Merge remote branch 'rmk/for-linus' into for-linus

* rmk/for-linus: (1557 commits)
  ARM: 6806/1: irq: introduce entry and exit functions for chained handlers
  ARM: 6781/1: Thumb-2: Work around buggy Thumb-2 short branch relocations in gas
  ARM: 6747/1: P2V: Thumb2 support
  ARM: 6798/1: aout-core: zero thread debug registers in a.out core dump
  ARM: 6796/1: Footbridge: Fix I/O mappings for NOMMU mode
  ARM: 6784/1: errata: no automatic Store Buffer drain on Cortex-A9
  ARM: 6772/1: errata: possible fault MMU translations following an ASID switch
  ARM: 6776/1: mach-ux500: activate fix for errata 753970
  ARM: 6794/1: SPEAr: Append UL to device address macros.
  ARM: 6793/1: SPEAr: Remove unused *_SIZE macros from spear*.h files
  ARM: 6792/1: SPEAr: Replace SIZE macro's with SZ_4K macros
  ARM: 6791/1: SPEAr3xx: Declare device structures after shirq code
  ARM: 6790/1: SPEAr: Clock Framework: Rename usbd clock and align apb_clk entry
  ARM: 6789/1: SPEAr3xx: Rename sdio to sdhci
  ARM: 6788/1: SPEAr: Include mach/hardware.h instead of mach/spear.h
  ARM: 6787/1: SPEAr: Reorder #includes in .h & .c files.
  ARM: 6681/1: SPEAr: add debugfs support to clk API
  ARM: 6703/1: SPEAr: update clk API support
  ARM: 6679/1: SPEAr: make clk API functions more generic
  ARM: 6737/1: SPEAr: formalized timer support
  ...

Conflicts:
	arch/arm/mach-msm/board-msm7x27.c
	arch/arm/mach-msm/board-msm7x30.c
	arch/arm/mach-msm/board-qsd8x50.c
	arch/arm/mach-msm/board-sapphire.c
	arch/arm/mach-msm/include/mach/memory.h

32 files changed, 483 insertions, 92 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 9d30c6f804b..89266382b53 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -390,7 +390,7 @@ config CPU_PJ4
 
 # ARMv6
 config CPU_V6
-	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX || ARCH_DOVE
+	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
 	select CPU_32v6
 	select CPU_ABRT_EV6
 	select CPU_PABRT_V6
@@ -402,21 +402,23 @@ config CPU_V6
 	select CPU_TLB_V6 if MMU
 
 # ARMv6k
-config CPU_32v6K
-	bool "Support ARM V6K processor extensions" if !SMP
-	depends on CPU_V6 || CPU_V7
-	default y if SMP && !(ARCH_MX3 || ARCH_OMAP2)
-	help
-	  Say Y here if your ARMv6 processor supports the 'K' extension.
-	  This enables the kernel to use some instructions not present
-	  on previous processors, and as such a kernel build with this
-	  enabled will not boot on processors with do not support these
-	  instructions.
+config CPU_V6K
+	bool "Support ARM V6K processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
+	select CPU_32v6
+	select CPU_32v6K
+	select CPU_ABRT_EV6
+	select CPU_PABRT_V6
+	select CPU_CACHE_V6
+	select CPU_CACHE_VIPT
+	select CPU_CP15_MMU
+	select CPU_HAS_ASID if MMU
+	select CPU_COPY_V6 if MMU
+	select CPU_TLB_V6 if MMU
 
 # ARMv7
 config CPU_V7
 	bool "Support ARM V7 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
-	select CPU_32v6K if !ARCH_OMAP2
+	select CPU_32v6K
 	select CPU_32v7
 	select CPU_ABRT_EV7
 	select CPU_PABRT_V7
@@ -433,25 +435,33 @@ config CPU_32v3
 	bool
 	select TLS_REG_EMUL if SMP || !MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select CPU_USE_DOMAINS if MMU
 
 config CPU_32v4
 	bool
 	select TLS_REG_EMUL if SMP || !MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select CPU_USE_DOMAINS if MMU
 
 config CPU_32v4T
 	bool
 	select TLS_REG_EMUL if SMP || !MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select CPU_USE_DOMAINS if MMU
 
 config CPU_32v5
 	bool
 	select TLS_REG_EMUL if SMP || !MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select CPU_USE_DOMAINS if MMU
 
 config CPU_32v6
 	bool
 	select TLS_REG_EMUL if !CPU_32v6K && !MMU
+	select CPU_USE_DOMAINS if CPU_V6 && MMU
+
+config CPU_32v6K
+	bool
 
 config CPU_32v7
 	bool
@@ -607,8 +617,6 @@ config CPU_CP15_MPU
 
 config CPU_USE_DOMAINS
 	bool
-	depends on MMU
-	default y if !CPU_32v6K
 	help
 	  This option enables or disables the use of domain switching
 	  via the set_fs() function.
@@ -623,7 +631,7 @@ comment "Processor Features"
 
 config ARM_THUMB
 	bool "Support Thumb user binaries"
-	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V7 || CPU_FEROCEON
+	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
 	default y
 	help
 	  Say Y if you want to include kernel support for running user space
@@ -644,7 +652,7 @@ config ARM_THUMBEE
 
 config SWP_EMULATE
 	bool "Emulate SWP/SWPB instructions"
-	depends on CPU_V7 && !CPU_V6
+	depends on !CPU_USE_DOMAINS && CPU_V7
 	select HAVE_PROC_CPU if PROC_FS
 	default y if SMP
 	help
@@ -681,7 +689,7 @@ config CPU_BIG_ENDIAN
 config CPU_ENDIAN_BE8
 	bool
 	depends on CPU_BIG_ENDIAN
-	default CPU_V6 || CPU_V7
+	default CPU_V6 || CPU_V6K || CPU_V7
 	help
 	  Support for the BE-8 (big-endian) mode on ARMv6 and ARMv7 processors.
 
