Merge branch 'linux-2.6'

7 files changed, 606 insertions, 5 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index e684e9b3821..b81391a4e37 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -366,6 +366,19 @@ config CPU_32v6K
 	  enabled will not boot on processors with do not support these
 	  instructions.
 
+# ARMv7
+config CPU_V7
+	bool "Support ARM V7 processor"
+	depends on ARCH_INTEGRATOR
+	select CPU_32v6K
+	select CPU_32v7
+	select CPU_ABRT_EV7
+	select CPU_CACHE_V7
+	select CPU_CACHE_VIPT
+	select CPU_CP15_MMU
+	select CPU_COPY_V6 if MMU
+	select CPU_TLB_V6 if MMU
+
 # Figure out what processor architecture version we should be using.
 # This defines the compiler instruction set which depends on the machine type.
 config CPU_32v3
@@ -391,6 +404,9 @@ config CPU_32v5
 config CPU_32v6
 	bool
 
+config CPU_32v7
+	bool
+
 # The abort model
 config CPU_ABRT_NOMMU
 	bool
@@ -413,6 +429,9 @@ config CPU_ABRT_EV5TJ
 config CPU_ABRT_EV6
 	bool
 
+config CPU_ABRT_EV7
+	bool
+
 # The cache model
 config CPU_CACHE_V3
 	bool
@@ -429,6 +448,9 @@ config CPU_CACHE_V4WB
 config CPU_CACHE_V6
 	bool
 
+config CPU_CACHE_V7
+	bool
+
 config CPU_CACHE_VIVT
 	bool
 
@@ -503,7 +525,7 @@ 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_V6
+	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_V6 || CPU_V7
 	default y
 	help
 	  Say Y if you want to include kernel support for running user space
@@ -578,9 +600,15 @@ config CPU_CACHE_ROUND_ROBIN
 	  Say Y here to use the predictable round-robin cache replacement
 	  policy.  Unless you specifically require this or are unsure, say N.
 
+config CPU_L2CACHE_DISABLE
+	bool "Disable level 2 cache"
+	depends on CPU_V7
+	help
+	  Say Y here to disable the level 2 cache.  If unsure, say N.
+
 config CPU_BPREDICT_DISABLE
 	bool "Disable branch prediction"
-	depends on CPU_ARM1020 || CPU_V6 || CPU_XSC3
+	depends on CPU_ARM1020 || CPU_V6 || CPU_XSC3 || CPU_V7
 	help
 	  Say Y here to disable branch prediction.  If unsure, say N.
 
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 2f8b9594777..b5bd335ff14 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -24,12 +24,14 @@ obj-$(CONFIG_CPU_ABRT_LV4T)	+= abort-lv4t.o
 obj-$(CONFIG_CPU_ABRT_EV5T)	+= abort-ev5t.o
 obj-$(CONFIG_CPU_ABRT_EV5TJ)	+= abort-ev5tj.o
 obj-$(CONFIG_CPU_ABRT_EV6)	+= abort-ev6.o
+obj-$(CONFIG_CPU_ABRT_EV7)	+= abort-ev7.o
 
 obj-$(CONFIG_CPU_CACHE_V3)	+= cache-v3.o
 obj-$(CONFIG_CPU_CACHE_V4)	+= cache-v4.o
 obj-$(CONFIG_CPU_CACHE_V4WT)	+= cache-v4wt.o
 obj-$(CONFIG_CPU_CACHE_V4WB)	+= cache-v4wb.o
 obj-$(CONFIG_CPU_CACHE_V6)	+= cache-v6.o
+obj-$(CONFIG_CPU_CACHE_V7)	+= cache-v7.o
 
 obj-$(CONFIG_CPU_COPY_V3)	+= copypage-v3.o
 obj-$(CONFIG_CPU_COPY_V4WT)	+= copypage-v4wt.o
@@ -66,5 +68,6 @@ obj-$(CONFIG_CPU_SA1100)	+= proc-sa1100.o
 obj-$(CONFIG_CPU_XSCALE)	+= proc-xscale.o
 obj-$(CONFIG_CPU_XSC3)		+= proc-xsc3.o
 obj-$(CONFIG_CPU_V6)		+= proc-v6.o
+obj-$(CONFIG_CPU_V7)		+= proc-v7.o
 
