1 files changed, 40 insertions, 0 deletions
diff --git a/drivers/gpu/drm/radeon/ObjectID.h b/drivers/gpu/drm/radeon/ObjectID.h
index ca4b038050d..06192698bd9 100644
--- a/drivers/gpu/drm/radeon/ObjectID.h
+++ b/drivers/gpu/drm/radeon/ObjectID.h
@@ -69,6 +69,8 @@
 #define ENCODER_OBJECT_ID_ALMOND                  0x22
 #define ENCODER_OBJECT_ID_TRAVIS                  0x23
 #define ENCODER_OBJECT_ID_NUTMEG                  0x22
+#define ENCODER_OBJECT_ID_HDMI_ANX9805            0x26
+
 /* Kaleidoscope (KLDSCP) Class Display Hardware (internal) */
 #define ENCODER_OBJECT_ID_INTERNAL_KLDSCP_TMDS1   0x13
 #define ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1    0x14
@@ -86,6 +88,8 @@
 #define ENCODER_OBJECT_ID_INTERNAL_UNIPHY1        0x20
 #define ENCODER_OBJECT_ID_INTERNAL_UNIPHY2        0x21
 #define ENCODER_OBJECT_ID_INTERNAL_VCE            0x24
+#define ENCODER_OBJECT_ID_INTERNAL_UNIPHY3        0x25
+#define ENCODER_OBJECT_ID_INTERNAL_AMCLK          0x27
 
 #define ENCODER_OBJECT_ID_GENERAL_EXTERNAL_DVO    0xFF
 
@@ -364,6 +368,14 @@
                                                  GRAPH_OBJECT_ENUM_ID2 << ENUM_ID_SHIFT |\
                                                  ENCODER_OBJECT_ID_INTERNAL_UNIPHY2 << OBJECT_ID_SHIFT)
 
+#define ENCODER_INTERNAL_UNIPHY3_ENUM_ID1         ( GRAPH_OBJECT_TYPE_ENCODER << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
+                                                 ENCODER_OBJECT_ID_INTERNAL_UNIPHY3 << OBJECT_ID_SHIFT)
+
+#define ENCODER_INTERNAL_UNIPHY3_ENUM_ID2         ( GRAPH_OBJECT_TYPE_ENCODER << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID2 << ENUM_ID_SHIFT |\
+                                                 ENCODER_OBJECT_ID_INTERNAL_UNIPHY3 << OBJECT_ID_SHIFT)
+
 #define ENCODER_GENERAL_EXTERNAL_DVO_ENUM_ID1    ( GRAPH_OBJECT_TYPE_ENCODER << OBJECT_TYPE_SHIFT |\
                                                   GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
                                                   ENCODER_OBJECT_ID_GENERAL_EXTERNAL_DVO << OBJECT_ID_SHIFT)
@@ -392,6 +404,10 @@
                                                   GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
                                                   ENCODER_OBJECT_ID_INTERNAL_VCE << OBJECT_ID_SHIFT)
 
+#define ENCODER_HDMI_ANX9805_ENUM_ID1            ( GRAPH_OBJECT_TYPE_ENCODER << OBJECT_TYPE_SHIFT |\
+                                                  GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
+                                                  ENCODER_OBJECT_ID_HDMI_ANX9805 << OBJECT_ID_SHIFT)
+
 /****************************************************/
 /* Connector Object ID definition - Shared with BIOS */
 /****************************************************/
@@ -461,6 +477,14 @@
                                                  GRAPH_OBJECT_ENUM_ID4 << ENUM_ID_SHIFT |\
                                                  CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_D << OBJECT_ID_SHIFT)
 
+#define CONNECTOR_SINGLE_LINK_DVI_D_ENUM_ID5   ( GRAPH_OBJECT_TYPE_CONNECTOR << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID5 << ENUM_ID_SHIFT |\
+                                                 CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_D << OBJECT_ID_SHIFT)
+
+#define CONNECTOR_SINGLE_LINK_DVI_D_ENUM_ID6   ( GRAPH_OBJECT_TYPE_CONNECTOR << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID6 << ENUM_ID_SHIFT |\
+                                                 CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_D << OBJECT_ID_SHIFT)
+
 #define CONNECTOR_DUAL_LINK_DVI_D_ENUM_ID1     ( GRAPH_OBJECT_TYPE_CONNECTOR << OBJECT_TYPE_SHIFT |\
                                                  GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
                                                  CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_D << OBJECT_ID_SHIFT)
@@ -473,6 +497,10 @@
                                                  GRAPH_OBJECT_ENUM_ID3 << ENUM_ID_SHIFT |\
                                                  CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_D << OBJECT_ID_SHIFT)
 
+#define CONNECTOR_DUAL_LINK_DVI_D_ENUM_ID4     ( GRAPH_OBJECT_TYPE_CONNECTOR << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID4 << ENUM_ID_SHIFT |\
+                                                 CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_D << OBJECT_ID_SHIFT)
+
 #define CONNECTOR_VGA_ENUM_ID1                 ( GRAPH_OBJECT_TYPE_CONNECTOR << OBJECT_TYPE_SHIFT |\
                                                  GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
                                                  CONNECTOR_OBJECT_ID_VGA << OBJECT_ID_SHIFT)
@@ -541,6 +569,18 @@
                                                  GRAPH_OBJECT_ENUM_ID3 << ENUM_ID_SHIFT |\
                                                  CONNECTOR_OBJECT_ID_HDMI_TYPE_A << OBJECT_ID_SHIFT)
 
+#define CONNECTOR_HDMI_TYPE_A_ENUM_ID4         ( GRAPH_OBJECT_TYPE_CONNECTOR << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID4 << ENUM_ID_SHIFT |\
+                                                 CONNECTOR_OBJECT_ID_HDMI_TYPE_A << OBJECT_ID_SHIFT)
+
+#define CONNECTOR_HDMI_TYPE_A_ENUM_ID5         ( GRAPH_OBJECT_TYPE_CONNECTOR << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID5 << ENUM_ID_SHIFT |\
+                                                 CONNECTOR_OBJECT_ID_HDMI_TYPE_A << OBJECT_ID_SHIFT)
+
+#define CONNECTOR_HDMI_TYPE_A_ENUM_ID6         ( GRAPH_OBJECT_TYPE_CONNECTOR << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID6 << ENUM_ID_SHIFT |\
+                                                 CONNECTOR_OBJECT_ID_HDMI_TYPE_A << OBJECT_ID_SHIFT)
+
 #define CONNECTOR_HDMI_TYPE_B_ENUM_ID1         ( GRAPH_OBJECT_TYPE_CONNECTOR << OBJECT_TYPE_SHIFT |\
                                                  GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
                                                  CONNECTOR_OBJECT_ID_HDMI_TYPE_B << OBJECT_ID_SHIFT)
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 6550db3aa5c..f5a35760198 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -1,3 +1,39 @@
-include include/asm-generic/Kbuild.asm
 