@@ -747,7 +755,7 @@ config CPU_CACHE_ROUND_ROBIN
 
 config CPU_BPREDICT_DISABLE
 	bool "Disable branch prediction"
-	depends on CPU_ARM1020 || CPU_V6 || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526
+	depends on CPU_ARM1020 || CPU_V6 || CPU_V6K || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526
 	help
 	  Say Y here to disable branch prediction.  If unsure, say N.
 
@@ -767,7 +775,7 @@ config NEEDS_SYSCALL_FOR_CMPXCHG
 
 config DMA_CACHE_RWFO
 	bool "Enable read/write for ownership DMA cache maintenance"
-	depends on CPU_V6 && SMP
+	depends on CPU_V6K && SMP
 	default y
 	help
 	  The Snoop Control Unit on ARM11MPCore does not detect the
@@ -823,7 +831,7 @@ config CACHE_L2X0
 config CACHE_PL310
 	bool
 	depends on CACHE_L2X0
-	default y if CPU_V7 && !CPU_V6
+	default y if CPU_V7 && !(CPU_V6 || CPU_V6K)
 	help
 	  This option enables optimisations for the PL310 cache
 	  controller.
@@ -845,16 +853,21 @@ config CACHE_XSC3L2
 	help
 	  This option enables the L2 cache on XScale3.
 
+config ARM_L1_CACHE_SHIFT_6
+	bool
+	help
+	  Setting ARM L1 cache line size to 64 Bytes.
+
 config ARM_L1_CACHE_SHIFT
 	int
 	default 6 if ARM_L1_CACHE_SHIFT_6
 	default 5
 
 config ARM_DMA_MEM_BUFFERABLE
-	bool "Use non-cacheable memory for DMA" if CPU_V6 && !CPU_V7
+	bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K) && !CPU_V7
 	depends on !(MACH_REALVIEW_PB1176 || REALVIEW_EB_ARM11MP || \
 		     MACH_REALVIEW_PB11MP)
-	default y if CPU_V6 || CPU_V7
+	default y if CPU_V6 || CPU_V6K || CPU_V7
 	help
 	  Historically, the kernel has used strongly ordered mappings to
 	  provide DMA coherent memory.  With the advent of ARMv7, mapping
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 00d74a04af3..bca7e61928c 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -90,6 +90,7 @@ obj-$(CONFIG_CPU_XSC3)		+= proc-xsc3.o
 obj-$(CONFIG_CPU_MOHAWK)	+= proc-mohawk.o
 obj-$(CONFIG_CPU_FEROCEON)	+= proc-feroceon.o
 obj-$(CONFIG_CPU_V6)		+= proc-v6.o
+obj-$(CONFIG_CPU_V6K)		+= proc-v6.o
 obj-$(CONFIG_CPU_V7)		+= proc-v7.o
 
 AFLAGS_proc-v6.o	:=-Wa,-march=armv6
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index f332df7f0d3..1478aa52214 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -20,11 +20,11 @@
  */
 	.align	5
 ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_32v6K
-	clrex
-#else
+#ifdef CONFIG_CPU_V6
 	sub	r1, sp, #4			@ Get unused stack location
 	strex	r0, r1, [r1]			@ Clear the exclusive monitor
+#elif defined(CONFIG_CPU_32v6K)
+	clrex
 #endif
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 170c9bb9586..ef59099a546 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -49,7 +49,13 @@ static inline void cache_wait(void __iomem *reg, unsigned long mask)
 static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
+
+#ifdef CONFIG_ARM_ERRATA_753970
+	/* write to an unmmapped register */
+	writel_relaxed(0, base + L2X0_DUMMY_REG);
+#else
 	writel_relaxed(0, base + L2X0_CACHE_SYNC);
+#endif
 	cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
 
@@ -67,18 +73,24 @@ static inline void l2x0_inv_line(unsigned long addr)
 	writel_relaxed(addr, base + L2X0_INV_LINE_PA);
 }
 
-#ifdef CONFIG_PL310_ERRATA_588369
-static void debug_writel(unsigned long val)
-{
-	extern void omap_smc1(u32 fn, u32 arg);
+#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915)
 
-	/*
-	 * Texas Instrument secure monitor api to modify the
-	 * PL310 Debug Control Register.
-	 */
-	omap_smc1(0x100, val);
+#define debug_writel(val)	outer_cache.set_debug(val)
+
+static void l2x0_set_debug(unsigned long val)
+{
+	writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL);
+}
+#else
+/* Optimised out for non-errata case */
+static inline void debug_writel(unsigned long val)
+{
 }
 
+#define l2x0_set_debug	NULL
+#endif
+
+#ifdef CONFIG_PL310_ERRATA_588369
 static inline void l2x0_flush_line(unsigned long addr)
 {
 	void __iomem *base = l2x0_base;
@@ -91,11 +103,6 @@ static inline void l2x0_flush_line(unsigned long addr)
 }
 #else
 
-/* Optimised out for non-errata case */
-static inline void debug_writel(unsigned long val)
-{
-}
-
 static inline void l2x0_flush_line(unsigned long addr)
 {
 	void __iomem *base = l2x0_base;
@@ -119,9 +126,11 @@ static void l2x0_flush_all(void)
 
