Merge branch 'for-linus' of master.kernel.org:/home/rmk/linux-2.6-arm

* 'for-linus' of master.kernel.org:/home/rmk/linux-2.6-arm: (91 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
  ...

23 files changed, 472 insertions, 624 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 185ee822c93..74554f1742d 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_MODULES)		+= armksyms.o module.o
 obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
+obj-$(CONFIG_PM)		+= sleep.o
 obj-$(CONFIG_HAVE_SCHED_CLOCK)	+= sched_clock.o
 obj-$(CONFIG_SMP)		+= smp.o smp_tlb.o
 obj-$(CONFIG_HAVE_ARM_SCU)	+= smp_scu.o
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index e5e1e538767..acca35aebe2 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -140,24 +140,18 @@ EXPORT_SYMBOL(__aeabi_ulcmp);
 #endif
 
 	/* bitops */
-EXPORT_SYMBOL(_set_bit_le);
-EXPORT_SYMBOL(_test_and_set_bit_le);
-EXPORT_SYMBOL(_clear_bit_le);
-EXPORT_SYMBOL(_test_and_clear_bit_le);
-EXPORT_SYMBOL(_change_bit_le);
-EXPORT_SYMBOL(_test_and_change_bit_le);
+EXPORT_SYMBOL(_set_bit);
+EXPORT_SYMBOL(_test_and_set_bit);
+EXPORT_SYMBOL(_clear_bit);
+EXPORT_SYMBOL(_test_and_clear_bit);
+EXPORT_SYMBOL(_change_bit);
+EXPORT_SYMBOL(_test_and_change_bit);
 EXPORT_SYMBOL(_find_first_zero_bit_le);
 EXPORT_SYMBOL(_find_next_zero_bit_le);
 EXPORT_SYMBOL(_find_first_bit_le);
 EXPORT_SYMBOL(_find_next_bit_le);
 
 #ifdef __ARMEB__
-EXPORT_SYMBOL(_set_bit_be);
-EXPORT_SYMBOL(_test_and_set_bit_be);
-EXPORT_SYMBOL(_clear_bit_be);
-EXPORT_SYMBOL(_test_and_clear_bit_be);
-EXPORT_SYMBOL(_change_bit_be);
-EXPORT_SYMBOL(_test_and_change_bit_be);
 EXPORT_SYMBOL(_find_first_zero_bit_be);
 EXPORT_SYMBOL(_find_next_zero_bit_be);
 EXPORT_SYMBOL(_find_first_bit_be);
@@ -170,3 +164,7 @@ EXPORT_SYMBOL(mcount);
 #endif
 EXPORT_SYMBOL(__gnu_mcount_nc);
 #endif
+
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
+EXPORT_SYMBOL(__pv_phys_offset);
+#endif
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 82da6617213..927522cfc12 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -13,6 +13,9 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
+#include <asm/cacheflush.h>
+#include <asm/glue-df.h>
+#include <asm/glue-pf.h>
 #include <asm/mach/arch.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
@@ -114,6 +117,14 @@ int main(void)
 #ifdef MULTI_PABORT
   DEFINE(PROCESSOR_PABT_FUNC,	offsetof(struct processor, _prefetch_abort));
 #endif
+#ifdef MULTI_CPU
+  DEFINE(CPU_SLEEP_SIZE,	offsetof(struct processor, suspend_size));
+  DEFINE(CPU_DO_SUSPEND,	offsetof(struct processor, do_suspend));
+  DEFINE(CPU_DO_RESUME,		offsetof(struct processor, do_resume));
+#endif
+#ifdef MULTI_CACHE
+  DEFINE(CACHE_FLUSH_KERN_ALL,	offsetof(struct cpu_cache_fns, flush_kern_all));
+#endif
   BLANK();
   DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index c6273a3bfc2..d86fcd44b22 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -583,6 +583,11 @@ void __init pci_common_init(struct hw_pci *hw)
 			 * Assign resources.
 			 */
 			pci_bus_assign_resources(bus);
+
+			/*
+			 * Enable bridges
+			 */
+			pci_enable_bridges(bus);
 		}
 