-header-y += hwcap.h
+
+generic-y += auxvec.h
+generic-y += bitsperlong.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += exec.h
+generic-y += hash.h
+generic-y += ioctl.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += msgbuf.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += poll.h
+generic-y += preempt.h
+generic-y += resource.h
+generic-y += rwsem.h
+generic-y += sections.h
+generic-y += segment.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += shmbuf.h
+generic-y += siginfo.h
+generic-y += simd.h
+generic-y += sizes.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += timex.h
+generic-y += trace_clock.h
+generic-y += unaligned.h
diff --git a/arch/arm/include/asm/a.out-core.h b/arch/arm/include/asm/a.out-core.h
deleted file mode 100644
index 93d04acaa31..00000000000
--- a/arch/arm/include/asm/a.out-core.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* a.out coredump register dumper
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#ifndef _ASM_A_OUT_CORE_H
-#define _ASM_A_OUT_CORE_H
-
-#ifdef __KERNEL__
-
-#include <linux/user.h>
-#include <linux/elfcore.h>
-
-/*
- * fill in the user structure for an a.out core dump
- */
-static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
-{
-	struct task_struct *tsk = current;
-
-	dump->magic = CMAGIC;
-	dump->start_code = tsk->mm->start_code;
-	dump->start_stack = regs->ARM_sp & ~(PAGE_SIZE - 1);
-
-	dump->u_tsize = (tsk->mm->end_code - tsk->mm->start_code) >> PAGE_SHIFT;
-	dump->u_dsize = (tsk->mm->brk - tsk->mm->start_data + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	dump->u_ssize = 0;
-
-	dump->u_debugreg[0] = tsk->thread.debug.bp[0].address;
-	dump->u_debugreg[1] = tsk->thread.debug.bp[1].address;
-	dump->u_debugreg[2] = tsk->thread.debug.bp[0].insn.arm;
-	dump->u_debugreg[3] = tsk->thread.debug.bp[1].insn.arm;
-	dump->u_debugreg[4] = tsk->thread.debug.nsaved;
-
-	if (dump->start_stack < 0x04000000)
-		dump->u_ssize = (0x04000000 - dump->start_stack) >> PAGE_SHIFT;
-
-	dump->regs = *regs;
-	dump->u_fpvalid = dump_fpu (regs, &dump->u_fp);
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_A_OUT_CORE_H */
diff --git a/arch/arm/include/asm/a.out.h b/arch/arm/include/asm/a.out.h
deleted file mode 100644
index 083894b2e3b..00000000000
--- a/arch/arm/include/asm/a.out.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef __ARM_A_OUT_H__
-#define __ARM_A_OUT_H__
-
-#include <linux/personality.h>
-#include <linux/types.h>
-
-struct exec
-{
-  __u32 a_info;		/* Use macros N_MAGIC, etc for access */
-  __u32 a_text;		/* length of text, in bytes */
-  __u32 a_data;		/* length of data, in bytes */
-  __u32 a_bss;		/* length of uninitialized data area for file, in bytes */
-  __u32 a_syms;		/* length of symbol table data in file, in bytes */
-  __u32 a_entry;	/* start address */
-  __u32 a_trsize;	/* length of relocation info for text, in bytes */
-  __u32 a_drsize;	/* length of relocation info for data, in bytes */
-};
-
-/*
- * This is always the same
- */
-#define N_TXTADDR(a)	(0x00008000)
-
-#define N_TRSIZE(a)	((a).a_trsize)
-#define N_DRSIZE(a)	((a).a_drsize)
-#define N_SYMSIZE(a)	((a).a_syms)
-
-#define M_ARM 103
-
-#ifndef LIBRARY_START_TEXT
-#define LIBRARY_START_TEXT	(0x00c00000)
-#endif
-
-#endif /* __A_OUT_GNU_H__ */
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
new file mode 100644
index 00000000000..0704e0cf557
--- /dev/null
+++ b/arch/arm/include/asm/arch_timer.h
@@ -0,0 +1,129 @@
+#ifndef __ASMARM_ARCH_TIMER_H
+#define __ASMARM_ARCH_TIMER_H
+
+#include <asm/barrier.h>
+#include <asm/errno.h>
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/types.h>
+
+#include <clocksource/arm_arch_timer.h>
+
+#ifdef CONFIG_ARM_ARCH_TIMER
+int arch_timer_arch_init(void);
+
+/*
+ * These register accessors are marked inline so the compiler can
+ * nicely work out which register we want, and chuck away the rest of
+ * the code. At least it does so with a recent GCC (4.6.3).
+ */
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
+{
+	if (access == ARCH_TIMER_PHYS_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mcr p15, 0, %0, c14, c2, 1" : : "r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
+			break;
+		}
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mcr p15, 0, %0, c14, c3, 0" : : "r" (val));
+			break;
+		}
+	}
+
+	isb();
+}
+
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
+{
+	u32 val = 0;
+
+	if (access == ARCH_TIMER_PHYS_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mrc p15, 0, %0, c14, c2, 1" : "=r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
+			break;
+		}
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
+			break;
+		case ARCH_TIMER_REG_TVAL:
+			asm volatile("mrc p15, 0, %0, c14, c3, 0" : "=r" (val));
+			break;
+		}
+	}
+
+	return val;
+}
+
+static inline u32 arch_timer_get_cntfrq(void)
+{
+	u32 val;
+	asm volatile("mrc p15, 0, %0, c14, c0, 0" : "=r" (val));
+	return val;
+}
+
+static inline u64 arch_counter_get_cntvct(void)
+{
+	u64 cval;
+
+	isb();
+	asm volatile("mrrc p15, 1, %Q0, %R0, c14" : "=r" (cval));
+	return cval;
+}
+
+static inline u32 arch_timer_get_cntkctl(void)
+{
+	u32 cntkctl;
+	asm volatile("mrc p15, 0, %0, c14, c1, 0" : "=r" (cntkctl));
+	return cntkctl;
+}
+
+static inline void arch_timer_set_cntkctl(u32 cntkctl)
+{
+	asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl));
+}
+
+static inline void arch_counter_set_user_access(void)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+
+	/* Disable user access to both physical/virtual counters/timers */
+	/* Also disable virtual event stream */
+	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
+			| ARCH_TIMER_USR_VT_ACCESS_EN
+			| ARCH_TIMER_VIRT_EVT_EN
+			| ARCH_TIMER_USR_VCT_ACCESS_EN
+			| ARCH_TIMER_USR_PCT_ACCESS_EN);
+	arch_timer_set_cntkctl(cntkctl);
+}
+
+static inline void arch_timer_evtstrm_enable(int divider)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+	cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
+	/* Set the divider and enable virtual event stream */
+	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+			| ARCH_TIMER_VIRT_EVT_EN;
+	arch_timer_set_cntkctl(cntkctl);
+	elf_hwcap |= HWCAP_EVTSTRM;
+}
+
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 062b58c029a..57f0584e8d9 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -13,18 +13,26 @@
  *  Do not include any C declarations in this file - it is included by
  *  assembler source.
  */
+#ifndef __ASM_ASSEMBLER_H__
+#define __ASM_ASSEMBLER_H__
+
 #ifndef __ASSEMBLY__
 #error "Only include this from assembly code"
 #endif
 
 #include <asm/ptrace.h>
+#include <asm/domain.h>
+#include <asm/opcodes-virt.h>
+#include <asm/asm-offsets.h>
+
+#define IOMEM(x)	(x)
 
 /*
  * Endian independent macros for shifting bytes within registers.
  */
 #ifndef __ARMEB__
-#define pull            lsr
-#define push            lsl
+#define lspull          lsr
+#define lspush          lsl
 #define get_byte_0      lsl #0
 #define get_byte_1	lsr #8
 #define get_byte_2	lsr #16
@@ -34,8 +42,8 @@
 #define put_byte_2	lsl #16
 #define put_byte_3	lsl #24
 #else
-#define pull            lsl
-#define push            lsr
+#define lspull          lsl
+#define lspush          lsr
 #define get_byte_0	lsr #24
 #define get_byte_1	lsr #16
 #define get_byte_2	lsr #8
@@ -46,6 +54,13 @@
 #define put_byte_3      lsl #0
 #endif
 
+/* Select code for any configuration running in BE8 mode */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define ARM_BE8(code...) code
+#else
+#define ARM_BE8(code...)
+#endif
+
 /*
  * Data preload for architectures that support it
  */
@@ -129,16 +144,29 @@
  * assumes FIQs are enabled, and that the processor is in SVC mode.
  */
 	.macro	save_and_disable_irqs, oldcpsr
+#ifdef CONFIG_CPU_V7M
+	mrs	\oldcpsr, primask
+#else
 	mrs	\oldcpsr, cpsr
+#endif
 	disable_irq
 	.endm
 
+	.macro	save_and_disable_irqs_notrace, oldcpsr
+	mrs	\oldcpsr, cpsr
+	disable_irq_notrace
+	.endm
+
 /*
  * Restore interrupt state previously stored in a register.  We don't
  * guarantee that this will preserve the flags.
  */
 	.macro	restore_irqs_notrace, oldcpsr
+#ifdef CONFIG_CPU_V7M
+	msr	primask, \oldcpsr
+#else
 	msr	cpsr_c, \oldcpsr
+#endif
 	.endm
 
 	.macro restore_irqs, oldcpsr
@@ -147,6 +175,47 @@
 	restore_irqs_notrace \oldcpsr
 	.endm
 