 	/* clean all ways */
 	spin_lock_irqsave(&l2x0_lock, flags);
+	debug_writel(0x03);
 	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY);
 	cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask);
 	cache_sync();
+	debug_writel(0x00);
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
@@ -329,6 +338,7 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	outer_cache.flush_all = l2x0_flush_all;
 	outer_cache.inv_all = l2x0_inv_all;
 	outer_cache.disable = l2x0_disable;
+	outer_cache.set_debug = l2x0_set_debug;
 
 	printk(KERN_INFO "%s cache controller enabled\n", type);
 	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 5164069ced4..cddd684364d 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -297,6 +297,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 	memblock_reserve(__pa(_stext), _end - _stext);
 #endif
 #ifdef CONFIG_BLK_DEV_INITRD
+	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);
+		phys_initrd_start = phys_initrd_size = 0;
+	}
 	if (phys_initrd_size) {
 		memblock_reserve(phys_initrd_start, phys_initrd_size);
 
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index b0a98305055..afe209e1e1f 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -31,7 +31,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long start_addr;
-#ifdef CONFIG_CPU_V6
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 	unsigned int cache_type;
 	int do_align = 0, aliasing = 0;
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 3c67e92f7d5..ff7b43b5885 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -827,16 +827,6 @@ static void __init sanity_check_meminfo(void)
 			 * rather difficult.
 			 */
 			reason = "with VIPT aliasing cache";
-		} else if (is_smp() && tlb_ops_need_broadcast()) {
-			/*
-			 * kmap_high needs to occasionally flush TLB entries,
-			 * however, if the TLB entries need to be broadcast
-			 * we may deadlock:
-			 *  kmap_high(irqs off)->flush_all_zero_pkmaps->
-			 *  flush_tlb_kernel_range->smp_call_function_many
-			 *   (must not be called with irqs off)
-			 */
-			reason = "without hardware TLB ops broadcasting";
 		}
 		if (reason) {
 			printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n",
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index bcf748d9f4e..226e3d8351c 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -493,6 +493,9 @@ arm1020_processor_functions:
 	.word	cpu_arm1020_dcache_clean_area
 	.word	cpu_arm1020_switch_mm
 	.word	cpu_arm1020_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	arm1020_processor_functions, . - arm1020_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index ab7ec26657e..86d9c2cf0bc 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -474,6 +474,9 @@ arm1020e_processor_functions:
 	.word	cpu_arm1020e_dcache_clean_area
 	.word	cpu_arm1020e_switch_mm
 	.word	cpu_arm1020e_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	arm1020e_processor_functions, . - arm1020e_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 831c5e54e22..83d3dd34f84 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -457,6 +457,9 @@ arm1022_processor_functions:
 	.word	cpu_arm1022_dcache_clean_area
 	.word	cpu_arm1022_switch_mm
 	.word	cpu_arm1022_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	arm1022_processor_functions, . - arm1022_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index e3f7e9a166b..686043ee728 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -452,6 +452,9 @@ arm1026_processor_functions:
 	.word	cpu_arm1026_dcache_clean_area
 	.word	cpu_arm1026_switch_mm
 	.word	cpu_arm1026_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	arm1026_processor_functions, . - arm1026_processor_functions
 
 	.section .rodata
diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S
index 6a7be1863ed..5f79dc4ce3f 100644
--- a/arch/arm/mm/proc-arm6_7.S
+++ b/arch/arm/mm/proc-arm6_7.S
@@ -284,6 +284,9 @@ ENTRY(arm6_processor_functions)
 		.word	cpu_arm6_dcache_clean_area
 		.word	cpu_arm6_switch_mm
 		.word	cpu_arm6_set_pte_ext
+		.word	0
+		.word	0
+		.word	0
 		.size	arm6_processor_functions, . - arm6_processor_functions
 
 /*
@@ -301,6 +304,9 @@ ENTRY(arm7_processor_functions)
 		.word	cpu_arm7_dcache_clean_area
 		.word	cpu_arm7_switch_mm
 		.word	cpu_arm7_set_pte_ext
+		.word	0
+		.word	0
+		.word	0
 		.size	arm7_processor_functions, . - arm7_processor_functions
 
 		.section ".rodata"
diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S
index c285395f44b..665266da143 100644
--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -185,6 +185,9 @@ ENTRY(arm720_processor_functions)
 		.word	cpu_arm720_dcache_clean_area
 		.word	cpu_arm720_switch_mm
 		.word	cpu_arm720_set_pte_ext
+		.word	0
+		.word	0
+		.word	0
 		.size	arm720_processor_functions, . - arm720_processor_functions
 
 		.section ".rodata"
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index 38b27dcba72..6f9d12effee 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -130,6 +130,9 @@ ENTRY(arm740_processor_functions)
 	.word	cpu_arm740_dcache_clean_area
 	.word	cpu_arm740_switch_mm
 	.word	0			@ cpu_*_set_pte
+	.word	0
+	.word	0
+	.word	0
 	.size	arm740_processor_functions, . - arm740_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S
index 0c9786de20a..e4c165ca669 100644
--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -70,6 +70,9 @@ ENTRY(arm7tdmi_processor_functions)
 		.word	cpu_arm7tdmi_dcache_clean_area
 		.word	cpu_arm7tdmi_switch_mm
 		.word	0		@ cpu_*_set_pte
+		.word	0
+		.word	0
+		.word	0
 		.size	arm7tdmi_processor_functions, . - arm7tdmi_processor_functions
 
 		.section ".rodata"
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 6109f278a90..219980ec8b6 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -387,6 +387,40 @@ ENTRY(cpu_arm920_set_pte_ext)
 #endif
 	mov	pc, lr
 