 		/*
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index a0f07521ca8..d2d983be096 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -25,7 +25,7 @@
 		.macro	addruart, rp, rv
 		.endm
 
-#if defined(CONFIG_CPU_V6)
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 
 		.macro	senduart, rd, rx
 		mcr	p14, 0, \rd, c0, c5, 0
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 2b46fea36c9..e8d88567680 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -16,7 +16,8 @@
  */
 
 #include <asm/memory.h>
-#include <asm/glue.h>
+#include <asm/glue-df.h>
+#include <asm/glue-pf.h>
 #include <asm/vfpmacros.h>
 #include <mach/entry-macro.S>
 #include <asm/thread_notify.h>
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index ae946490016..051166c2a93 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -76,13 +76,13 @@
 #ifndef CONFIG_THUMB2_KERNEL
 	.macro	svc_exit, rpsr
 	msr	spsr_cxsf, \rpsr
-#if defined(CONFIG_CPU_32v6K)
-	clrex					@ clear the exclusive monitor
-	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
-#elif defined (CONFIG_CPU_V6)
+#if defined(CONFIG_CPU_V6)
 	ldr	r0, [sp]
 	strex	r1, r2, [sp]			@ clear the exclusive monitor
 	ldmib	sp, {r1 - pc}^			@ load r1 - pc, cpsr
+#elif defined(CONFIG_CPU_32v6K)
+	clrex					@ clear the exclusive monitor
+	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
 #else
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
 #endif
@@ -92,10 +92,10 @@
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [sp, #\offset + S_PC]!	@ get pc
 	msr	spsr_cxsf, r1			@ save in spsr_svc
-#if defined(CONFIG_CPU_32v6K)
-	clrex					@ clear the exclusive monitor
-#elif defined (CONFIG_CPU_V6)
+#if defined(CONFIG_CPU_V6)
 	strex	r1, r2, [sp]			@ clear the exclusive monitor
+#elif defined(CONFIG_CPU_32v6K)
+	clrex					@ clear the exclusive monitor
 #endif
 	.if	\fast
 	ldmdb	sp, {r1 - lr}^			@ get calling r1 - lr
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 8f57515bbdb..c84b57d27d0 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -25,83 +25,6 @@
  * machine ID for example).
  */
 	__HEAD
-__error_a:
-#ifdef CONFIG_DEBUG_LL
-	mov	r4, r1				@ preserve machine ID
-	adr	r0, str_a1
-	bl	printascii
-	mov	r0, r4
-	bl	printhex8
-	adr	r0, str_a2
-	bl	printascii
-	adr	r3, __lookup_machine_type_data
-	ldmia	r3, {r4, r5, r6}		@ get machine desc list
-	sub	r4, r3, r4			@ get offset between virt&phys
-	add	r5, r5, r4			@ convert virt addresses to
-	add	r6, r6, r4			@ physical address space
-1:	ldr	r0, [r5, #MACHINFO_TYPE]	@ get machine type
-	bl	printhex8
-	mov	r0, #'\t'
-	bl	printch
-	ldr     r0, [r5, #MACHINFO_NAME]	@ get machine name
-	add	r0, r0, r4
-	bl	printascii
-	mov	r0, #'\n'
-	bl	printch
-	add	r5, r5, #SIZEOF_MACHINE_DESC	@ next machine_desc
-	cmp	r5, r6
-	blo	1b
-	adr	r0, str_a3
-	bl	printascii
-	b	__error
-ENDPROC(__error_a)
-
-str_a1:	.asciz	"\nError: unrecognized/unsupported machine ID (r1 = 0x"
-str_a2:	.asciz	").\n\nAvailable machine support:\n\nID (hex)\tNAME\n"
-str_a3:	.asciz	"\nPlease check your kernel config and/or bootloader.\n"
-	.align
-#else
-	b	__error
-#endif
-
-/*
- * Lookup machine architecture in the linker-build list of architectures.
- * Note that we can't use the absolute addresses for the __arch_info
- * lists since we aren't running with the MMU on (and therefore, we are
- * not in the correct address space).  We have to calculate the offset.
- *
- *  r1 = machine architecture number
- * Returns:
- *  r3, r4, r6 corrupted
- *  r5 = mach_info pointer in physical address space
- */
-__lookup_machine_type:
-	adr	r3, __lookup_machine_type_data
-	ldmia	r3, {r4, r5, r6}
-	sub	r3, r3, r4			@ get offset between virt&phys
-	add	r5, r5, r3			@ convert virt addresses to
-	add	r6, r6, r3			@ physical address space
-1:	ldr	r3, [r5, #MACHINFO_TYPE]	@ get machine type
-	teq	r3, r1				@ matches loader number?
-	beq	2f				@ found
-	add	r5, r5, #SIZEOF_MACHINE_DESC	@ next machine_desc
-	cmp	r5, r6
-	blo	1b
-	mov	r5, #0				@ unknown machine
-2:	mov	pc, lr
-ENDPROC(__lookup_machine_type)
-
-/*
- * Look in arch/arm/kernel/arch.[ch] for information about the
- * __arch_info structures.
- */
-	.align	2
-	.type	__lookup_machine_type_data, %object
-__lookup_machine_type_data:
-	.long	.
-	.long	__arch_info_begin
-	.long	__arch_info_end
-	.size	__lookup_machine_type_data, . - __lookup_machine_type_data
 