 obj-$(CONFIG_CACHE_L2X0)	+= cache-l2x0.o
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
new file mode 100644
index 00000000000..eb90bce38e1
--- /dev/null
+++ b/arch/arm/mm/abort-ev7.S
@@ -0,0 +1,32 @@
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+/*
+ * Function: v7_early_abort
+ *
+ * Params  : r2 = address of aborted instruction
+ *         : r3 = saved SPSR
+ *
+ * Returns : r0 = address of abort
+ *	   : r1 = FSR, bit 11 = write
+ *	   : r2-r8 = corrupted
+ *	   : r9 = preserved
+ *	   : sp = pointer to registers
+ *
+ * Purpose : obtain information about current aborted instruction.
+ */
+	.align	5
+ENTRY(v7_early_abort)
+	/*
+	 * The effect of data aborts on on the exclusive access monitor are
+	 * UNPREDICTABLE. Do a CLREX to clear the state
+	 */
+	clrex
+
+	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
+	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
+
+	/*
+	 * V6 code adjusts the returned DFSR.
+	 * New designs should not need to patch up faults.
+	 */
+	mov	pc, lr
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
new file mode 100644
index 00000000000..35ffc4d9599
--- /dev/null
+++ b/arch/arm/mm/cache-v7.S
@@ -0,0 +1,253 @@
+/*
+ *  linux/arch/arm/mm/cache-v7.S
+ *
+ *  Copyright (C) 2001 Deep Blue Solutions Ltd.
+ *  Copyright (C) 2005 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  This is the "shell" of the ARMv7 processor support.
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/assembler.h>
+
+#include "proc-macros.S"
+
+/*
+ *	v7_flush_dcache_all()
+ *
+ *	Flush the whole D-cache.
+ *
+ *	Corrupted registers: r0-r5, r7, r9-r11
+ *
+ *	- mm    - mm_struct describing address space
+ */
+ENTRY(v7_flush_dcache_all)
+	mrc	p15, 1, r0, c0, c0, 1		@ read clidr
+	ands	r3, r0, #0x7000000		@ extract loc from clidr
+	mov	r3, r3, lsr #23			@ left align loc bit field
+	beq	finished			@ if loc is 0, then no need to clean
+	mov	r10, #0				@ start clean at cache level 0
+loop1:
+	add	r2, r10, r10, lsr #1		@ work out 3x current cache level
+	mov	r1, r0, lsr r2			@ extract cache type bits from clidr
+	and	r1, r1, #7			@ mask of the bits for current cache only
+	cmp	r1, #2				@ see what cache we have at this level
+	blt	skip				@ skip if no cache, or just i-cache
+	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
+	isb					@ isb to sych the new cssr&csidr
+	mrc	p15, 1, r1, c0, c0, 0		@ read the new csidr
+	and	r2, r1, #7			@ extract the length of the cache lines
+	add	r2, r2, #4			@ add 4 (line length offset)
+	ldr	r4, =0x3ff
+	ands	r4, r4, r1, lsr #3		@ find maximum number on the way size
+	clz	r5, r4				@ find bit position of way size increment
+	ldr	r7, =0x7fff
+	ands	r7, r7, r1, lsr #13		@ extract max number of the index size
+loop2:
+	mov	r9, r4				@ create working copy of max way size
+loop3:
+	orr	r11, r10, r9, lsl r5		@ factor way and cache number into r11
+	orr	r11, r11, r7, lsl r2		@ factor index number into r11
+	mcr	p15, 0, r11, c7, c14, 2		@ clean & invalidate by set/way
+	subs	r9, r9, #1			@ decrement the way
+	bge	loop3
+	subs	r7, r7, #1			@ decrement the index
+	bge	loop2
+skip:
+	add	r10, r10, #2			@ increment cache number
+	cmp	r3, r10
+	bgt	loop1
+finished:
+	mov	r10, #0				@ swith back to cache level 0
+	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
+	isb
+	mov	pc, lr
+
+/*
+ *	v7_flush_cache_all()
+ *
+ *	Flush the entire cache system.
+ *  The data cache flush is now achieved using atomic clean / invalidates
+ *  working outwards from L1 cache. This is done using Set/Way based cache
+ *  maintainance instructions.
+ *  The instruction cache can still be invalidated back to the point of
+ *  unification in a single instruction.
+ *
+ */
+ENTRY(v7_flush_kern_cache_all)
+	stmfd	sp!, {r4-r5, r7, r9-r11, lr}
+	bl	v7_flush_dcache_all
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ I+BTB cache invalidate
+	ldmfd	sp!, {r4-r5, r7, r9-r11, lr}
+	mov	pc, lr
+
+/*
+ *	v7_flush_cache_all()
+ *
+ *	Flush all TLB entries in a particular address space
+ *