+/* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
+.globl	cpu_arm920_suspend_size
+.equ	cpu_arm920_suspend_size, 4 * 3
+#ifdef CONFIG_PM
+ENTRY(cpu_arm920_do_suspend)
+	stmfd	sp!, {r4 - r7, lr}
+	mrc	p15, 0, r4, c13, c0, 0	@ PID
+	mrc	p15, 0, r5, c3, c0, 0	@ Domain ID
+	mrc	p15, 0, r6, c2, c0, 0	@ TTB address
+	mrc	p15, 0, r7, c1, c0, 0	@ Control register
+	stmia	r0, {r4 - r7}
+	ldmfd	sp!, {r4 - r7, pc}
+ENDPROC(cpu_arm920_do_suspend)
+
+ENTRY(cpu_arm920_do_resume)
+	mov	ip, #0
+	mcr	p15, 0, ip, c8, c7, 0	@ invalidate I+D TLBs
+	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I+D caches
+	ldmia	r0, {r4 - r7}
+	mcr	p15, 0, r4, c13, c0, 0	@ PID
+	mcr	p15, 0, r5, c3, c0, 0	@ Domain ID
+	mcr	p15, 0, r6, c2, c0, 0	@ TTB address
+	mov	r0, r7			@ control register
+	mov	r2, r6, lsr #14		@ get TTB0 base
+	mov	r2, r2, lsl #14
+	ldr	r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
+		     PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE
+	b	cpu_resume_mmu
+ENDPROC(cpu_arm920_do_resume)
+#else
+#define cpu_arm920_do_suspend	0
+#define cpu_arm920_do_resume	0
+#endif
+
 	__CPUINIT
 
 	.type	__arm920_setup, #function
@@ -432,6 +466,9 @@ arm920_processor_functions:
 	.word	cpu_arm920_dcache_clean_area
 	.word	cpu_arm920_switch_mm
 	.word	cpu_arm920_set_pte_ext
+	.word	cpu_arm920_suspend_size
+	.word	cpu_arm920_do_suspend
+	.word	cpu_arm920_do_resume
 	.size	arm920_processor_functions, . - arm920_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index bb2f0f46a5e..36154b1e792 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -436,6 +436,9 @@ arm922_processor_functions:
 	.word	cpu_arm922_dcache_clean_area
 	.word	cpu_arm922_switch_mm
 	.word	cpu_arm922_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	arm922_processor_functions, . - arm922_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index c13e01accfe..89c5e0009c4 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -503,6 +503,9 @@ arm925_processor_functions:
 	.word	cpu_arm925_dcache_clean_area
 	.word	cpu_arm925_switch_mm
 	.word	cpu_arm925_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	arm925_processor_functions, . - arm925_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 42eb4315740..6a4bdb2c94a 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -401,6 +401,40 @@ ENTRY(cpu_arm926_set_pte_ext)
 #endif
 	mov	pc, lr
 
+/* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
+.globl	cpu_arm926_suspend_size
+.equ	cpu_arm926_suspend_size, 4 * 3
+#ifdef CONFIG_PM
+ENTRY(cpu_arm926_do_suspend)
+	stmfd	sp!, {r4 - r7, lr}
+	mrc	p15, 0, r4, c13, c0, 0	@ PID
+	mrc	p15, 0, r5, c3, c0, 0	@ Domain ID
+	mrc	p15, 0, r6, c2, c0, 0	@ TTB address
+	mrc	p15, 0, r7, c1, c0, 0	@ Control register
+	stmia	r0, {r4 - r7}
+	ldmfd	sp!, {r4 - r7, pc}
+ENDPROC(cpu_arm926_do_suspend)
+
+ENTRY(cpu_arm926_do_resume)
+	mov	ip, #0
+	mcr	p15, 0, ip, c8, c7, 0	@ invalidate I+D TLBs
+	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I+D caches
+	ldmia	r0, {r4 - r7}
+	mcr	p15, 0, r4, c13, c0, 0	@ PID
+	mcr	p15, 0, r5, c3, c0, 0	@ Domain ID
+	mcr	p15, 0, r6, c2, c0, 0	@ TTB address
+	mov	r0, r7			@ control register
+	mov	r2, r6, lsr #14		@ get TTB0 base
+	mov	r2, r2, lsl #14
+	ldr	r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
+		     PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE
+	b	cpu_resume_mmu
+ENDPROC(cpu_arm926_do_resume)
+#else
+#define cpu_arm926_do_suspend	0
+#define cpu_arm926_do_resume	0
+#endif
+
 	__CPUINIT
 
 	.type	__arm926_setup, #function
@@ -456,6 +490,9 @@ arm926_processor_functions:
 	.word	cpu_arm926_dcache_clean_area
 	.word	cpu_arm926_switch_mm
 	.word	cpu_arm926_set_pte_ext
+	.word	cpu_arm926_suspend_size
+	.word	cpu_arm926_do_suspend
+	.word	cpu_arm926_do_resume
 	.size	arm926_processor_functions, . - arm926_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index 7b11cdb9935..26aea3f71c2 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -363,6 +363,9 @@ ENTRY(arm940_processor_functions)
 	.word	cpu_arm940_dcache_clean_area
 	.word	cpu_arm940_switch_mm
 	.word	0		@ cpu_*_set_pte
+	.word	0
+	.word	0
+	.word	0
 	.size	arm940_processor_functions, . - arm940_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index 1a5bbf08034..8063345406f 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -419,6 +419,9 @@ ENTRY(arm946_processor_functions)
 	.word	cpu_arm946_dcache_clean_area
 	.word	cpu_arm946_switch_mm
 	.word	0		@ cpu_*_set_pte
+	.word	0
+	.word	0
+	.word	0
 	.size	arm946_processor_functions, . - arm946_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S
index db67e3134d7..7b7ebd4d096 100644
--- a/arch/arm/mm/proc-arm9tdmi.S
+++ b/arch/arm/mm/proc-arm9tdmi.S
@@ -70,6 +70,9 @@ ENTRY(arm9tdmi_processor_functions)
 		.word	cpu_arm9tdmi_dcache_clean_area
 		.word	cpu_arm9tdmi_switch_mm
 		.word	0		@ cpu_*_set_pte
+		.word	0
+		.word	0
+		.word	0
 		.size	arm9tdmi_processor_functions, . - arm9tdmi_processor_functions
 