 /* Determine validity of the r2 atags pointer.  The heuristic requires
  * that the pointer be aligned, in the first 16k of physical RAM and
@@ -109,8 +32,6 @@ __lookup_machine_type_data:
  * of this function may be more lenient with the physical address and
  * may also be able to move the ATAGS block if necessary.
  *
- * r8  = machinfo
- *
  * Returns:
  *  r2 either valid atags pointer, or zero
  *  r5, r6 corrupted
@@ -185,17 +106,6 @@ __mmap_switched_data:
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
 /*
- * This provides a C-API version of __lookup_machine_type
- */
-ENTRY(lookup_machine_type)
-	stmfd	sp!, {r4 - r6, lr}
-	mov	r1, r0
-	bl	__lookup_machine_type
-	mov	r0, r5
-	ldmfd	sp!, {r4 - r6, pc}
-ENDPROC(lookup_machine_type)
-
-/*
  * This provides a C-API version of __lookup_processor_type
  */
 ENTRY(lookup_processor_type)
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 814ce1a7327..6b1e0ad9ec3 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -44,9 +44,6 @@ ENTRY(stext)
 	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
 	movs	r10, r5				@ invalid processor (r5=0)?
 	beq	__error_p				@ yes, error 'p'
-	bl	__lookup_machine_type		@ r5=machinfo
-	movs	r8, r5				@ invalid machine (r5=0)?
-	beq	__error_a			@ yes, error 'a'
 
 	adr	lr, BSYM(__after_proc_init)	@ return (PIC) address
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index f06ff9feb0d..c9173cfbbc7 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -26,14 +26,6 @@
 #include <mach/debug-macro.S>
 #endif
 
-#if (PHYS_OFFSET & 0x001fffff)
-#error "PHYS_OFFSET must be at an even 2MiB boundary!"
-#endif
-
-#define KERNEL_RAM_VADDR	(PAGE_OFFSET + TEXT_OFFSET)
-#define KERNEL_RAM_PADDR	(PHYS_OFFSET + TEXT_OFFSET)
-
-
 /*
  * swapper_pg_dir is the virtual address of the initial page table.
  * We place the page tables 16K below KERNEL_RAM_VADDR.  Therefore, we must
@@ -41,6 +33,7 @@
  * the least significant 16 bits to be 0x8000, but we could probably
  * relax this restriction to KERNEL_RAM_VADDR >= PAGE_OFFSET + 0x4000.
  */
+#define KERNEL_RAM_VADDR	(PAGE_OFFSET + TEXT_OFFSET)
 #if (KERNEL_RAM_VADDR & 0xffff) != 0x8000
 #error KERNEL_RAM_VADDR must start at 0xXXXX8000
 #endif
@@ -48,8 +41,8 @@
 	.globl	swapper_pg_dir
 	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - 0x4000
 