+/*
+ * Get current thread_info.
+ */
+	.macro	get_thread_info, rd
+ ARM(	mov	\rd, sp, lsr #13	)
+ THUMB(	mov	\rd, sp			)
+ THUMB(	lsr	\rd, \rd, #13		)
+	mov	\rd, \rd, lsl #13
+	.endm
+
+/*
+ * Increment/decrement the preempt count.
+ */
+#ifdef CONFIG_PREEMPT_COUNT
+	.macro	inc_preempt_count, ti, tmp
+	ldr	\tmp, [\ti, #TI_PREEMPT]	@ get preempt count
+	add	\tmp, \tmp, #1			@ increment it
+	str	\tmp, [\ti, #TI_PREEMPT]
+	.endm
+
+	.macro	dec_preempt_count, ti, tmp
+	ldr	\tmp, [\ti, #TI_PREEMPT]	@ get preempt count
+	sub	\tmp, \tmp, #1			@ decrement it
+	str	\tmp, [\ti, #TI_PREEMPT]
+	.endm
+
+	.macro	dec_preempt_count_ti, ti, tmp
+	get_thread_info \ti
+	dec_preempt_count \ti, \tmp
+	.endm
+#else
+	.macro	inc_preempt_count, ti, tmp
+	.endm
+
+	.macro	dec_preempt_count, ti, tmp
+	.endm
+
+	.macro	dec_preempt_count_ti, ti, tmp
+	.endm
+#endif
+
 #define USER(x...)				\
 9999:	x;					\
 	.pushsection __ex_table,"a";		\
@@ -157,16 +226,24 @@
 #ifdef CONFIG_SMP
 #define ALT_SMP(instr...)					\
 9998:	instr
+/*
+ * Note: if you get assembler errors from ALT_UP() when building with
+ * CONFIG_THUMB2_KERNEL, you almost certainly need to use
+ * ALT_SMP( W(instr) ... )
+ */
 #define ALT_UP(instr...)					\
 	.pushsection ".alt.smp.init", "a"			;\
 	.long	9998b						;\
-	instr							;\
+9997:	instr							;\
+	.if . - 9997b != 4					;\
+		.error "ALT_UP() content must assemble to exactly 4 bytes";\
+	.endif							;\
 	.popsection
 #define ALT_UP_B(label)					\
 	.equ	up_b_offset, label - 9998b			;\
 	.pushsection ".alt.smp.init", "a"			;\
 	.long	9998b						;\
-	b	. + up_b_offset					;\
+	W(b)	. + up_b_offset					;\
 	.popsection
 #else
 #define ALT_SMP(instr...)
@@ -175,22 +252,48 @@
 #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
+	.macro	smp_dmb mode
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
-	ALT_SMP(dmb)
+	.ifeqs "\mode","arm"
+	ALT_SMP(dmb	ish)
+	.else
+	ALT_SMP(W(dmb)	ish)
+	.endif
 #elif __LINUX_ARM_ARCH__ == 6
 	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb
 #else
 #error Incompatible SMP platform
 #endif
+	.ifeqs "\mode","arm"
 	ALT_UP(nop)
+	.else
+	ALT_UP(W(nop))
+	.endif
 #endif
 	.endm
 
-#ifdef CONFIG_THUMB2_KERNEL
+#if defined(CONFIG_CPU_V7M)
+	/*
+	 * setmode is used to assert to be in svc mode during boot. For v7-M
+	 * this is done in __v7m_setup, so setmode can be empty here.
+	 */
+	.macro	setmode, mode, reg
+	.endm
+#elif defined(CONFIG_THUMB2_KERNEL)
 	.macro	setmode, mode, reg
 	mov	\reg, #\mode
 	msr	cpsr_c, \reg
@@ -202,16 +305,48 @@
 #endif
 
 /*
+ * Helper macro to enter SVC mode cleanly and mask interrupts. reg is
+ * a scratch register for the macro to overwrite.
+ *
+ * This macro is intended for forcing the CPU into SVC mode at boot time.
+ * you cannot return to the original mode.
+ */
+.macro safe_svcmode_maskall reg:req
+#if __LINUX_ARM_ARCH__ >= 6 && !defined(CONFIG_CPU_V7M)
+	mrs	\reg , cpsr
+	eor	\reg, \reg, #HYP_MODE
+	tst	\reg, #MODE_MASK
+	bic	\reg , \reg , #MODE_MASK
+	orr	\reg , \reg , #PSR_I_BIT | PSR_F_BIT | SVC_MODE
+THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
+	bne	1f
+	orr	\reg, \reg, #PSR_A_BIT
+	adr	lr, BSYM(2f)
+	msr	spsr_cxsf, \reg
+	__MSR_ELR_HYP(14)
+	__ERET
+1:	msr	cpsr_c, \reg
+2:
+#else
+/*
+ * workaround for possibly broken pre-v6 hardware
+ * (akita, Sharp Zaurus C-1000, PXA270-based)
+ */
+	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, \reg
+#endif
+.endm
+
+/*
  * STRT/LDRT access macros with ARM and Thumb-2 variants
  */
 #ifdef CONFIG_THUMB2_KERNEL
 
-	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort
+	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=TUSER()
 9999:
 	.if	\inc == 1
-	\instr\cond\()bt \reg, [\ptr, #\off]
+	\instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
 	.elseif	\inc == 4
-	\instr\cond\()t \reg, [\ptr, #\off]
+	\instr\cond\()\t\().w \reg, [\ptr, #\off]
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -238,7 +373,7 @@
 	@ Slightly optimised to avoid incrementing the pointer twice
 	usraccoff \instr, \reg, \ptr, \inc, 0, \cond, \abort
 	.if	\rept == 2
-	usraccoff \instr, \reg, \ptr, \inc, 4, \cond, \abort
+	usraccoff \instr, \reg, \ptr, \inc, \inc, \cond, \abort
 	.endif
 
 	add\cond \ptr, #\rept * \inc
@@ -246,13 +381,13 @@
 
 #else	/* !CONFIG_THUMB2_KERNEL */
 
-	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort
+	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort, t=TUSER()
 	.rept	\rept
 9999:
 	.if	\inc == 1
-	\instr\cond\()bt \reg, [\ptr], #\inc
+	\instr\cond\()b\()\t \reg, [\ptr], #\inc
 	.elseif	\inc == 4
-	\instr\cond\()t \reg, [\ptr], #\inc
+	\instr\cond\()\t \reg, [\ptr], #\inc
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -273,3 +408,21 @@
 	.macro	ldrusr, reg, ptr, inc, cond=al, rept=1, abort=9001f
 	usracc	ldr, \reg, \ptr, \inc, \cond, \rept, \abort
 	.endm
+
+/* Utility macro for declaring string literals */
+	.macro	string name:req, string
+	.type \name , #object
+\name:
+	.asciz "\string"
+	.size \name , . - \name
+	.endm
+
+	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
+#ifndef CONFIG_CPU_USE_DOMAINS
+	adds	\tmp, \addr, #\size - 1
+	sbcccs	\tmp, \tmp, \limit
+	bcs	\bad
+#endif
+	.endm
+
+#endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 7e79503ab89..3040359094d 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -12,8 +12,11 @@
 #define __ASM_ARM_ATOMIC_H
 
 #include <linux/compiler.h>
+#include <linux/prefetch.h>
 #include <linux/types.h>
-#include <asm/system.h>
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)	{ (i) }
 
@@ -39,6 +42,7 @@ static inline void atomic_add(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic_add\n"
 "1:	ldrex	%0, [%3]\n"
 "	add	%0, %0, %4\n"
@@ -56,6 +60,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	int result;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic_add_return\n"
 "1:	ldrex	%0, [%3]\n"
@@ -77,6 +82,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic_sub\n"
 "1:	ldrex	%0, [%3]\n"
 "	sub	%0, %0, %4\n"
@@ -94,6 +100,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	int result;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic_sub_return\n"
 "1:	ldrex	%0, [%3]\n"
@@ -112,9 +119,11 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 
 static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 {
-	unsigned long oldval, res;
+	int oldval;
+	unsigned long res;
 
 	smp_mb();
+	prefetchw(&ptr->counter);
 
 	do {
 		__asm__ __volatile__("@ atomic_cmpxchg\n"
@@ -132,19 +141,31 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 	return oldval;
 }
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
-	unsigned long tmp, tmp2;
+	int oldval, newval;
+	unsigned long tmp;
 
-	__asm__ __volatile__("@ atomic_clear_mask\n"
-"1:	ldrex	%0, [%3]\n"
-"	bic	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr)
-	: "r" (addr), "Ir" (mask)
+	smp_mb();
+	prefetchw(&v->counter);
+
+	__asm__ __volatile__ ("@ atomic_add_unless\n"
+"1:	ldrex	%0, [%4]\n"
+"	teq	%0, %5\n"
+"	beq	2f\n"
+"	add	%1, %0, %6\n"
+"	strex	%2, %1, [%4]\n"
+"	teq	%2, #0\n"
+"	bne	1b\n"
+"2:"
+	: "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter)
+	: "r" (&v->counter), "r" (u), "r" (a)
 	: "cc");
+
+	if (oldval != u)
+		smp_mb();
+
+	return oldval;
 }
 