 		.section ".rodata"
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index 7c9ad621f0e..fc2a4ae15cf 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -195,6 +195,9 @@ fa526_processor_functions:
 	.word	cpu_fa526_dcache_clean_area
 	.word	cpu_fa526_switch_mm
 	.word	cpu_fa526_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	fa526_processor_functions, . - fa526_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index b4597edbff9..d3883eed7a4 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -554,6 +554,9 @@ feroceon_processor_functions:
 	.word	cpu_feroceon_dcache_clean_area
 	.word	cpu_feroceon_switch_mm
 	.word	cpu_feroceon_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	feroceon_processor_functions, . - feroceon_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 4458ee6aa71..9d4f2ae6337 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -388,6 +388,9 @@ mohawk_processor_functions:
 	.word	cpu_mohawk_dcache_clean_area
 	.word	cpu_mohawk_switch_mm
 	.word	cpu_mohawk_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	mohawk_processor_functions, . - mohawk_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S
index 5aa8d59c2e8..46f09ed16b9 100644
--- a/arch/arm/mm/proc-sa110.S
+++ b/arch/arm/mm/proc-sa110.S
@@ -203,6 +203,9 @@ ENTRY(sa110_processor_functions)
 	.word	cpu_sa110_dcache_clean_area
 	.word	cpu_sa110_switch_mm
 	.word	cpu_sa110_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	sa110_processor_functions, . - sa110_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 2ac4e6f1071..74483d1977f 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -169,6 +169,42 @@ ENTRY(cpu_sa1100_set_pte_ext)
 #endif
 	mov	pc, lr
 
+.globl	cpu_sa1100_suspend_size
+.equ	cpu_sa1100_suspend_size, 4*4
+#ifdef CONFIG_PM
+ENTRY(cpu_sa1100_do_suspend)
+	stmfd	sp!, {r4 - r7, lr}
+	mrc	p15, 0, r4, c3, c0, 0		@ domain ID
+	mrc	p15, 0, r5, c2, c0, 0		@ translation table base addr
+	mrc	p15, 0, r6, c13, c0, 0		@ PID
+	mrc	p15, 0, r7, c1, c0, 0		@ control reg
+	stmia	r0, {r4 - r7}			@ store cp regs
+	ldmfd	sp!, {r4 - r7, pc}
+ENDPROC(cpu_sa1100_do_suspend)
+
+ENTRY(cpu_sa1100_do_resume)
+	ldmia	r0, {r4 - r7}			@ load cp regs
+	mov	r1, #0
+	mcr	p15, 0, r1, c8, c7, 0		@ flush I+D TLBs
+	mcr	p15, 0, r1, c7, c7, 0		@ flush I&D cache
+	mcr	p15, 0, r1, c9, c0, 0		@ invalidate RB
+	mcr	p15, 0, r1, c9, c0, 5		@ allow user space to use RB
+
+	mcr	p15, 0, r4, c3, c0, 0		@ domain ID
+	mcr	p15, 0, r5, c2, c0, 0		@ translation table base addr
+	mcr	p15, 0, r6, c13, c0, 0		@ PID
+	mov	r0, r7				@ control register
+	mov	r2, r5, lsr #14			@ get TTB0 base
+	mov	r2, r2, lsl #14
+	ldr	r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
+		     PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE
+	b	cpu_resume_mmu
+ENDPROC(cpu_sa1100_do_resume)
+#else
+#define cpu_sa1100_do_suspend	0
+#define cpu_sa1100_do_resume	0
+#endif
+
 	__CPUINIT
 
 	.type	__sa1100_setup, #function
@@ -218,6 +254,9 @@ ENTRY(sa1100_processor_functions)
 	.word	cpu_sa1100_dcache_clean_area
 	.word	cpu_sa1100_switch_mm
 	.word	cpu_sa1100_set_pte_ext
+	.word	cpu_sa1100_suspend_size
+	.word	cpu_sa1100_do_suspend
+	.word	cpu_sa1100_do_resume
 	.size	sa1100_processor_functions, . - sa1100_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 59a7e1ffe7b..832b6bdc192 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -121,6 +121,53 @@ ENTRY(cpu_v6_set_pte_ext)
 #endif
 	mov	pc, lr
 