-	.macro	pgtbl, rd
-	ldr	\rd, =(KERNEL_RAM_PADDR - 0x4000)
+	.macro	pgtbl, rd, phys
+	add	\rd, \phys, #TEXT_OFFSET - 0x4000
 	.endm
 
 #ifdef CONFIG_XIP_KERNEL
@@ -87,25 +80,33 @@ ENTRY(stext)
 	movs	r10, r5				@ invalid processor (r5=0)?
  THUMB( it	eq )		@ force fixup-able long branch encoding
 	beq	__error_p			@ yes, error 'p'
-	bl	__lookup_machine_type		@ r5=machinfo
-	movs	r8, r5				@ invalid machine (r5=0)?
- THUMB( it	eq )		@ force fixup-able long branch encoding
-	beq	__error_a			@ yes, error 'a'
+
+#ifndef CONFIG_XIP_KERNEL
+	adr	r3, 2f
+	ldmia	r3, {r4, r8}
+	sub	r4, r3, r4			@ (PHYS_OFFSET - PAGE_OFFSET)
+	add	r8, r8, r4			@ PHYS_OFFSET
+#else
+	ldr	r8, =PLAT_PHYS_OFFSET
+#endif
 
 	/*
 	 * r1 = machine no, r2 = atags,
-	 * r8 = machinfo, r9 = cpuid, r10 = procinfo
+	 * r8 = phys_offset, r9 = cpuid, r10 = procinfo
 	 */
 	bl	__vet_atags
 #ifdef CONFIG_SMP_ON_UP
 	bl	__fixup_smp
 #endif
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
+	bl	__fixup_pv_table
+#endif
 	bl	__create_page_tables
 
 	/*
 	 * The following calls CPU specific code in a position independent
 	 * manner.  See arch/arm/mm/proc-*.S for details.  r10 = base of
-	 * xxx_proc_info structure selected by __lookup_machine_type
+	 * xxx_proc_info structure selected by __lookup_processor_type
 	 * above.  On return, the CPU will be ready for the MMU to be
 	 * turned on, and r0 will hold the CPU control register value.
 	 */
@@ -118,22 +119,24 @@ ENTRY(stext)
 1:	b	__enable_mmu
 ENDPROC(stext)
 	.ltorg
+#ifndef CONFIG_XIP_KERNEL
+2:	.long	.
+	.long	PAGE_OFFSET
+#endif
 
 /*
  * Setup the initial page tables.  We only setup the barest
  * amount which are required to get the kernel running, which
  * generally means mapping in the kernel code.
  *
- * r8  = machinfo
- * r9  = cpuid
- * r10 = procinfo
+ * r8 = phys_offset, r9 = cpuid, r10 = procinfo
  *
  * Returns:
  *  r0, r3, r5-r7 corrupted
  *  r4 = physical page table address
  */
 __create_page_tables:
-	pgtbl	r4				@ page table address
+	pgtbl	r4, r8				@ page table address
 
 	/*
 	 * Clear the 16K level 1 swapper page table
@@ -189,10 +192,8 @@ __create_page_tables:
 	/*
 	 * Map some ram to cover our .data and .bss areas.
 	 */
-	orr	r3, r7, #(KERNEL_RAM_PADDR & 0xff000000)
-	.if	(KERNEL_RAM_PADDR & 0x00f00000)
-	orr	r3, r3, #(KERNEL_RAM_PADDR & 0x00f00000)
-	.endif
+	add	r3, r8, #TEXT_OFFSET
+	orr	r3, r3, r7
 	add	r0, r4,  #(KERNEL_RAM_VADDR & 0xff000000) >> 18
 	str	r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> 18]!
 	ldr	r6, =(_end - 1)
@@ -205,14 +206,17 @@ __create_page_tables:
 #endif
 