 #else /* ARM_ARCH_6 */
@@ -195,29 +216,19 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags);
-	*addr &= ~mask;
-	raw_local_irq_restore(flags);
-}
-
-#endif /* __LINUX_ARM_ARCH__ */
-
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 
 	c = atomic_read(v);
 	while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
 		c = old;
-	return c != u;
+	return c;
 }
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+
+#endif /* __LINUX_ARM_ARCH__ */
+
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 #define atomic_inc(v)		atomic_add(1, v)
 #define atomic_dec(v)		atomic_sub(1, v)
@@ -230,21 +241,39 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 
 #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
 
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
-	u64 __aligned(8) counter;
+	long long counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(i) { (i) }
 
-static inline u64 atomic64_read(atomic64_t *v)
+#ifdef CONFIG_ARM_LPAE
+static inline long long atomic64_read(const atomic64_t *v)
 {
-	u64 result;
+	long long result;
+
+	__asm__ __volatile__("@ atomic64_read\n"
+"	ldrd	%0, %H0, [%1]"
+	: "=&r" (result)
+	: "r" (&v->counter), "Qo" (v->counter)
+	);
+
+	return result;
+}
+
+static inline void atomic64_set(atomic64_t *v, long long i)
+{
+	__asm__ __volatile__("@ atomic64_set\n"
+"	strd	%2, %H2, [%1]"
+	: "=Qo" (v->counter)
+	: "r" (&v->counter), "r" (i)
+	);
+}
+#else
+static inline long long atomic64_read(const atomic64_t *v)
+{
+	long long result;
 
 	__asm__ __volatile__("@ atomic64_read\n"
 "	ldrexd	%0, %H0, [%1]"
@@ -255,10 +284,11 @@ static inline u64 atomic64_read(atomic64_t *v)
 	return result;
 }
 
-static inline void atomic64_set(atomic64_t *v, u64 i)
+static inline void atomic64_set(atomic64_t *v, long long i)
 {
-	u64 tmp;
+	long long tmp;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_set\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
 "	strexd	%0, %3, %H3, [%2]\n"
@@ -268,16 +298,18 @@ static inline void atomic64_set(atomic64_t *v, u64 i)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }
+#endif
 
-static inline void atomic64_add(u64 i, atomic64_t *v)
+static inline void atomic64_add(long long i, atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_add\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%0, %0, %4\n"
-"	adc	%H0, %H0, %H4\n"
+"	adds	%Q0, %Q0, %Q4\n"
+"	adc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -286,17 +318,18 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
 	: "cc");
 }
 
-static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic64_add_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%0, %0, %4\n"
-"	adc	%H0, %H0, %H4\n"
+"	adds	%Q0, %Q0, %Q4\n"
+"	adc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -309,15 +342,16 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
 	return result;
 }
 
-static inline void atomic64_sub(u64 i, atomic64_t *v)
+static inline void atomic64_sub(long long i, atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_sub\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, %4\n"
-"	sbc	%H0, %H0, %H4\n"
+"	subs	%Q0, %Q0, %Q4\n"
+"	sbc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -326,17 +360,18 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
 	: "cc");
 }
 
-static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
+static inline long long atomic64_sub_return(long long i, atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic64_sub_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, %4\n"
-"	sbc	%H0, %H0, %H4\n"
+"	subs	%Q0, %Q0, %Q4\n"
+"	sbc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -349,12 +384,14 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
 	return result;
 }
 
-static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
+static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
+					long long new)
 {
-	u64 oldval;
+	long long oldval;
 	unsigned long res;
 
 	smp_mb();
+	prefetchw(&ptr->counter);
 
 	do {
 		__asm__ __volatile__("@ atomic64_cmpxchg\n"
@@ -373,12 +410,13 @@ static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
 	return oldval;
 }
 
-static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
+static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
 	smp_mb();
+	prefetchw(&ptr->counter);
 
 	__asm__ __volatile__("@ atomic64_xchg\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
@@ -394,18 +432,19 @@ static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
 	return result;
 }
 
-static inline u64 atomic64_dec_if_positive(atomic64_t *v)
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, #1\n"
-"	sbc	%H0, %H0, #0\n"
-"	teq	%H0, #0\n"
+"	subs	%Q0, %Q0, #1\n"
+"	sbc	%R0, %R0, #0\n"
+"	teq	%R0, #0\n"
 "	bmi	2f\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
@@ -420,13 +459,14 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v)
 	return result;
 }
 
-static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
+static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
-	u64 val;
+	long long val;
 	unsigned long tmp;
 	int ret = 1;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic64_add_unless\n"
 "1:	ldrexd	%0, %H0, [%4]\n"
@@ -434,8 +474,8 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
 "	teqeq	%H0, %H5\n"
 "	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%0, %0, %6\n"
-"	adc	%H0, %H0, %H6\n"
+"	adds	%Q0, %Q0, %Q6\n"
+"	adc	%R0, %R0, %R6\n"
 "	strexd	%2, %0, %H0, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
@@ -460,9 +500,6 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
 
-#else /* !CONFIG_GENERIC_ATOMIC64 */
-#include <asm-generic/atomic64.h>
-#endif
-#include <asm-generic/atomic-long.h>
+#endif /* !CONFIG_GENERIC_ATOMIC64 */
 #endif
 #endif
diff --git a/arch/arm/include/asm/auxvec.h b/arch/arm/include/asm/auxvec.h
deleted file mode 100644
index c0536f6b29a..00000000000
--- a/arch/arm/include/asm/auxvec.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __ASMARM_AUXVEC_H
-#define __ASMARM_AUXVEC_H
-
-#endif
diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h
new file mode 100644
index 00000000000..1714800fa11
--- /dev/null
+++ b/arch/arm/include/asm/bL_switcher.h
@@ -0,0 +1,77 @@
+/*
+ * arch/arm/include/asm/bL_switcher.h
+ *
+ * Created by:  Nicolas Pitre, April 2012
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * 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_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+			 bL_switch_completion_handler completer,
+			 void *completer_cookie);
+static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
+{
+	return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL);
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE	0
+#define BL_NOTIFY_POST_ENABLE	1
+#define BL_NOTIFY_PRE_DISABLE	2
+#define BL_NOTIFY_POST_DISABLE	3
+
+#ifdef CONFIG_BL_SWITCHER
+
+int bL_switcher_register_notifier(struct notifier_block *nb);
+int bL_switcher_unregister_notifier(struct notifier_block *nb);
+
+/*
+ * Use these functions to temporarily prevent enabling/disabling of
+ * the switcher.
+ * bL_switcher_get_enabled() returns true if the switcher is currently
+ * enabled.  Each call to bL_switcher_get_enabled() must be followed
+ * by a call to bL_switcher_put_enabled().  These functions are not
+ * recursive.
+ */
+bool bL_switcher_get_enabled(void);
+void bL_switcher_put_enabled(void);
+
+int bL_switcher_trace_trigger(void);
+int bL_switcher_get_logical_index(u32 mpidr);
+
+#else
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+#endif /* CONFIG_BL_SWITCHER */
+
+#endif
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
new file mode 100644
index 00000000000..c6a3e73a6e2
--- /dev/null
+++ b/arch/arm/include/asm/barrier.h
@@ -0,0 +1,86 @@
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+#include <asm/outercache.h>
+
+#define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");
+
+#if __LINUX_ARM_ARCH__ >= 7 ||		\
+	(__LINUX_ARM_ARCH__ == 6 && defined(CONFIG_CPU_32v6K))
+#define sev()	__asm__ __volatile__ ("sev" : : : "memory")
+#define wfe()	__asm__ __volatile__ ("wfe" : : : "memory")
+#define wfi()	__asm__ __volatile__ ("wfi" : : : "memory")
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 7
+#define isb(option) __asm__ __volatile__ ("isb " #option : : : "memory")
+#define dsb(option) __asm__ __volatile__ ("dsb " #option : : : "memory")
+#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
+#elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+				    : : "r" (0) : "memory")
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+				    : : "r" (0) : "memory")
+#define dmb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
+				    : : "r" (0) : "memory")
+#elif defined(CONFIG_CPU_FA526)
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+				    : : "r" (0) : "memory")
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+				    : : "r" (0) : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
+#else
+#define isb(x) __asm__ __volatile__ ("" : : : "memory")
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+				    : : "r" (0) : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
+#endif
+
+#ifdef CONFIG_ARCH_HAS_BARRIERS
+#include <mach/barriers.h>
+#elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
+#define mb()		do { dsb(); outer_sync(); } while (0)
+#define rmb()		dsb()
+#define wmb()		do { dsb(st); outer_sync(); } while (0)
+#else
+#define mb()		barrier()
+#define rmb()		barrier()
+#define wmb()		barrier()
+#endif
+
+#ifndef CONFIG_SMP
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#else
+#define smp_mb()	dmb(ish)
+#define smp_rmb()	smp_mb()
+#define smp_wmb()	dmb(ishst)
+#endif
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
+#define read_barrier_depends()		do { } while(0)
+#define smp_read_barrier_depends()	do { } while(0)
+
+#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
+
+#define smp_mb__before_atomic()	smp_mb()
+#define smp_mb__after_atomic()	smp_mb()
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_BARRIER_H */
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 338ff19ae44..56380995f4c 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -24,10 +24,8 @@
 #endif
 