+/* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
+.globl	cpu_v6_suspend_size
+.equ	cpu_v6_suspend_size, 4 * 8
+#ifdef CONFIG_PM
+ENTRY(cpu_v6_do_suspend)
+	stmfd	sp!, {r4 - r11, lr}
+	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
+	mrc	p15, 0, r5, c13, c0, 1	@ Context ID
+	mrc	p15, 0, r6, c3, c0, 0	@ Domain ID
+	mrc	p15, 0, r7, c2, c0, 0	@ Translation table base 0
+	mrc	p15, 0, r8, c2, c0, 1	@ Translation table base 1
+	mrc	p15, 0, r9, c1, c0, 1	@ auxillary control register
+	mrc	p15, 0, r10, c1, c0, 2	@ co-processor access control
+	mrc	p15, 0, r11, c1, c0, 0	@ control register
+	stmia	r0, {r4 - r11}
+	ldmfd	sp!, {r4- r11, pc}
+ENDPROC(cpu_v6_do_suspend)
+
+ENTRY(cpu_v6_do_resume)
+	mov	ip, #0
+	mcr	p15, 0, ip, c7, c14, 0	@ clean+invalidate D cache
+	mcr	p15, 0, ip, c7, c5, 0	@ invalidate I cache
+	mcr	p15, 0, ip, c7, c15, 0	@ clean+invalidate cache
+	mcr	p15, 0, ip, c7, c10, 4	@ drain write buffer
+	ldmia	r0, {r4 - r11}
+	mcr	p15, 0, r4, c13, c0, 0	@ FCSE/PID
+	mcr	p15, 0, r5, c13, c0, 1	@ Context ID
+	mcr	p15, 0, r6, c3, c0, 0	@ Domain ID
+	mcr	p15, 0, r7, c2, c0, 0	@ Translation table base 0
+	mcr	p15, 0, r8, c2, c0, 1	@ Translation table base 1
+	mcr	p15, 0, r9, c1, c0, 1	@ auxillary control register
+	mcr	p15, 0, r10, 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, r11			@ control register
+	mov	r2, r7, lsr #14		@ get TTB0 base
+	mov	r2, r2, lsl #14
+	ldr	r3, cpu_resume_l1_flags
+	b	cpu_resume_mmu
+ENDPROC(cpu_v6_do_resume)
+cpu_resume_l1_flags:
+	ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP)
+	ALT_UP(.long  PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP)
+#else
+#define cpu_v6_do_suspend 0
+#define cpu_v6_do_resume 0
+#endif
 
 
 	.type	cpu_v6_name, #object
@@ -206,6 +253,9 @@ ENTRY(v6_processor_functions)
 	.word	cpu_v6_dcache_clean_area
 	.word	cpu_v6_switch_mm
 	.word	cpu_v6_set_pte_ext
+	.word	cpu_v6_suspend_size
+	.word	cpu_v6_do_suspend
+	.word	cpu_v6_do_resume
 	.size	v6_processor_functions, . - v6_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 0c1172b56b4..262fa88a743 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -108,10 +108,16 @@ ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_ARM_ERRATA_430973
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 #endif
+#ifdef CONFIG_ARM_ERRATA_754322
+	dsb
+#endif
 	mcr	p15, 0, r2, c13, c0, 1		@ set reserved context ID
 	isb
 1:	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
 	isb
+#ifdef CONFIG_ARM_ERRATA_754322
+	dsb
+#endif
 	mcr	p15, 0, r1, c13, c0, 1		@ set context ID
 	isb
 #endif
@@ -171,6 +177,87 @@ cpu_v7_name:
 	.ascii	"ARMv7 Processor"
 	.align
 
+	/*
+	 * Memory region attributes with SCTLR.TRE=1
+	 *
+	 *   n = TEX[0],C,B
+	 *   TR = PRRR[2n+1:2n]		- memory type
+	 *   IR = NMRR[2n+1:2n]		- inner cacheable property
+	 *   OR = NMRR[2n+17:2n+16]	- outer cacheable property
+	 *
+	 *			n	TR	IR	OR
+	 *   UNCACHED		000	00
+	 *   BUFFERABLE		001	10	00	00
+	 *   WRITETHROUGH	010	10	10	10
+	 *   WRITEBACK		011	10	11	11
+	 *   reserved		110
+	 *   WRITEALLOC		111	10	01	01
+	 *   DEV_SHARED		100	01
+	 *   DEV_NONSHARED	100	01
+	 *   DEV_WC		001	10
+	 *   DEV_CACHED		011	10
+	 *
+	 * Other attributes:
+	 *
+	 *   DS0 = PRRR[16] = 0		- device shareable property
+	 *   DS1 = PRRR[17] = 1		- device shareable property
+	 *   NS0 = PRRR[18] = 0		- normal shareable property
+	 *   NS1 = PRRR[19] = 1		- normal shareable property
+	 *   NOS = PRRR[24+n] = 1	- not outer shareable
+	 */
+.equ	PRRR,	0xff0a81a8
+.equ	NMRR,	0x40e040e0
+
+/* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
+.globl	cpu_v7_suspend_size
+.equ	cpu_v7_suspend_size, 4 * 8
+#ifdef CONFIG_PM
+ENTRY(cpu_v7_do_suspend)
+	stmfd	sp!, {r4 - r11, lr}
+	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
+	mrc	p15, 0, r5, c13, c0, 1	@ Context ID
+	mrc	p15, 0, r6, c3, c0, 0	@ Domain ID
+	mrc	p15, 0, r7, c2, c0, 0	@ TTB 0
+	mrc	p15, 0, r8, c2, c0, 1	@ TTB 1
+	mrc	p15, 0, r9, c1, c0, 0	@ Control register
+	mrc	p15, 0, r10, c1, c0, 1	@ Auxiliary control register
+	mrc	p15, 0, r11, c1, c0, 2	@ Co-processor access control
+	stmia	r0, {r4 - r11}
+	ldmfd	sp!, {r4 - r11, pc}
+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
+	ldmia	r0, {r4 - r11}
+	mcr	p15, 0, r4, c13, c0, 0	@ FCSE/PID
+	mcr	p15, 0, r5, c13, c0, 1	@ Context ID
+	mcr	p15, 0, r6, c3, c0, 0	@ Domain ID
+	mcr	p15, 0, r7, c2, c0, 0	@ TTB 0
+	mcr	p15, 0, r8, c2, c0, 1	@ TTB 1
+	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
+	mcr	p15, 0, r10, c1, c0, 1	@ Auxillary control register
+	mcr	p15, 0, r11, 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
+	isb
+	mov	r0, r9			@ control register
+	mov	r2, r7, lsr #14		@ get TTB0 base
+	mov	r2, r2, lsl #14
+	ldr	r3, cpu_resume_l1_flags
+	b	cpu_resume_mmu
+ENDPROC(cpu_v7_do_resume)
+cpu_resume_l1_flags:
+	ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP)
+	ALT_UP(.long  PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP)
+#else
+#define cpu_v7_do_suspend	0
+#define cpu_v7_do_resume	0
+#endif
+
 	__CPUINIT
 