+ *	- mm    - mm_struct describing address space
+ */
+ENTRY(v7_flush_user_cache_all)
+	/*FALLTHROUGH*/
+
+/*
+ *	v7_flush_cache_range(start, end, flags)
+ *
+ *	Flush a range of TLB entries in the specified address space.
+ *
+ *	- start - start address (may not be aligned)
+ *	- end   - end address (exclusive, may not be aligned)
+ *	- flags	- vm_area_struct flags describing address space
+ *
+ *	It is assumed that:
+ *	- we have a VIPT cache.
+ */
+ENTRY(v7_flush_user_cache_range)
+	mov	pc, lr
+
+/*
+ *	v7_coherent_kern_range(start,end)
+ *
+ *	Ensure that the I and D caches are coherent within specified
+ *	region.  This is typically used when code has been written to
+ *	a memory region, and will be executed.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ *
+ *	It is assumed that:
+ *	- the Icache does not read data from the write buffer
+ */
+ENTRY(v7_coherent_kern_range)
+	/* FALLTHROUGH */
+
+/*
+ *	v7_coherent_user_range(start,end)
+ *
+ *	Ensure that the I and D caches are coherent within specified
+ *	region.  This is typically used when code has been written to
+ *	a memory region, and will be executed.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ *
+ *	It is assumed that:
+ *	- the Icache does not read data from the write buffer
+ */
+ENTRY(v7_coherent_user_range)
+	dcache_line_size r2, r3
+	sub	r3, r2, #1
+	bic	r0, r0, r3
+1:	mcr	p15, 0, r0, c7, c11, 1		@ clean D line to the point of unification
+	dsb
+	mcr	p15, 0, r0, c7, c5, 1		@ invalidate I line
+	add	r0, r0, r2
+	cmp	r0, r1
+	blo	1b
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 6		@ invalidate BTB
+	dsb
+	isb
+	mov	pc, lr
+
+/*
+ *	v7_flush_kern_dcache_page(kaddr)
+ *
+ *	Ensure that the data held in the page kaddr is written back
+ *	to the page in question.
+ *
+ *	- kaddr   - kernel address (guaranteed to be page aligned)
+ */
+ENTRY(v7_flush_kern_dcache_page)
+	dcache_line_size r2, r3
+	add	r1, r0, #PAGE_SZ
+1:
+	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line / unified line
+	add	r0, r0, r2
+	cmp	r0, r1
+	blo	1b
+	dsb
+	mov	pc, lr
+
+/*
+ *	v7_dma_inv_range(start,end)
+ *
+ *	Invalidate the data cache within the specified region; we will
+ *	be performing a DMA operation in this region and we want to
+ *	purge old data in the cache.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(v7_dma_inv_range)
+	dcache_line_size r2, r3
+	sub	r3, r2, #1
+	tst	r0, r3
+	bic	r0, r0, r3
+	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
+
+	tst	r1, r3
+	bic	r1, r1, r3
+	mcrne	p15, 0, r1, c7, c14, 1		@ clean & invalidate D / U line
+1:
+	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D / U line
+	add	r0, r0, r2
+	cmp	r0, r1
+	blo	1b
+	dsb
+	mov	pc, lr
+
+/*
+ *	v7_dma_clean_range(start,end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(v7_dma_clean_range)
+	dcache_line_size r2, r3
+	sub	r3, r2, #1
+	bic	r0, r0, r3
+1:
+	mcr	p15, 0, r0, c7, c10, 1		@ clean D / U line
+	add	r0, r0, r2
+	cmp	r0, r1
+	blo	1b
+	dsb
+	mov	pc, lr
+
+/*
+ *	v7_dma_flush_range(start,end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(v7_dma_flush_range)
+	dcache_line_size r2, r3
+	sub	r3, r2, #1
+	bic	r0, r0, r3
+1:
+	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
+	add	r0, r0, r2
+	cmp	r0, r1
+	blo	1b
+	dsb
+	mov	pc, lr
+
+	__INITDATA
+
+	.type	v7_cache_fns, #object
+ENTRY(v7_cache_fns)
+	.long	v7_flush_kern_cache_all
+	.long	v7_flush_user_cache_all
+	.long	v7_flush_user_cache_range
+	.long	v7_coherent_kern_range
+	.long	v7_coherent_user_range
+	.long	v7_flush_kern_dcache_page
+	.long	v7_dma_inv_range
+	.long	v7_dma_clean_range
+	.long	v7_dma_flush_range
+	.size	v7_cache_fns, . - v7_cache_fns
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 9da43a0fdcd..fc84fcc7438 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -14,7 +14,8 @@
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
-unsigned int cpu_last_asid = { 1 << ASID_BITS };
+static DEFINE_SPINLOCK(cpu_asid_lock);
+unsigned int cpu_last_asid = ASID_FIRST_VERSION;
 