 #include <linux/compiler.h>
-#include <asm/system.h>
-
-#define smp_mb__before_clear_bit()	mb()
-#define smp_mb__after_clear_bit()	mb()
+#include <linux/irqflags.h>
+#include <asm/barrier.h>
 
 /*
  * These functions are the basis of our bit ops.
@@ -149,14 +147,18 @@ ____atomic_test_and_change_bit(unsigned int bit, volatile unsigned long *p)
  */
 
 /*
+ * Native endian assembly bitops.  nr = 0 -> word 0 bit 0.
+ */
+extern void _set_bit(int nr, volatile unsigned long * p);
+extern void _clear_bit(int nr, volatile unsigned long * p);
+extern void _change_bit(int nr, volatile unsigned long * p);
+extern int _test_and_set_bit(int nr, volatile unsigned long * p);
+extern int _test_and_clear_bit(int nr, volatile unsigned long * p);
+extern int _test_and_change_bit(int nr, volatile unsigned long * p);
+
+/*
  * Little endian assembly bitops.  nr = 0 -> byte 0 bit 0.
  */
-extern void _set_bit_le(int nr, volatile unsigned long * p);
-extern void _clear_bit_le(int nr, volatile unsigned long * p);
-extern void _change_bit_le(int nr, volatile unsigned long * p);
-extern int _test_and_set_bit_le(int nr, volatile unsigned long * p);
-extern int _test_and_clear_bit_le(int nr, volatile unsigned long * p);
-extern int _test_and_change_bit_le(int nr, volatile unsigned long * p);
 extern int _find_first_zero_bit_le(const void * p, unsigned size);
 extern int _find_next_zero_bit_le(const void * p, int size, int offset);
 extern int _find_first_bit_le(const unsigned long *p, unsigned size);
@@ -165,12 +167,6 @@ extern int _find_next_bit_le(const unsigned long *p, int size, int offset);
 /*
  * Big endian assembly bitops.  nr = 0 -> byte 3 bit 0.
  */
-extern void _set_bit_be(int nr, volatile unsigned long * p);
-extern void _clear_bit_be(int nr, volatile unsigned long * p);
-extern void _change_bit_be(int nr, volatile unsigned long * p);
-extern int _test_and_set_bit_be(int nr, volatile unsigned long * p);
-extern int _test_and_clear_bit_be(int nr, volatile unsigned long * p);
-extern int _test_and_change_bit_be(int nr, volatile unsigned long * p);
 extern int _find_first_zero_bit_be(const void * p, unsigned size);
 extern int _find_next_zero_bit_be(const void * p, int size, int offset);
 extern int _find_first_bit_be(const unsigned long *p, unsigned size);
@@ -180,58 +176,40 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 /*
  * The __* form of bitops are non-atomic and may be reordered.
  */
-#define	ATOMIC_BITOP_LE(name,nr,p)		\
-	(__builtin_constant_p(nr) ?		\
-	 ____atomic_##name(nr, p) :		\
-	 _##name##_le(nr,p))
-
-#define	ATOMIC_BITOP_BE(name,nr,p)		\
-	(__builtin_constant_p(nr) ?		\
-	 ____atomic_##name(nr, p) :		\
-	 _##name##_be(nr,p))
+#define ATOMIC_BITOP(name,nr,p)			\
+	(__builtin_constant_p(nr) ? ____atomic_##name(nr, p) : _##name(nr,p))
 #else
-#define ATOMIC_BITOP_LE(name,nr,p)	_##name##_le(nr,p)
-#define ATOMIC_BITOP_BE(name,nr,p)	_##name##_be(nr,p)
+#define ATOMIC_BITOP(name,nr,p)		_##name(nr,p)
 #endif
 
-#define NONATOMIC_BITOP(name,nr,p)		\
-	(____nonatomic_##name(nr, p))
+/*
+ * Native endian atomic definitions.
+ */
+#define set_bit(nr,p)			ATOMIC_BITOP(set_bit,nr,p)
+#define clear_bit(nr,p)			ATOMIC_BITOP(clear_bit,nr,p)
+#define change_bit(nr,p)		ATOMIC_BITOP(change_bit,nr,p)
+#define test_and_set_bit(nr,p)		ATOMIC_BITOP(test_and_set_bit,nr,p)
+#define test_and_clear_bit(nr,p)	ATOMIC_BITOP(test_and_clear_bit,nr,p)
+#define test_and_change_bit(nr,p)	ATOMIC_BITOP(test_and_change_bit,nr,p)
 
 #ifndef __ARMEB__
 /*
  * These are the little endian, atomic definitions.
  */
-#define set_bit(nr,p)			ATOMIC_BITOP_LE(set_bit,nr,p)
-#define clear_bit(nr,p)			ATOMIC_BITOP_LE(clear_bit,nr,p)
-#define change_bit(nr,p)		ATOMIC_BITOP_LE(change_bit,nr,p)
-#define test_and_set_bit(nr,p)		ATOMIC_BITOP_LE(test_and_set_bit,nr,p)
-#define test_and_clear_bit(nr,p)	ATOMIC_BITOP_LE(test_and_clear_bit,nr,p)
-#define test_and_change_bit(nr,p)	ATOMIC_BITOP_LE(test_and_change_bit,nr,p)
 #define find_first_zero_bit(p,sz)	_find_first_zero_bit_le(p,sz)
 #define find_next_zero_bit(p,sz,off)	_find_next_zero_bit_le(p,sz,off)
 #define find_first_bit(p,sz)		_find_first_bit_le(p,sz)
 #define find_next_bit(p,sz,off)		_find_next_bit_le(p,sz,off)
 
-#define WORD_BITOFF_TO_LE(x)		((x))
-
 #else
-
 /*
  * These are the big endian, atomic definitions.
  */
-#define set_bit(nr,p)			ATOMIC_BITOP_BE(set_bit,nr,p)
-#define clear_bit(nr,p)			ATOMIC_BITOP_BE(clear_bit,nr,p)
-#define change_bit(nr,p)		ATOMIC_BITOP_BE(change_bit,nr,p)
-#define test_and_set_bit(nr,p)		ATOMIC_BITOP_BE(test_and_set_bit,nr,p)
-#define test_and_clear_bit(nr,p)	ATOMIC_BITOP_BE(test_and_clear_bit,nr,p)
-#define test_and_change_bit(nr,p)	ATOMIC_BITOP_BE(test_and_change_bit,nr,p)
 #define find_first_zero_bit(p,sz)	_find_first_zero_bit_be(p,sz)
 #define find_next_zero_bit(p,sz,off)	_find_next_zero_bit_be(p,sz,off)
 #define find_first_bit(p,sz)		_find_first_bit_be(p,sz)
 #define find_next_bit(p,sz,off)		_find_next_bit_be(p,sz,off)
 
-#define WORD_BITOFF_TO_LE(x)		((x) ^ 0x18)
-
 #endif
 
 #if __LINUX_ARM_ARCH__ < 5
@@ -274,25 +252,59 @@ static inline int constant_fls(int x)
 }
 
 /*
- * On ARMv5 and above those functions can be implemented around
- * the clz instruction for much better code efficiency.
+ * On ARMv5 and above those functions can be implemented around the
+ * clz instruction for much better code efficiency.  __clz returns
+ * the number of leading zeros, zero input will return 32, and
+ * 0x80000000 will return 0.
  */
+static inline unsigned int __clz(unsigned int x)
+{
+	unsigned int ret;
 
+	asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
+
+	return ret;
+}
+
+/*
+ * fls() returns zero if the input is zero, otherwise returns the bit
+ * position of the last set bit, where the LSB is 1 and MSB is 32.
+ */
 static inline int fls(int x)
 {
-	int ret;
-
 	if (__builtin_constant_p(x))
 	       return constant_fls(x);
 