 	/*
-	 * Then map first 1MB of ram in case it contains our boot params.
+	 * Then map boot params address in r2 or
+	 * the first 1MB of ram if boot params address is not specified.
 	 */
-	add	r0, r4, #PAGE_OFFSET >> 18
-	orr	r6, r7, #(PHYS_OFFSET & 0xff000000)
-	.if	(PHYS_OFFSET & 0x00f00000)
-	orr	r6, r6, #(PHYS_OFFSET & 0x00f00000)
-	.endif
-	str	r6, [r0]
+	mov	r0, r2, lsr #20
+	movs	r0, r0, lsl #20
+	moveq	r0, r8
+	sub	r3, r0, r8
+	add	r3, r3, #PAGE_OFFSET
+	add	r3, r4, r3, lsr #18
+	orr	r6, r7, r0
+	str	r6, [r3]
 
 #ifdef CONFIG_DEBUG_LL
 #ifndef CONFIG_DEBUG_ICEDCC
@@ -457,4 +461,129 @@ ENTRY(fixup_smp)
 	ldmfd	sp!, {r4 - r6, pc}
 ENDPROC(fixup_smp)
 
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
+
+/* __fixup_pv_table - patch the stub instructions with the delta between
+ * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be 16MiB aligned and
+ * can be expressed by an immediate shifter operand. The stub instruction
+ * has a form of '(add|sub) rd, rn, #imm'.
+ */
+	__HEAD
+__fixup_pv_table:
+	adr	r0, 1f
+	ldmia	r0, {r3-r5, r7}
+	sub	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
+	add	r4, r4, r3	@ adjust table start address
+	add	r5, r5, r3	@ adjust table end address
+	add	r7, r7, r3	@ adjust __pv_phys_offset address
+	str	r8, [r7]	@ save computed PHYS_OFFSET to __pv_phys_offset
+#ifndef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
+	mov	r6, r3, lsr #24	@ constant for add/sub instructions
+	teq	r3, r6, lsl #24 @ must be 16MiB aligned
+#else
+	mov	r6, r3, lsr #16	@ constant for add/sub instructions
+	teq	r3, r6, lsl #16	@ must be 64kiB aligned
+#endif
+THUMB(	it	ne		@ cross section branch )
+	bne	__error
+	str	r6, [r7, #4]	@ save to __pv_offset
+	b	__fixup_a_pv_table
+ENDPROC(__fixup_pv_table)
+
+	.align
+1:	.long	.
+	.long	__pv_table_begin
+	.long	__pv_table_end
+2:	.long	__pv_phys_offset
+
+	.text
+__fixup_a_pv_table:
+#ifdef CONFIG_THUMB2_KERNEL
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
+	lsls	r0, r6, #24
+	lsr	r6, #8
+	beq	1f
+	clz	r7, r0
+	lsr	r0, #24
+	lsl	r0, r7
+	bic	r0, 0x0080
+	lsrs	r7, #1
+	orrcs   r0, #0x0080
+	orr	r0, r0, r7, lsl #12
+#endif
+1:	lsls	r6, #24
+	beq	4f
+	clz	r7, r6
+	lsr	r6, #24
+	lsl	r6, r7
+	bic	r6, #0x0080
+	lsrs	r7, #1
+	orrcs	r6, #0x0080
+	orr	r6, r6, r7, lsl #12
+	orr	r6, #0x4000
+	b	4f
+2:	@ at this point the C flag is always clear
+	add     r7, r3
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
+	ldrh	ip, [r7]
+	tst	ip, 0x0400	@ the i bit tells us LS or MS byte
+	beq	3f
+	cmp	r0, #0		@ set C flag, and ...
+	biceq	ip, 0x0400	@ immediate zero value has a special encoding
+	streqh	ip, [r7]	@ that requires the i bit cleared
+#endif
+3:	ldrh	ip, [r7, #2]
+	and	ip, 0x8f00
+	orrcc	ip, r6	@ mask in offset bits 31-24
+	orrcs	ip, r0	@ mask in offset bits 23-16
+	strh	ip, [r7, #2]
+4:	cmp	r4, r5
+	ldrcc	r7, [r4], #4	@ use branch for delay slot
+	bcc	2b
+	bx	lr
+#else
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT
+	and	r0, r6, #255	@ offset bits 23-16
+	mov	r6, r6, lsr #8	@ offset bits 31-24
+#else
+	mov	r0, #0		@ just in case...
+#endif
+	b	3f
+2:	ldr	ip, [r7, r3]
+	bic	ip, ip, #0x000000ff
+	tst	ip, #0x400	@ rotate shift tells us LS or MS byte
+	orrne	ip, ip, r6	@ mask in offset bits 31-24
+	orreq	ip, ip, r0	@ mask in offset bits 23-16
+	str	ip, [r7, r3]
+3:	cmp	r4, r5
+	ldrcc	r7, [r4], #4	@ use branch for delay slot
+	bcc	2b
+	mov	pc, lr
+#endif
+ENDPROC(__fixup_a_pv_table)
+
+ENTRY(fixup_pv_table)
+	stmfd	sp!, {r4 - r7, lr}
+	ldr	r2, 2f			@ get address of __pv_phys_offset
+	mov	r3, #0			@ no offset
+	mov	r4, r0			@ r0 = table start
+	add	r5, r0, r1		@ r1 = table size
+	ldr	r6, [r2, #4]		@ get __pv_offset
+	bl	__fixup_a_pv_table
+	ldmfd	sp!, {r4 - r7, pc}
+ENDPROC(fixup_pv_table)
+
+	.align
+2:	.long	__pv_phys_offset
+
+	.data
+	.globl	__pv_phys_offset
+	.type	__pv_phys_offset, %object
+__pv_phys_offset:
+	.long	0
+	.size	__pv_phys_offset, . - __pv_phys_offset
+__pv_offset:
+	.long	0
+#endif
+
 #include "head-common.S"
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 28536e352de..3535d3793e6 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -179,14 +179,21 @@ int __init arch_probe_nr_irqs(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static void route_irq(struct irq_desc *desc, unsigned int irq, unsigned int cpu)
+static bool migrate_one_irq(struct irq_data *d)
 {
-	pr_debug("IRQ%u: moving from cpu%u to cpu%u\n", irq, desc->irq_data.node, cpu);
+	unsigned int cpu = cpumask_any_and(d->affinity, cpu_online_mask);
+	bool ret = false;
 
