm-generic/pgtable-nopud.h>
 #include <asm/memory.h>
-#include <mach/vmalloc.h>
 #include <asm/pgtable-hwdef.h>
 
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level.h>
+#else
 #include <asm/pgtable-2level.h>
+#endif
 
 /*
  * Just any arbitrary offset to the start of the vmalloc VM area: the
@@ -33,15 +37,10 @@
  * any out-of-bounds memory accesses will hopefully be caught.
  * The vmalloc() routines leaves a hole of 4kB between each vmalloced
  * area for the same reason. ;)
- *
- * Note that platforms may override VMALLOC_START, but they must provide
- * VMALLOC_END.  VMALLOC_END defines the (exclusive) limit of this space,
- * which may not overlap IO space.
  */
-#ifndef VMALLOC_START
 #define VMALLOC_OFFSET		(8*1024*1024)
 #define VMALLOC_START		(((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
-#endif
+#define VMALLOC_END		0xff000000UL
 
 #define LIBRARY_TEXT_START	0x0c000000
 
@@ -163,39 +162,8 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
 
-/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
- * setup: the pgd is never bad, and a pmd always exists (as it's folded
- * into the pgd entry)
- */
-#define pgd_none(pgd)		(0)
-#define pgd_bad(pgd)		(0)
-#define pgd_present(pgd)	(1)
-#define pgd_clear(pgdp)		do { } while (0)
-#define set_pgd(pgd,pgdp)	do { } while (0)
-#define set_pud(pud,pudp)	do { } while (0)
-
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(dir, addr)	((pmd_t *)(dir))
-
 #define pmd_none(pmd)		(!pmd_val(pmd))
 #define pmd_present(pmd)	(pmd_val(pmd))
-#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
-
-#define copy_pmd(pmdpd,pmdps)		\
-	do {				\
-		pmdpd[0] = pmdps[0];	\
-		pmdpd[1] = pmdps[1];	\
-		flush_pmd_entry(pmdpd);	\
-	} while (0)
-
-#define pmd_clear(pmdp)			\
-	do {				\
-		pmdp[0] = __pmd(0);	\
-		pmdp[1] = __pmd(0);	\
-		clean_pmd_entry(pmdp);	\
-	} while (0)
 
 static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 {
@@ -204,10 +172,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
-/* we don't need complex calculations here as the pmd is folded into the pgd */
-#define pmd_addr_end(addr,end)	(end)
-
-
 #ifndef CONFIG_HIGHPTE
 #define __pte_map(pmd)		pmd_page_vaddr(*(pmd))
 #define __pte_unmap(pte)	do { } while (0)
@@ -229,7 +193,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))
 #define mk_pte(page,prot)	pfn_pte(page_to_pfn(page), prot)
 
-#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
 #if __LINUX_ARM_ARCH__ < 6
@@ -336,6 +299,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
  * We provide our own arch_get_unmapped_area to cope with VIPT caches.
  */
 #define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
 /*
  * remap a physical page `pfn' of size `size' with page protection `prot'
@@ -346,9 +310,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 #define pgtable_cache_init() do { } while (0)
 
-void identity_mapping_add(pgd_t *, unsigned long, unsigned long);
-void identity_mapping_del(pgd_t *, unsigned long, unsigned long);
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* CONFIG_MMU */
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 0bda22c094a6..b5a5be2536c1 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -27,13 +27,22 @@ enum arm_pmu_type {
 /*
  * struct arm_pmu_platdata - ARM PMU platform data
  *
- * @handle_irq: an optional handler which will be called from the interrupt and
- * passed the address of the low level handler, and can be used to implement
- * any platform specific handling before or after calling it.
+ * @handle_irq: an optional handler which will be called from the
+ *	interrupt and passed the address of the low level handler,
+ *	and can be used to implement any platform specific handling
+ *	before or after calling it.
+ * @enable_irq: an optional handler which will be called after
+ *	request_irq and be used to handle some platform specific
+ *	irq enablement
+ * @disable_irq: an optional handler which will be called before
+ *	free_irq and be used to handle some platform specific
+ *	irq disablement
  */
 struct arm_pmu_platdata {
 	irqreturn_t (*handle_irq)(int irq, void *dev,
 				  irq_handler_t pmu_handler);
+	void (*enable_irq)(int irq);
+	void (*disable_irq)(int irq);
 };
 