 /*
  * We fork()ed a process, and we need a new context for the child
@@ -31,15 +32,16 @@ void __new_context(struct mm_struct *mm)
 {
 	unsigned int asid;
 
+	spin_lock(&cpu_asid_lock);
 	asid = ++cpu_last_asid;
 	if (asid == 0)
-		asid = cpu_last_asid = 1 << ASID_BITS;
+		asid = cpu_last_asid = ASID_FIRST_VERSION;
 
 	/*
 	 * If we've used up all our ASIDs, we need
 	 * to start a new version and flush the TLB.
 	 */
-	if ((asid & ~ASID_MASK) == 0) {
+	if (unlikely((asid & ~ASID_MASK) == 0)) {
 		asid = ++cpu_last_asid;
 		/* set the reserved ASID before flushing the TLB */
 		asm("mcr	p15, 0, %0, c13, c0, 1	@ set reserved context ID\n"
@@ -47,7 +49,16 @@ void __new_context(struct mm_struct *mm)
 		    : "r" (0));
 		isb();
 		flush_tlb_all();
+		if (icache_is_vivt_asid_tagged()) {
+			asm("mcr	p15, 0, %0, c7, c5, 0	@ invalidate I-cache\n"
+			    "mcr	p15, 0, %0, c7, c5, 6	@ flush BTAC/BTB\n"
+			    :
+			    : "r" (0));
+			dsb();
+		}
 	}
+	spin_unlock(&cpu_asid_lock);
 