 /*
@@ -264,6 +351,12 @@ __v7_setup:
 	orreq	r10, r10, #1 << 6		@ set bit #6
 	mcreq	p15, 0, r10, c15, c0, 1		@ write diagnostic register
 #endif
+#ifdef CONFIG_ARM_ERRATA_751472
+	cmp	r6, #0x30			@ present prior to r3p0
+	mrclt	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orrlt	r10, r10, #1 << 11		@ set bit #11
+	mcrlt	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
 
 3:	mov	r10, #0
 #ifdef HARVARD_CACHE
@@ -276,36 +369,8 @@ __v7_setup:
 	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
-	/*
-	 * Memory region attributes with SCTLR.TRE=1
-	 *
-	 *   n = TEX[0],C,B
-	 *   TR = PRRR[2n+1:2n]		- memory type
-	 *   IR = NMRR[2n+1:2n]		- inner cacheable property
-	 *   OR = NMRR[2n+17:2n+16]	- outer cacheable property
-	 *
-	 *			n	TR	IR	OR
-	 *   UNCACHED		000	00
-	 *   BUFFERABLE		001	10	00	00
-	 *   WRITETHROUGH	010	10	10	10
-	 *   WRITEBACK		011	10	11	11
-	 *   reserved		110
-	 *   WRITEALLOC		111	10	01	01
-	 *   DEV_SHARED		100	01
-	 *   DEV_NONSHARED	100	01
-	 *   DEV_WC		001	10
-	 *   DEV_CACHED		011	10
-	 *
-	 * Other attributes:
-	 *
-	 *   DS0 = PRRR[16] = 0		- device shareable property
-	 *   DS1 = PRRR[17] = 1		- device shareable property
-	 *   NS0 = PRRR[18] = 0		- normal shareable property
-	 *   NS1 = PRRR[19] = 1		- normal shareable property
-	 *   NOS = PRRR[24+n] = 1	- not outer shareable
-	 */
-	ldr	r5, =0xff0a81a8			@ PRRR
-	ldr	r6, =0x40e040e0			@ NMRR
+	ldr	r5, =PRRR			@ PRRR
+	ldr	r6, =NMRR			@ NMRR
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
 	mcr	p15, 0, r6, c10, c2, 1		@ write NMRR
 #endif
@@ -351,6 +416,9 @@ ENTRY(v7_processor_functions)
 	.word	cpu_v7_dcache_clean_area
 	.word	cpu_v7_switch_mm
 	.word	cpu_v7_set_pte_ext
+	.word	0
+	.word	0
+	.word	0
 	.size	v7_processor_functions, . - v7_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index ec26355cb7c..63d8b2044e8 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -413,9 +413,52 @@ ENTRY(cpu_xsc3_set_pte_ext)
 	mov	pc, lr
 
 	.ltorg
-
 	.align
 
+.globl	cpu_xsc3_suspend_size
+.equ	cpu_xsc3_suspend_size, 4 * 8
+#ifdef CONFIG_PM
+ENTRY(cpu_xsc3_do_suspend)
+	stmfd	sp!, {r4 - r10, lr}
+	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
+	mrc	p15, 0, r5, c15, c1, 0	@ CP access reg
+	mrc	p15, 0, r6, c13, c0, 0	@ PID
+	mrc 	p15, 0, r7, c3, c0, 0	@ domain ID
+	mrc 	p15, 0, r8, c2, c0, 0	@ translation table base addr
+	mrc	p15, 0, r9, c1, c0, 1	@ auxiliary control reg
+	mrc 	p15, 0, r10, c1, c0, 0	@ control reg
+	bic	r4, r4, #2		@ clear frequency change bit
+	stmia	r0, {r1, r4 - r10}	@ store v:p offset + cp regs
+	ldmia	sp!, {r4 - r10, pc}
+ENDPROC(cpu_xsc3_do_suspend)
+
+ENTRY(cpu_xsc3_do_resume)
+	ldmia	r0, {r1, r4 - r10}	@ load v:p offset + cp regs
+	mov	ip, #0
+	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I & D caches, BTB
+	mcr	p15, 0, ip, c7, c10, 4	@ drain write (&fill) buffer
+	mcr	p15, 0, ip, c7, c5, 4	@ flush prefetch buffer
+	mcr	p15, 0, ip, c8, c7, 0	@ invalidate I & D TLBs
+	mcr	p14, 0, r4, c6, c0, 0	@ clock configuration, turbo mode.
+	mcr	p15, 0, r5, c15, c1, 0	@ CP access reg
+	mcr	p15, 0, r6, c13, c0, 0	@ PID
+	mcr	p15, 0, r7, c3, c0, 0	@ domain ID
+	mcr	p15, 0, r8, c2, c0, 0	@ translation table base addr
+	mcr	p15, 0, r9, c1, c0, 1	@ auxiliary control reg
+
+	@ temporarily map resume_turn_on_mmu into the page table,
+	@ otherwise prefetch abort occurs after MMU is turned on
+	mov	r0, r10			@ control register
+	mov	r2, r8, lsr #14		@ get TTB0 base
+	mov	r2, r2, lsl #14
+	ldr	r3, =0x542e		@ section flags
+	b	cpu_resume_mmu
+ENDPROC(cpu_xsc3_do_resume)
+#else
+#define cpu_xsc3_do_suspend	0
+#define cpu_xsc3_do_resume	0
+#endif
+
 	__CPUINIT
 