-	raw_spin_lock_irq(&desc->lock);
-	desc->irq_data.chip->irq_set_affinity(&desc->irq_data,
-					      cpumask_of(cpu), false);
-	raw_spin_unlock_irq(&desc->lock);
+	if (cpu >= nr_cpu_ids) {
+		cpu = cpumask_any(cpu_online_mask);
+		ret = true;
+	}
+
+	pr_debug("IRQ%u: moving from cpu%u to cpu%u\n", d->irq, d->node, cpu);
+
+	d->chip->irq_set_affinity(d, cpumask_of(cpu), true);
+
+	return ret;
 }
 
 /*
@@ -198,25 +205,30 @@ void migrate_irqs(void)
 {
 	unsigned int i, cpu = smp_processor_id();
 	struct irq_desc *desc;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
 	for_each_irq_desc(i, desc) {
 		struct irq_data *d = &desc->irq_data;
+		bool affinity_broken = false;
 
-		if (d->node == cpu) {
-			unsigned int newcpu = cpumask_any_and(d->affinity,
-							      cpu_online_mask);
-			if (newcpu >= nr_cpu_ids) {
-				if (printk_ratelimit())
-					printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n",
-					       i, cpu);
+		raw_spin_lock(&desc->lock);
+		do {
+			if (desc->action == NULL)
+				break;
 
-				cpumask_setall(d->affinity);
-				newcpu = cpumask_any_and(d->affinity,
-							 cpu_online_mask);
-			}
+			if (d->node != cpu)
+				break;
 