+	mm->cpu_vm_mask = cpumask_of_cpu(smp_processor_id());
 	mm->context.id = asid;
 }
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 9e2c89eb211..b13150052a7 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -59,3 +59,15 @@
 	.word	\ucset
 #endif
 	.endm
+
+/*
+ * cache_line_size - get the cache line size from the CSIDR register
+ * (available on ARMv7+). It assumes that the CSSR register was configured
+ * to access the L1 data cache CSIDR.
+ */
+	.macro	dcache_line_size, reg, tmp
+	mrc	p15, 1, \tmp, c0, c0, 0		@ read CSIDR
+	and	\tmp, \tmp, #7			@ cache line size encoding
+	mov	\reg, #16			@ size offset
+	mov	\reg, \reg, lsl \tmp		@ actual cache line size
+	.endm
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
new file mode 100644
index 00000000000..dd823dd4a37
--- /dev/null
+++ b/arch/arm/mm/proc-v7.S
@@ -0,0 +1,262 @@
+/*
+ *  linux/arch/arm/mm/proc-v7.S
+ *
+ *  Copyright (C) 2001 Deep Blue Solutions Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  This is the "shell" of the ARMv7 processor support.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/asm-offsets.h>
+#include <asm/elf.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/pgtable.h>
+
+#include "proc-macros.S"
+
+#define TTB_C		(1 << 0)
+#define TTB_S		(1 << 1)
+#define TTB_RGN_OC_WT	(2 << 3)
+#define TTB_RGN_OC_WB	(3 << 3)
+
+ENTRY(cpu_v7_proc_init)
+	mov	pc, lr
+
+ENTRY(cpu_v7_proc_fin)
+	mov	pc, lr
+
+/*
+ *	cpu_v7_reset(loc)
+ *
+ *	Perform a soft reset of the system.  Put the CPU into the
+ *	same state as it would be if it had been reset, and branch
+ *	to what would be the reset vector.
+ *
+ *	- loc   - location to jump to for soft reset
+ *
+ *	It is assumed that:
+ */
+	.align	5
+ENTRY(cpu_v7_reset)
+	mov	pc, r0
+
+/*
+ *	cpu_v7_do_idle()
+ *
+ *	Idle the processor (eg, wait for interrupt).
+ *
+ *	IRQs are already disabled.
+ */
+ENTRY(cpu_v7_do_idle)
+	.long	0xe320f003			@ ARM V7 WFI instruction
+	mov	pc, lr
+
+ENTRY(cpu_v7_dcache_clean_area)
+#ifndef TLB_CAN_READ_FROM_L1_CACHE
+	dcache_line_size r2, r3
+1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
+	add	r0, r0, r2
+	subs	r1, r1, r2
+	bhi	1b
+	dsb
+#endif
+	mov	pc, lr
+
+/*
+ *	cpu_v7_switch_mm(pgd_phys, tsk)
+ *
+ *	Set the translation table base pointer to be pgd_phys
+ *
+ *	- pgd_phys - physical address of new TTB
+ *
+ *	It is assumed that:
+ *	- we are not using split page tables
+ */
+ENTRY(cpu_v7_switch_mm)
+	mov	r2, #0
+	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	orr	r0, r0, #TTB_RGN_OC_WB		@ mark PTWs outer cacheable, WB
+	mcr	p15, 0, r2, c13, c0, 1		@ set reserved context ID
+	isb
+1:	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
+	isb
+	mcr	p15, 0, r1, c13, c0, 1		@ set context ID
+	isb
+	mov	pc, lr
+
+/*
+ *	cpu_v7_set_pte_ext(ptep, pte)
+ *
+ *	Set a level 2 translation table entry.
+ *
+ *	- ptep  - pointer to level 2 translation table entry
+ *		  (hardware version is stored at -1024 bytes)
+ *	- pte   - PTE value to store
+ *	- ext	- value for extended PTE bits
+ *
+ *	Permissions:
+ *	  YUWD  APX AP1 AP0	SVC	User
+ *	  0xxx   0   0   0	no acc	no acc
+ *	  100x   1   0   1	r/o	no acc
+ *	  10x0   1   0   1	r/o	no acc
+ *	  1011   0   0   1	r/w	no acc
+ *	  110x   0   1   0	r/w	r/o
+ *	  11x0   0   1   0	r/w	r/o
+ *	  1111   0   1   1	r/w	r/w
+ */
+ENTRY(cpu_v7_set_pte_ext)
+	str	r1, [r0], #-2048		@ linux version
+
+	bic	r3, r1, #0x000003f0
+	bic	r3, r3, #0x00000003
+	orr	r3, r3, r2
+	orr	r3, r3, #PTE_EXT_AP0 | 2
+
+	tst	r1, #L_PTE_WRITE
+	tstne	r1, #L_PTE_DIRTY
+	orreq	r3, r3, #PTE_EXT_APX
+
+	tst	r1, #L_PTE_USER
+	orrne	r3, r3, #PTE_EXT_AP1
+	tstne	r3, #PTE_EXT_APX