 	.type	__xsc3_setup, #function
@@ -476,6 +519,9 @@ ENTRY(xsc3_processor_functions)
 	.word	cpu_xsc3_dcache_clean_area
 	.word	cpu_xsc3_switch_mm
 	.word	cpu_xsc3_set_pte_ext
+	.word	cpu_xsc3_suspend_size
+	.word	cpu_xsc3_do_suspend
+	.word	cpu_xsc3_do_resume
 	.size	xsc3_processor_functions, . - xsc3_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 5a37c5e45c4..086038cd86a 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -513,11 +513,49 @@ ENTRY(cpu_xscale_set_pte_ext)
 	xscale_set_pte_ext_epilogue
 	mov	pc, lr
 
-
 	.ltorg
-
 	.align
 
+.globl	cpu_xscale_suspend_size
+.equ	cpu_xscale_suspend_size, 4 * 7
+#ifdef CONFIG_PM
+ENTRY(cpu_xscale_do_suspend)
+	stmfd	sp!, {r4 - r10, lr}
+	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
+	mrc	p15, 0, r5, c15, c1, 0	@ CP access reg
+	mrc	p15, 0, r6, c13, c0, 0	@ PID
+	mrc	p15, 0, r7, c3, c0, 0	@ domain ID
+	mrc	p15, 0, r8, c2, c0, 0	@ translation table base addr
+	mrc	p15, 0, r9, c1, c1, 0	@ auxiliary control reg
+	mrc	p15, 0, r10, c1, c0, 0	@ control reg
+	bic	r4, r4, #2		@ clear frequency change bit
+	stmia	r0, {r4 - r10}		@ store cp regs
+	ldmfd	sp!, {r4 - r10, pc}
+ENDPROC(cpu_xscale_do_suspend)
+
+ENTRY(cpu_xscale_do_resume)
+	ldmia	r0, {r4 - r10}		@ load cp regs
+	mov	ip, #0
+	mcr	p15, 0, ip, c8, c7, 0	@ invalidate I & D TLBs
+	mcr	p15, 0, ip, c7, c7, 0	@ invalidate I & D caches, BTB
+	mcr	p14, 0, r4, c6, c0, 0	@ clock configuration, turbo mode.
+	mcr	p15, 0, r5, c15, c1, 0	@ CP access reg
+	mcr	p15, 0, r6, c13, c0, 0	@ PID
+	mcr	p15, 0, r7, c3, c0, 0	@ domain ID
+	mcr	p15, 0, r8, c2, c0, 0	@ translation table base addr
+	mcr	p15, 0, r9, c1, c1, 0	@ auxiliary control reg
+	mov	r0, r10			@ control register
+	mov	r2, r8, lsr #14		@ get TTB0 base
+	mov	r2, r2, lsl #14
+	ldr	r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \
+		     PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE
+	b	cpu_resume_mmu
+ENDPROC(cpu_xscale_do_resume)
+#else
+#define cpu_xscale_do_suspend	0
+#define cpu_xscale_do_resume	0
+#endif
+
 	__CPUINIT
 
 	.type	__xscale_setup, #function
@@ -565,6 +603,9 @@ ENTRY(xscale_processor_functions)
 	.word	cpu_xscale_dcache_clean_area
 	.word	cpu_xscale_switch_mm
 	.word	cpu_xscale_set_pte_ext
+	.word	cpu_xscale_suspend_size
+	.word	cpu_xscale_do_suspend
+	.word	cpu_xscale_do_resume
 	.size	xscale_processor_functions, . - xscale_processor_functions
 
 	.section ".rodata"
diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c
index 935993e1b1e..036fdbfdd62 100644
--- a/arch/arm/mm/vmregion.c
+++ b/arch/arm/mm/vmregion.c
@@ -38,7 +38,7 @@ struct arm_vmregion *
 arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
 		   size_t size, gfp_t gfp)
 {
-	unsigned long addr = head->vm_start, end = head->vm_end - size;
+	unsigned long start = head->vm_start, addr = head->vm_end;
 	unsigned long flags;
 	struct arm_vmregion *c, *new;
 
@@ -54,21 +54,20 @@ arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
 
 	spin_lock_irqsave(&head->vm_lock, flags);
 
-	list_for_each_entry(c, &head->vm_list, vm_list) {
-		if ((addr + size) < addr)
-			goto nospc;
-		if ((addr + size) <= c->vm_start)
+	addr = rounddown(addr - size, align);
+	list_for_each_entry_reverse(c, &head->vm_list, vm_list) {
+		if (addr >= c->vm_end)
 			goto found;
-		addr = ALIGN(c->vm_end, align);
-		if (addr > end)
+		addr = rounddown(c->vm_start - size, align);
+		if (addr < start)
 			goto nospc;
 	}
 
  found:
 	/*
-	 * Insert this entry _before_ the one we found.
+	 * Insert this entry after the one we found.
 	 */
-	list_add_tail(&new->vm_list, &c->vm_list);
+	list_add(&new->vm_list, &c->vm_list);
 	new->vm_start = addr;
 	new->vm_end = addr + size;
 	new->vm_active = 1;