-	asm("clz\t%0, %1" : "=r" (ret) : "r" (x) : "cc");
-       	ret = 32 - ret;
-	return ret;
+	return 32 - __clz(x);
+}
+
+/*
+ * __fls() returns the bit position of the last bit set, where the
+ * LSB is 0 and MSB is 31.  Zero input is undefined.
+ */
+static inline unsigned long __fls(unsigned long x)
+{
+	return fls(x) - 1;
+}
+
+/*
+ * ffs() returns zero if the input was zero, otherwise returns the bit
+ * position of the first set bit, where the LSB is 1 and MSB is 32.
+ */
+static inline int ffs(int x)
+{
+	return fls(x & -x);
+}
+
+/*
+ * __ffs() returns the bit position of the first bit set, where the
+ * LSB is 0 and MSB is 31.  Zero input is undefined.
+ */
+static inline unsigned long __ffs(unsigned long x)
+{
+	return ffs(x) - 1;
 }
 
-#define __fls(x) (fls(x) - 1)
-#define ffs(x) ({ unsigned long __t = (x); fls(__t & -__t); })
-#define __ffs(x) (ffs(x) - 1)
 #define ffz(x) __ffs( ~(x) )
 
 #endif
@@ -303,41 +315,34 @@ static inline int fls(int x)
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/lock.h>
 
-/*
- * Ext2 is defined to use little-endian byte ordering.
- * These do not need to be atomic.
- */
-#define ext2_set_bit(nr,p)			\
-		__test_and_set_bit(WORD_BITOFF_TO_LE(nr), (unsigned long *)(p))
-#define ext2_set_bit_atomic(lock,nr,p)          \
-                test_and_set_bit(WORD_BITOFF_TO_LE(nr), (unsigned long *)(p))
-#define ext2_clear_bit(nr,p)			\
-		__test_and_clear_bit(WORD_BITOFF_TO_LE(nr), (unsigned long *)(p))
-#define ext2_clear_bit_atomic(lock,nr,p)        \
-                test_and_clear_bit(WORD_BITOFF_TO_LE(nr), (unsigned long *)(p))
-#define ext2_test_bit(nr,p)			\
-		test_bit(WORD_BITOFF_TO_LE(nr), (unsigned long *)(p))
-#define ext2_find_first_zero_bit(p,sz)		\
-		_find_first_zero_bit_le(p,sz)
-#define ext2_find_next_zero_bit(p,sz,off)	\
-		_find_next_zero_bit_le(p,sz,off)
-#define ext2_find_next_bit(p, sz, off) \
-		_find_next_bit_le(p, sz, off)
+#ifdef __ARMEB__
+
+static inline int find_first_zero_bit_le(const void *p, unsigned size)
+{
+	return _find_first_zero_bit_le(p, size);
+}
+#define find_first_zero_bit_le find_first_zero_bit_le
+
+static inline int find_next_zero_bit_le(const void *p, int size, int offset)
+{
+	return _find_next_zero_bit_le(p, size, offset);
+}
+#define find_next_zero_bit_le find_next_zero_bit_le
+
+static inline int find_next_bit_le(const void *p, int size, int offset)
+{
+	return _find_next_bit_le(p, size, offset);
+}
+#define find_next_bit_le find_next_bit_le
+
+#endif
+
+#include <asm-generic/bitops/le.h>
 
 /*
- * Minix is defined to use little-endian byte ordering.
- * These do not need to be atomic.
+ * Ext2 is defined to use little-endian byte ordering.
  */
-#define minix_set_bit(nr,p)			\
-		__set_bit(WORD_BITOFF_TO_LE(nr), (unsigned long *)(p))
-#define minix_test_bit(nr,p)			\
-		test_bit(WORD_BITOFF_TO_LE(nr), (unsigned long *)(p))
-#define minix_test_and_set_bit(nr,p)		\
-		__test_and_set_bit(WORD_BITOFF_TO_LE(nr), (unsigned long *)(p))
-#define minix_test_and_clear_bit(nr,p)		\
-		__test_and_clear_bit(WORD_BITOFF_TO_LE(nr), (unsigned long *)(p))
-#define minix_find_first_zero_bit(p,sz)		\
-		_find_first_zero_bit_le(p,sz)
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/arm/include/asm/bitsperlong.h b/arch/arm/include/asm/bitsperlong.h
deleted file mode 100644
index 6dc0bb0c13b..00000000000
--- a/arch/arm/include/asm/bitsperlong.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/bitsperlong.h>
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index 4d88425a416..b274bde2490 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -1,24 +1,92 @@
 #ifndef _ASMARM_BUG_H
 #define _ASMARM_BUG_H
 
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <asm/opcodes.h>
 
 #ifdef CONFIG_BUG
+
+/*
+ * Use a suitable undefined instruction to use for ARM/Thumb2 bug handling.
+ * We need to be careful not to conflict with those used by other modules and
+ * the register_undef_hook() system.
+ */
+#ifdef CONFIG_THUMB2_KERNEL
+#define BUG_INSTR_VALUE 0xde02
+#define BUG_INSTR(__value) __inst_thumb16(__value)
+#else
+#define BUG_INSTR_VALUE 0xe7f001f2
+#define BUG_INSTR(__value) __inst_arm(__value)
+#endif
+
+
+#define BUG() _BUG(__FILE__, __LINE__, BUG_INSTR_VALUE)
+#define _BUG(file, line, value) __BUG(file, line, value)
+
 #ifdef CONFIG_DEBUG_BUGVERBOSE
-extern void __bug(const char *file, int line) __attribute__((noreturn));
 
-/* give file/line information */
-#define BUG()		__bug(__FILE__, __LINE__)
+/*
+ * The extra indirection is to ensure that the __FILE__ string comes through
+ * OK. Many version of gcc do not support the asm %c parameter which would be
+ * preferable to this unpleasantness. We use mergeable string sections to
+ * avoid multiple copies of the string appearing in the kernel image.
+ */
 
-#else
+#define __BUG(__file, __line, __value)				\
+do {								\
+	asm volatile("1:\t" BUG_INSTR(__value) "\n"  \
+		".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
+		"2:\t.asciz " #__file "\n" 			\
+		".popsection\n" 				\
+		".pushsection __bug_table,\"a\"\n"		\
+		"3:\t.word 1b, 2b\n"				\
+		"\t.hword " #__line ", 0\n"			\
+		".popsection");					\
+	unreachable();						\
+} while (0)
 
-/* this just causes an oops */
-#define BUG()		do { *(int *)0 = 0; } while (1)
+#else  /* not CONFIG_DEBUG_BUGVERBOSE */
 
-#endif
+#define __BUG(__file, __line, __value)				\
+do {								\
+	asm volatile(BUG_INSTR(__value) "\n");			\
+	unreachable();						\
+} while (0)
+#endif  /* CONFIG_DEBUG_BUGVERBOSE */
 
 #define HAVE_ARCH_BUG
-#endif
+#endif  /* CONFIG_BUG */
 
 #include <asm-generic/bug.h>
 
+struct pt_regs;
+void die(const char *msg, struct pt_regs *regs, int err);
+
+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);
+
+void hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int,
+				       struct pt_regs *),
+		     int sig, int code, const char *name);
+
+extern asmlinkage void c_backtrace(unsigned long fp, int pmode);
+
+struct mm_struct;
+extern void show_pte(struct mm_struct *mm, unsigned long addr);
+extern void __show_regs(struct pt_regs *);
+
 #endif
diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
index 9d6122096fb..75fe66bc02b 100644
--- a/arch/arm/include/asm/cache.h
+++ b/arch/arm/include/asm/cache.h
@@ -23,4 +23,6 @@
 #define ARCH_SLAB_MINALIGN 8
 #endif
 
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+
 #endif
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 3acd8fa25e3..fd43f7f55b7 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -12,7 +12,7 @@
 
 #include <linux/mm.h>
 
-#include <asm/glue.h>
+#include <asm/glue-cache.h>
 #include <asm/shmparam.h>
 #include <asm/cachetype.h>
 #include <asm/outercache.h>
@@ -20,123 +20,6 @@
 #define CACHE_COLOUR(vaddr)	((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)
 