 #ifdef CONFIG_CPU_HAS_PMU
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index 9e92cb205e65..f3628fb3d2b3 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -65,7 +65,11 @@ extern struct processor {
 	 * Set a possibly extended PTE.  Non-extended PTEs should
 	 * ignore 'ext'.
 	 */
+#ifdef CONFIG_ARM_LPAE
+	void (*set_pte_ext)(pte_t *ptep, pte_t pte);
+#else
 	void (*set_pte_ext)(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
 
 	/* Suspend/resume */
 	unsigned int suspend_size;
@@ -79,7 +83,11 @@ 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);
+#ifdef CONFIG_ARM_LPAE
+extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
+#else
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
 
 /* These three are private to arch/arm/kernel/suspend.c */
@@ -107,6 +115,18 @@ 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_pgd()	\
+	({						\
+		unsigned long pg, pg2;			\
+		__asm__("mrrc	p15, 0, %0, %1, c2"	\
+			: "=r" (pg), "=r" (pg2)		\
+			:				\
+			: "cc");			\
+		pg &= ~(PTRS_PER_PGD*sizeof(pgd_t)-1);	\
+		(pgd_t *)phys_to_virt(pg);		\
+	})
+#else
 #define cpu_get_pgd()	\
 	({						\
 		unsigned long pg;			\
@@ -115,6 +135,7 @@ extern void cpu_resume(void);
 		pg &= ~0x3fff;				\
 		(pgd_t *)phys_to_virt(pg);		\
 	})
+#endif
 
 #endif
 
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index b2d9df5667af..ce280b8d613c 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -123,6 +123,8 @@ static inline void prefetch(const void *ptr)
 
 #endif
 
+#define HAVE_ARCH_PICK_MMAP_LAYOUT
+
 #endif
 
 #endif /* __ASM_ARM_PROCESSOR_H */
diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
index c8e6ddf3e860..e3f757263438 100644
--- a/arch/arm/include/asm/sched_clock.h
+++ b/arch/arm/include/asm/sched_clock.h
@@ -8,113 +8,7 @@
 #ifndef ASM_SCHED_CLOCK
 #define ASM_SCHED_CLOCK
 
-#include <linux/kernel.h>
-#include <linux/types.h>
-
-struct clock_data {
-	u64 epoch_ns;
-	u32 epoch_cyc;
-	u32 epoch_cyc_copy;
-	u32 mult;
-	u32 shift;
-};
-
-#define DEFINE_CLOCK_DATA(name)	struct clock_data name
-
-static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
-{
-	return (cyc * mult) >> shift;
-}
-
-/*
- * Atomically update the sched_clock epoch.  Your update callback will
- * be called from a timer before the counter wraps - read the current
- * counter value, and call this function to safely move the epochs
- * forward.  Only use this from the update callback.
- */
-static inline void update_sched_clock(struct clock_data *cd, u32 cyc, u32 mask)
-{
-	unsigned long flags;
-	u64 ns = cd->epoch_ns +
-		cyc_to_ns((cyc - cd->epoch_cyc) & mask, cd->mult, cd->shift);
-
-	/*
-	 * Write epoch_cyc and epoch_ns in a way that the update is
-	 * detectable in cyc_to_fixed_sched_clock().
-	 */
-	raw_local_irq_save(flags);
-	cd->epoch_cyc = cyc;
-	smp_wmb();
-	cd->epoch_ns = ns;
-	smp_wmb();
-	cd->epoch_cyc_copy = cyc;
-	raw_local_irq_restore(flags);
-}
-
-/*
- * If your clock rate is known at compile time, using this will allow
- * you to optimize the mult/shift loads away.  This is paired with
- * init_fixed_sched_clock() to ensure that your mult/shift are correct.
- */
-static inline unsigned long long cyc_to_fixed_sched_clock(struct clock_data *cd,
-	u32 cyc, u32 mask, u32 mult, u32 shift)
-{
-	u64 epoch_ns;
-	u32 epoch_cyc;
-
-	/*
-	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
-	 * ensuring that we always write epoch_cyc, epoch_ns and
-	 * epoch_cyc_copy in strict order, and read them in strict order.
-	 * If epoch_cyc and epoch_cyc_copy are not equal, then we're in
-	 * the middle of an update, and we should repeat the load.
-	 */
-	do {
-		epoch_cyc = cd->epoch_cyc;
-		smp_rmb();
-		epoch_ns = cd->epoch_ns;
-		smp_rmb();
-	} while (epoch_cyc != cd->epoch_cyc_copy);
-
-	return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, mult, shift);
-}
-
-/*
- * Otherwise, you need to use this, which will obtain the mult/shift
- * from the clock_data structure.  Use init_sched_clock() with this.
- */
-static inline unsigned long long cyc_to_sched_clock(struct clock_data *cd,
-	u32 cyc, u32 mask)
-{
-	return cyc_to_fixed_sched_clock(cd, cyc, mask, cd->mult, cd->shift);
-}
-
-/*
- * Initialize the clock data - calculate the appropriate multiplier
- * and shift.  Also setup a timer to ensure that the epoch is refreshed
- * at the appropriate time interval, which will call your update
- * handler.
- */
-void init_sched_clock(struct clock_data *, void (*)(void),
-	unsigned int, unsigned long);
-
-/*
- * Use this initialization function rather than init_sched_clock() if
- * you're using cyc_to_fixed_sched_clock, which will warn if your
- * constants are incorrect.
- */
-static inline void init_fixed_sched_clock(struct clock_data *cd,
-	void (*update)(void), unsigned int bits, unsigned long rate,
-	u32 mult, u32 shift)
-{
-	init_sched_clock(cd, update, bits, rate);
-	if (cd->mult != mult || cd->shift != shift) {
-		pr_crit("sched_clock: wrong multiply/shift: %u>>%u vs calculated %u>>%u\n"
-			"sched_clock: fix multiply/shift to avoid scheduler hiccups\n",
-			mult, shift, cd->mult, cd->shift);
-	}
-}
-
 extern void sched_clock_postinit(void);
+extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
 