-			route_irq(desc, i, newcpu);
-		}
+			affinity_broken = migrate_one_irq(d);
+		} while (0);
+		raw_spin_unlock(&desc->lock);
+
+		if (affinity_broken && printk_ratelimit())
+			pr_warning("IRQ%u no longer affine to CPU%u\n", i, cpu);
 	}
+
+	local_irq_restore(flags);
 }
 #endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 6d4105e6872..fee7c36349e 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -76,6 +76,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 	for (i = 0; i < relsec->sh_size / sizeof(Elf32_Rel); i++, rel++) {
 		unsigned long loc;
 		Elf32_Sym *sym;
+		const char *symname;
 		s32 offset;
 #ifdef CONFIG_THUMB2_KERNEL
 		u32 upper, lower, sign, j1, j2;
@@ -83,18 +84,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 
 		offset = ELF32_R_SYM(rel->r_info);
 		if (offset < 0 || offset > (symsec->sh_size / sizeof(Elf32_Sym))) {
-			printk(KERN_ERR "%s: bad relocation, section %d reloc %d\n",
+			pr_err("%s: section %u reloc %u: bad relocation sym offset\n",
 				module->name, relindex, i);
 			return -ENOEXEC;
 		}
 
 		sym = ((Elf32_Sym *)symsec->sh_addr) + offset;
+		symname = strtab + sym->st_name;
 
 		if (rel->r_offset < 0 || rel->r_offset > dstsec->sh_size - sizeof(u32)) {
-			printk(KERN_ERR "%s: out of bounds relocation, "
-				"section %d reloc %d offset %d size %d\n",
-				module->name, relindex, i, rel->r_offset,
-				dstsec->sh_size);
+			pr_err("%s: section %u reloc %u sym '%s': out of bounds relocation, offset %d size %u\n",
+			       module->name, relindex, i, symname,
+			       rel->r_offset, dstsec->sh_size);
 			return -ENOEXEC;
 		}
 
@@ -120,10 +121,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			if (offset & 3 ||
 			    offset <= (s32)0xfe000000 ||
 			    offset >= (s32)0x02000000) {
-				printk(KERN_ERR
-				       "%s: relocation out of range, section "
-				       "%d reloc %d sym '%s'\n", module->name,
-				       relindex, i, strtab + sym->st_name);
+				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
+				       module->name, relindex, i, symname,
+				       ELF32_R_TYPE(rel->r_info), loc,
+				       sym->st_value);
 				return -ENOEXEC;
 			}
 
@@ -196,10 +197,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			if (!(offset & 1) ||
 			    offset <= (s32)0xff000000 ||
 			    offset >= (s32)0x01000000) {
-				printk(KERN_ERR
-				       "%s: relocation out of range, section "
-				       "%d reloc %d sym '%s'\n", module->name,
-				       relindex, i, strtab + sym->st_name);
+				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
+				       module->name, relindex, i, symname,
+				       ELF32_R_TYPE(rel->r_info), loc,
+				       sym->st_value);
 				return -ENOEXEC;
 			}
 
@@ -282,12 +283,13 @@ static const Elf_Shdr *find_mod_section(const Elf32_Ehdr *hdr,
 	return NULL;
 }
 
+extern void fixup_pv_table(const void *, unsigned long);
 extern void fixup_smp(const void *, unsigned long);
 
 int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 		    struct module *mod)
 {
-	const Elf_Shdr * __maybe_unused s = NULL;
+	const Elf_Shdr *s = NULL;
 #ifdef CONFIG_ARM_UNWIND
 	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 	const Elf_Shdr *sechdrs_end = sechdrs + hdr->e_shnum;
@@ -332,6 +334,11 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 					         maps[i].txt_sec->sh_addr,
 					         maps[i].txt_sec->sh_size);
 #endif
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
+	s = find_mod_section(hdr, sechdrs, ".pv_table");
+	if (s)
+		fixup_pv_table((void *)s->sh_addr, s->sh_size);
+#endif
 	s = find_mod_section(hdr, sechdrs, ".alt.smp.init");
 	if (s && !is_smp())
 		fixup_smp((void *)s->sh_addr, s->sh_size);
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index c058bfc8532..6fc2d228db5 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -30,7 +30,7 @@
  * enable the interrupt.
  */
 