 /*
- *	Cache Model
- *	===========
- */
-#undef _CACHE
-#undef MULTI_CACHE
-
-#if defined(CONFIG_CPU_CACHE_V3)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v3
-# endif
-#endif
-
-#if defined(CONFIG_CPU_CACHE_V4)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v4
-# endif
-#endif
-
-#if defined(CONFIG_CPU_ARM920T) || defined(CONFIG_CPU_ARM922T) || \
-    defined(CONFIG_CPU_ARM925T) || defined(CONFIG_CPU_ARM1020) || \
-    defined(CONFIG_CPU_ARM1026)
-# define MULTI_CACHE 1
-#endif
-
-#if defined(CONFIG_CPU_FA526)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE fa
-# endif
-#endif
-
-#if defined(CONFIG_CPU_ARM926T)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE arm926
-# endif
-#endif
-
-#if defined(CONFIG_CPU_ARM940T)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE arm940
-# endif
-#endif
-
-#if defined(CONFIG_CPU_ARM946E)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE arm946
-# endif
-#endif
-
-#if defined(CONFIG_CPU_CACHE_V4WB)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v4wb
-# endif
-#endif
-
-#if defined(CONFIG_CPU_XSCALE)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE xscale
-# endif
-#endif
-
-#if defined(CONFIG_CPU_XSC3)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE xsc3
-# endif
-#endif
-
-#if defined(CONFIG_CPU_MOHAWK)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE mohawk
-# endif
-#endif
-
-#if defined(CONFIG_CPU_FEROCEON)
-# define MULTI_CACHE 1
-#endif
-
-#if defined(CONFIG_CPU_V6)
-//# ifdef _CACHE
-#  define MULTI_CACHE 1
-//# else
-//#  define _CACHE v6
-//# endif
-#endif
-
-#if defined(CONFIG_CPU_V7)
-//# ifdef _CACHE
-#  define MULTI_CACHE 1
-//# else
-//#  define _CACHE v7
-//# endif
-#endif
-
-#if !defined(_CACHE) && !defined(MULTI_CACHE)
-#error Unknown cache maintainence model
-#endif
-
-/*
  * This flag is used to indicate that the page pointed to by a pte is clean
  * and does not require cleaning before returning it to the user.
  */
@@ -166,6 +49,13 @@
  *
  *		Unconditionally clean and invalidate the entire cache.
  *
+ *     flush_kern_louis()
+ *
+ *             Flush data cache levels up to the level of unification
+ *             inner shareable and invalidate the I-cache.
+ *             Only needed from v7 onwards, falls back to flush_cache_all()
+ *             for all other processor versions.
+ *
  *	flush_user_all()
  *
  *		Clean and invalidate all user space cache entries
@@ -214,11 +104,12 @@
 struct cpu_cache_fns {
 	void (*flush_icache_all)(void);
 	void (*flush_kern_all)(void);
+	void (*flush_kern_louis)(void);
 	void (*flush_user_all)(void);
 	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);
 
 	void (*coherent_kern_range)(unsigned long, unsigned long);
-	void (*coherent_user_range)(unsigned long, unsigned long);
+	int  (*coherent_user_range)(unsigned long, unsigned long);
 	void (*flush_kern_dcache_area)(void *, size_t);
 
 	void (*dma_map_area)(const void *, size_t, int);
@@ -236,6 +127,7 @@ extern struct cpu_cache_fns cpu_cache;
 
 #define __cpuc_flush_icache_all		cpu_cache.flush_icache_all
 #define __cpuc_flush_kern_all		cpu_cache.flush_kern_all
+#define __cpuc_flush_kern_louis		cpu_cache.flush_kern_louis
 #define __cpuc_flush_user_all		cpu_cache.flush_user_all
 #define __cpuc_flush_user_range		cpu_cache.flush_user_range
 #define __cpuc_coherent_kern_range	cpu_cache.coherent_kern_range
@@ -249,25 +141,18 @@ extern struct cpu_cache_fns cpu_cache;
  * visible to the CPU.
  */
 #define dmac_map_area			cpu_cache.dma_map_area
-#define dmac_unmap_area		cpu_cache.dma_unmap_area
+#define dmac_unmap_area			cpu_cache.dma_unmap_area
 #define dmac_flush_range		cpu_cache.dma_flush_range
 
 #else
 
-#define __cpuc_flush_icache_all		__glue(_CACHE,_flush_icache_all)
-#define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
-#define __cpuc_flush_user_all		__glue(_CACHE,_flush_user_cache_all)
-#define __cpuc_flush_user_range		__glue(_CACHE,_flush_user_cache_range)
-#define __cpuc_coherent_kern_range	__glue(_CACHE,_coherent_kern_range)
-#define __cpuc_coherent_user_range	__glue(_CACHE,_coherent_user_range)
-#define __cpuc_flush_dcache_area	__glue(_CACHE,_flush_kern_dcache_area)
-
 extern void __cpuc_flush_icache_all(void);
 extern void __cpuc_flush_kern_all(void);
+extern void __cpuc_flush_kern_louis(void);
 extern void __cpuc_flush_user_all(void);
 extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
 extern void __cpuc_coherent_kern_range(unsigned long, unsigned long);
-extern void __cpuc_coherent_user_range(unsigned long, unsigned long);
+extern int  __cpuc_coherent_user_range(unsigned long, unsigned long);
 extern void __cpuc_flush_dcache_area(void *, size_t);
 
 /*
@@ -276,10 +161,6 @@ extern void __cpuc_flush_dcache_area(void *, size_t);
  * is visible to DMA, or data written by DMA to system memory is
  * visible to the CPU.
  */
-#define dmac_map_area			__glue(_CACHE,_dma_map_area)
-#define dmac_unmap_area		__glue(_CACHE,_dma_unmap_area)
-#define dmac_flush_range		__glue(_CACHE,_dma_flush_range)
-
 extern void dmac_map_area(const void *, size_t, int);
 extern void dmac_unmap_area(const void *, size_t, int);
 extern void dmac_flush_range(const void *, const void *);
@@ -316,7 +197,8 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
  * Optimized __flush_icache_all for the common cases. Note that UP ARMv7
  * will fall through to use __flush_icache_all_generic.
  */
-#if (defined(CONFIG_CPU_V7) && defined(CONFIG_CPU_V6)) ||		\
+#if (defined(CONFIG_CPU_V7) && \
+     (defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K))) || \
 	defined(CONFIG_SMP_ON_UP)
 #define __flush_icache_preferred	__cpuc_flush_icache_all
 #elif __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
@@ -330,8 +212,14 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
 static inline void __flush_icache_all(void)
 {
 	__flush_icache_preferred();
+	dsb(ishst);
 }
 
+/*
+ * Flush caches up to Level of Unification Inner Shareable
+ */
+#define flush_cache_louis()		__cpuc_flush_kern_louis()
+
 #define flush_cache_all()		__cpuc_flush_kern_all()
 
 static inline void vivt_flush_cache_mm(struct mm_struct *mm)
@@ -343,7 +231,9 @@ static inline void vivt_flush_cache_mm(struct mm_struct *mm)
 static inline void
 vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)))
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
 		__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
 					vma->vm_flags);
 }
@@ -351,7 +241,9 @@ vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned
 static inline void
 vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn)
 {
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
 		unsigned long addr = user_addr & PAGE_MASK;
 		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
 	}
@@ -377,8 +269,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
  * Harvard caches are synchronised for the user space address range.
  * This is used for the ARM private sys_cacheflush system call.
  */
-#define flush_cache_user_range(vma,start,end) \
-	__cpuc_coherent_user_range((start) & PAGE_MASK, PAGE_ALIGN(end))
+#define flush_cache_user_range(s,e)	__cpuc_coherent_user_range(s,e)
 
 /*
  * Perform necessary cache operations to ensure that data previously
@@ -429,9 +320,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 }
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
-static inline void flush_kernel_dcache_page(struct page *page)
-{
-}
+extern void flush_kernel_dcache_page(struct page *);
 
 #define flush_dcache_mmap_lock(mapping) \
 	spin_lock_irq(&(mapping)->tree_lock)
@@ -463,7 +352,7 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		 * set_pte_at() called from vmap_pte_range() does not
 		 * have a DSB after cleaning the cache line.
 		 */
-		dsb();
+		dsb(ishst);
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
@@ -472,4 +361,132 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 		flush_cache_all();
 }
 