+	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+
+	tst	r1, #L_PTE_YOUNG
+	biceq	r3, r3, #PTE_EXT_APX | PTE_EXT_AP_MASK
+
+	tst	r1, #L_PTE_EXEC
+	orreq	r3, r3, #PTE_EXT_XN
+
+	tst	r1, #L_PTE_PRESENT
+	moveq	r3, #0
+
+	str	r3, [r0]
+	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+	mov	pc, lr
+
+cpu_v7_name:
+	.ascii	"ARMv7 Processor"
+	.align
+
+	.section ".text.init", #alloc, #execinstr
+
+/*
+ *	__v7_setup
+ *
+ *	Initialise TLB, Caches, and MMU state ready to switch the MMU
+ *	on.  Return in r0 the new CP15 C1 control register setting.
+ *
+ *	We automatically detect if we have a Harvard cache, and use the
+ *	Harvard cache control instructions insead of the unified cache
+ *	control instructions.
+ *
+ *	This should be able to cover all ARMv7 cores.
+ *
+ *	It is assumed that:
+ *	- cache type register is implemented
+ */
+__v7_setup:
+	adr	r12, __v7_setup_stack		@ the local stack
+	stmia	r12, {r0-r5, r7, r9, r11, lr}
+	bl	v7_flush_dcache_all
+	ldmia	r12, {r0-r5, r7, r9, r11, lr}
+	mov	r10, #0
+#ifdef HARVARD_CACHE
+	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
+#endif
+	dsb
+	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
+	mcr	p15, 0, r10, c2, c0, 2		@ TTB control register
+	orr	r4, r4, #TTB_RGN_OC_WB		@ mark PTWs outer cacheable, WB
+	mcr	p15, 0, r4, c2, c0, 0		@ load TTB0
+	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
+	mov	r10, #0x1f			@ domains 0, 1 = manager
+	mcr	p15, 0, r10, c3, c0, 0		@ load domain access register
+#ifndef CONFIG_CPU_L2CACHE_DISABLE
+	@ L2 cache configuration in the L2 aux control register
+	mrc	p15, 1, r10, c9, c0, 2
+	bic	r10, r10, #(1 << 16)		@ L2 outer cache
+	mcr	p15, 1, r10, c9, c0, 2
+	@ L2 cache is enabled in the aux control register
+	mrc	p15, 0, r10, c1, c0, 1
+	orr	r10, r10, #2
+	mcr	p15, 0, r10, c1, c0, 1
+#endif
+	mrc	p15, 0, r0, c1, c0, 0		@ read control register
+	ldr	r10, cr1_clear			@ get mask for bits to clear
+	bic	r0, r0, r10			@ clear bits them
+	ldr	r10, cr1_set			@ get mask for bits to set
+	orr	r0, r0, r10			@ set them
+	mov	pc, lr				@ return to head.S:__ret
+
+	/*
+	 *         V X F   I D LR
+	 * .... ...E PUI. .T.T 4RVI ZFRS BLDP WCAM
+	 * rrrr rrrx xxx0 0101 xxxx xxxx x111 xxxx < forced
+	 *         0 110       0011 1.00 .111 1101 < we want
+	 */
+	.type	cr1_clear, #object
+	.type	cr1_set, #object
+cr1_clear:
+	.word	0x0120c302
+cr1_set:
+	.word	0x00c0387d
+
+__v7_setup_stack:
+	.space	4 * 11				@ 11 registers
+
+	.type	v7_processor_functions, #object
+ENTRY(v7_processor_functions)
+	.word	v7_early_abort
+	.word	cpu_v7_proc_init
+	.word	cpu_v7_proc_fin
+	.word	cpu_v7_reset
+	.word	cpu_v7_do_idle
+	.word	cpu_v7_dcache_clean_area
+	.word	cpu_v7_switch_mm
+	.word	cpu_v7_set_pte_ext
+	.size	v7_processor_functions, . - v7_processor_functions
+
+	.type	cpu_arch_name, #object
+cpu_arch_name:
+	.asciz	"armv7"
+	.size	cpu_arch_name, . - cpu_arch_name
+
+	.type	cpu_elf_name, #object
+cpu_elf_name:
+	.asciz	"v7"
+	.size	cpu_elf_name, . - cpu_elf_name
+	.align
+
+	.section ".proc.info.init", #alloc, #execinstr
+
+	/*
+	 * Match any ARMv7 processor core.
+	 */
+	.type	__v7_proc_info, #object
+__v7_proc_info:
+	.long	0x000f0000		@ Required ID value
+	.long	0x000f0000		@ Mask for ID
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_BUFFERABLE | \
+		PMD_SECT_CACHEABLE | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_XN | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ
+	b	__v7_setup
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+	.long	cpu_v7_name
+	.long	v7_processor_functions
+	.long	v6wbi_tlb_fns
+	.long	v6_user_fns
+	.long	v7_cache_fns
+	.size	__v7_proc_info, . - __v7_proc_info