 #endif
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 915696dd9c7c..23ebc0c82a39 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -192,11 +192,7 @@ static const struct tagtable __tagtable_##fn __tag = { tag, fn }
 /*
  * Memory map description
  */
-#ifdef CONFIG_ARCH_EP93XX
-# define NR_BANKS 16
-#else
-# define NR_BANKS 8
-#endif
+#define NR_BANKS	CONFIG_ARM_NR_BANKS
 
 struct membank {
 	phys_addr_t start;
diff --git a/arch/arm/include/asm/swab.h b/arch/arm/include/asm/swab.h
index 9997ad20eff1..32ee164a2f6b 100644
--- a/arch/arm/include/asm/swab.h
+++ b/arch/arm/include/asm/swab.h
@@ -24,12 +24,13 @@
 
 #if defined(__KERNEL__) && __LINUX_ARM_ARCH__ >= 6
 
-static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
+static inline __attribute_const__ __u32 __arch_swahb32(__u32 x)
 {
 	__asm__ ("rev16 %0, %1" : "=r" (x) : "r" (x));
 	return x;
 }
-#define __arch_swab16 __arch_swab16
+#define __arch_swahb32 __arch_swahb32
+#define __arch_swab16(x) ((__u16)__arch_swahb32(x))
 
 static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 984014b92647..e4c96cc6ec0c 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -80,6 +80,14 @@ struct siginfo;
 void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
 		unsigned long err, unsigned long trap);
 
+#ifdef CONFIG_ARM_LPAE
+#define FAULT_CODE_ALIGNMENT	33
+#define FAULT_CODE_DEBUG	34
+#else
+#define FAULT_CODE_ALIGNMENT	1
+#define FAULT_CODE_DEBUG	2
+#endif
+
 void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 				       struct pt_regs *),
 		     int sig, int code, const char *name);
@@ -100,7 +108,7 @@ extern void __show_regs(struct pt_regs *);
 extern int __pure cpu_architecture(void);
 extern void cpu_init(void);
 
-void arm_machine_restart(char mode, const char *cmd);
+void soft_restart(unsigned long);
 extern void (*arm_pm_restart)(char str, const char *cmd);
 
 #define UDBG_UNDEFINED	(1 << 0)
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 265f908c4a6e..5d3ed7e38561 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -202,8 +202,18 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	tlb_remove_page(tlb, pte);
 }
 
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
+				  unsigned long addr)
+{
+#ifdef CONFIG_ARM_LPAE
+	tlb_add_flush(tlb, addr);
+	tlb_remove_page(tlb, virt_to_page(pmdp));
+#endif
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
+#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)
 
 #define tlb_migrate_finish(mm)		do { } while (0)