-#ifdef CONFIG_CPU_V6
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 enum armv6_perf_types {
 	ARMV6_PERFCTR_ICACHE_MISS	    = 0x0,
 	ARMV6_PERFCTR_IBUF_STALL	    = 0x1,
@@ -669,4 +669,4 @@ static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
 	return NULL;
 }
-#endif	/* CONFIG_CPU_V6 */
+#endif	/* CONFIG_CPU_V6 || CONFIG_CPU_V6K */
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index b13e70f63d7..2bf27f364d0 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -26,8 +26,6 @@
 #include <asm/system.h>
 #include <asm/traps.h>
 
-#include "ptrace.h"
-
 #define REG_PC	15
 #define REG_PSR	16
 /*
@@ -184,389 +182,12 @@ put_user_reg(struct task_struct *task, int offset, long data)
 	return ret;
 }
 
-static inline int
-read_u32(struct task_struct *task, unsigned long addr, u32 *res)
-{
-	int ret;
-
-	ret = access_process_vm(task, addr, res, sizeof(*res), 0);
-
-	return ret == sizeof(*res) ? 0 : -EIO;
-}
-
-static inline int
-read_instr(struct task_struct *task, unsigned long addr, u32 *res)
-{
-	int ret;
-
-	if (addr & 1) {
-		u16 val;
-		ret = access_process_vm(task, addr & ~1, &val, sizeof(val), 0);
-		ret = ret == sizeof(val) ? 0 : -EIO;
-		*res = val;
-	} else {
-		u32 val;
-		ret = access_process_vm(task, addr & ~3, &val, sizeof(val), 0);
-		ret = ret == sizeof(val) ? 0 : -EIO;
-		*res = val;
-	}
-	return ret;
-}
-
-/*
- * Get value of register `rn' (in the instruction)
- */
-static unsigned long
-ptrace_getrn(struct task_struct *child, unsigned long insn)
-{
-	unsigned int reg = (insn >> 16) & 15;
-	unsigned long val;
-
-	val = get_user_reg(child, reg);
-	if (reg == 15)
-		val += 8;
-
-	return val;
-}
-
-/*
- * Get value of operand 2 (in an ALU instruction)
- */
-static unsigned long
-ptrace_getaluop2(struct task_struct *child, unsigned long insn)
-{
-	unsigned long val;
-	int shift;
-	int type;
-
-	if (insn & 1 << 25) {
-		val = insn & 255;
-		shift = (insn >> 8) & 15;
-		type = 3;
-	} else {
-		val = get_user_reg (child, insn & 15);
-
-		if (insn & (1 << 4))
-			shift = (int)get_user_reg (child, (insn >> 8) & 15);
-		else
-			shift = (insn >> 7) & 31;
-
-		type = (insn >> 5) & 3;
-	}
-
-	switch (type) {
-	case 0:	val <<= shift;	break;
-	case 1:	val >>= shift;	break;
-	case 2:
-		val = (((signed long)val) >> shift);
-		break;
-	case 3:
- 		val = (val >> shift) | (val << (32 - shift));
-		break;
-	}
-	return val;
-}
-
-/*
- * Get value of operand 2 (in a LDR instruction)
- */
-static unsigned long
-ptrace_getldrop2(struct task_struct *child, unsigned long insn)
-{
-	unsigned long val;
-	int shift;
-	int type;
-
-	val = get_user_reg(child, insn & 15);
-	shift = (insn >> 7) & 31;
-	type = (insn >> 5) & 3;
-
-	switch (type) {
-	case 0:	val <<= shift;	break;
-	case 1:	val >>= shift;	break;
-	case 2:
-		val = (((signed long)val) >> shift);
-		break;
-	case 3:
- 		val = (val >> shift) | (val << (32 - shift));
-		break;
-	}
-	return val;
-}
-
-#define OP_MASK	0x01e00000
-#define OP_AND	0x00000000
-#define OP_EOR	0x00200000
-#define OP_SUB	0x00400000
-#define OP_RSB	0x00600000
-#define OP_ADD	0x00800000
-#define OP_ADC	0x00a00000