+/*
+ * Memory synchronization helpers for mixed cached vs non cached accesses.
+ *
+ * Some synchronization algorithms have to set states in memory with the
+ * cache enabled or disabled depending on the code path.  It is crucial
+ * to always ensure proper cache maintenance to update main memory right
+ * away in that case.
+ *
+ * Any cached write must be followed by a cache clean operation.
+ * Any cached read must be preceded by a cache invalidate operation.
+ * Yet, in the read case, a cache flush i.e. atomic clean+invalidate
+ * operation is needed to avoid discarding possible concurrent writes to the
+ * accessed memory.
+ *
+ * Also, in order to prevent a cached writer from interfering with an
+ * adjacent non-cached writer, each state variable must be located to
+ * a separate cache line.
+ */
+
+/*
+ * This needs to be >= the max cache writeback size of all
+ * supported platforms included in the current kernel configuration.
+ * This is used to align state variables to their own cache lines.
+ */
+#define __CACHE_WRITEBACK_ORDER 6  /* guessed from existing platforms */
+#define __CACHE_WRITEBACK_GRANULE (1 << __CACHE_WRITEBACK_ORDER)
+
+/*
+ * There is no __cpuc_clean_dcache_area but we use it anyway for
+ * code intent clarity, and alias it to __cpuc_flush_dcache_area.
+ */
+#define __cpuc_clean_dcache_area __cpuc_flush_dcache_area
+
+/*
+ * Ensure preceding writes to *p by this CPU are visible to
+ * subsequent reads by other CPUs:
+ */
+static inline void __sync_cache_range_w(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+	__cpuc_clean_dcache_area(_p, size);
+	outer_clean_range(__pa(_p), __pa(_p + size));
+}
+
+/*
+ * Ensure preceding writes to *p by other CPUs are visible to
+ * subsequent reads by this CPU.  We must be careful not to
+ * discard data simultaneously written by another CPU, hence the
+ * usage of flush rather than invalidate operations.
+ */
+static inline void __sync_cache_range_r(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+#ifdef CONFIG_OUTER_CACHE
+	if (outer_cache.flush_range) {
+		/*
+		 * Ensure dirty data migrated from other CPUs into our cache
+		 * are cleaned out safely before the outer cache is cleaned:
+		 */
+		__cpuc_clean_dcache_area(_p, size);
+
+		/* Clean and invalidate stale data for *p from outer ... */
+		outer_flush_range(__pa(_p), __pa(_p + size));
+	}
+#endif
+
+	/* ... and inner cache: */
+	__cpuc_flush_dcache_area(_p, size);
+}
+
+#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
+#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
+
+/*
+ * Disabling cache access for one CPU in an ARMv7 SMP system is tricky.
+ * To do so we must:
+ *
+ * - Clear the SCTLR.C bit to prevent further cache allocations
+ * - Flush the desired level of cache
+ * - Clear the ACTLR "SMP" bit to disable local coherency
+ *
+ * ... and so without any intervening memory access in between those steps,
+ * not even to the stack.
+ *
+ * WARNING -- After this has been called:
+ *
+ * - No ldrex/strex (and similar) instructions must be used.
+ * - The CPU is obviously no longer coherent with the other CPUs.
+ * - This is unlikely to work as expected if Linux is running non-secure.
+ *
+ * Note:
+ *
+ * - This is known to apply to several ARMv7 processor implementations,
+ *   however some exceptions may exist.  Caveat emptor.
+ *
+ * - The clobber list is dictated by the call to v7_flush_dcache_*.
+ *   fp is preserved to the stack explicitly prior disabling the cache
+ *   since adding it to the clobber list is incompatible with having
+ *   CONFIG_FRAME_POINTER=y.  ip is saved as well if ever r12-clobbering
+ *   trampoline are inserted by the linker and to keep sp 64-bit aligned.
+ */
+#define v7_exit_coherency_flush(level) \
+	asm volatile( \
+	"stmfd	sp!, {fp, ip} \n\t" \
+	"mrc	p15, 0, r0, c1, c0, 0	@ get SCTLR \n\t" \
+	"bic	r0, r0, #"__stringify(CR_C)" \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 0	@ set SCTLR \n\t" \
+	"isb	\n\t" \
+	"bl	v7_flush_dcache_"__stringify(level)" \n\t" \
+	"clrex	\n\t" \
+	"mrc	p15, 0, r0, c1, c0, 1	@ get ACTLR \n\t" \
+	"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 1	@ set ACTLR \n\t" \
+	"isb	\n\t" \
+	"dsb	\n\t" \
+	"ldmfd	sp!, {fp, ip}" \
+	: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
+	      "r9","r10","lr","memory" )
+
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
+
+void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
+			     void *kaddr, unsigned long len);
 #endif
diff --git a/arch/arm/include/asm/cachetype.h b/arch/arm/include/asm/cachetype.h
index c023db09fcc..7ea78144ae2 100644
--- a/arch/arm/include/asm/cachetype.h
+++ b/arch/arm/include/asm/cachetype.h
@@ -7,6 +7,7 @@
 #define CACHEID_VIPT			(CACHEID_VIPT_ALIASING|CACHEID_VIPT_NONALIASING)
 #define CACHEID_ASID_TAGGED		(1 << 3)
 #define CACHEID_VIPT_I_ALIASING		(1 << 4)
+#define CACHEID_PIPT			(1 << 5)
 
 extern unsigned int cacheid;
 
@@ -16,6 +17,7 @@ extern unsigned int cacheid;
 #define cache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_ALIASING)
 #define icache_is_vivt_asid_tagged()	cacheid_is(CACHEID_ASID_TAGGED)
 #define icache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_I_ALIASING)
+#define icache_is_pipt()		cacheid_is(CACHEID_PIPT)
 
 /*
  * __LINUX_ARM_ARCH__ is the minimum supported CPU architecture
@@ -26,7 +28,8 @@ extern unsigned int cacheid;
 #if __LINUX_ARM_ARCH__ >= 7
 #define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING |\
 				 CACHEID_ASID_TAGGED |\
-				 CACHEID_VIPT_I_ALIASING)
+				 CACHEID_VIPT_I_ALIASING |\
+				 CACHEID_PIPT)
 #elif __LINUX_ARM_ARCH__ >= 6
 #define	__CACHEID_ARCH_MIN	(~CACHEID_VIVT)
 #else
diff --git a/arch/arm/include/asm/checksum.h b/arch/arm/include/asm/checksum.h
index 6dcc1643086..52331511547 100644
--- a/arch/arm/include/asm/checksum.h
+++ b/arch/arm/include/asm/checksum.h
@@ -87,19 +87,33 @@ static inline __wsum
 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
 		   unsigned short proto, __wsum sum)
 {
-	__asm__(
-	"adds	%0, %1, %2		@ csum_tcpudp_nofold	\n\
-	adcs	%0, %0, %3					\n"
+	u32 lenprot = len | proto << 16;
+	if (__builtin_constant_p(sum) && sum == 0) {
+		__asm__(
+		"adds	%0, %1, %2	@ csum_tcpudp_nofold0	\n\t"
 #ifdef __ARMEB__
-	"adcs	%0, %0, %4					\n"
+		"adcs	%0, %0, %3				\n\t"
 #else
-	"adcs	%0, %0, %4, lsl #8				\n"
+		"adcs	%0, %0, %3, ror #8			\n\t"
 #endif
-	"adcs	%0, %0, %5					\n\
-	adc	%0, %0, #0"
-	: "=&r"(sum)
-	: "r" (sum), "r" (daddr), "r" (saddr), "r" (len), "Ir" (htons(proto))
-	: "cc");
+		"adc	%0, %0, #0"
+		: "=&r" (sum)
+		: "r" (daddr), "r" (saddr), "r" (lenprot)
+		: "cc");
+	} else {
+		__asm__(
+		"adds	%0, %1, %2	@ csum_tcpudp_nofold	\n\t"
+		"adcs	%0, %0, %3				\n\t"
+#ifdef __ARMEB__
+		"adcs	%0, %0, %4				\n\t"
+#else
+		"adcs	%0, %0, %4, ror #8			\n\t"
+#endif
+		"adc	%0, %0, #0"
+		: "=&r"(sum)
+		: "r" (sum), "r" (daddr), "r" (saddr), "r" (lenprot)
+		: "cc");
+	}
 	return sum;
 }	
 /*
diff --git a/arch/arm/include/asm/clkdev.h b/arch/arm/include/asm/clkdev.h
index b56c1389b6f..4e8a4b27d7c 100644
--- a/arch/arm/include/asm/clkdev.h
+++ b/arch/arm/include/asm/clkdev.h
@@ -12,23 +12,20 @@
 #ifndef __ASM_CLKDEV_H
 #define __ASM_CLKDEV_H
 
-struct clk;
-struct device;
+#include <linux/slab.h>
 
-struct clk_lookup {
-	struct list_head	node;
-	const char		*dev_id;
-	const char		*con_id;
-	struct clk		*clk;
-};
-
-struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
-	const char *dev_fmt, ...);
-
-void clkdev_add(struct clk_lookup *cl);
-void clkdev_drop(struct clk_lookup *cl);
+#ifndef CONFIG_COMMON_CLK
+#ifdef CONFIG_HAVE_MACH_CLKDEV
+#include <mach/clkdev.h>
+#else
+#define __clk_get(clk)	({ 1; })
+#define __clk_put(clk)	do { } while (0)
+#endif
+#endif
 
-void clkdev_add_table(struct clk_lookup *, size_t);
-int clk_add_alias(const char *, const char *, char *, struct device *);
+static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
+{
+	return kzalloc(size, GFP_KERNEL);
+}
 
 #endif
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
new file mode 100644
index 00000000000..abb2c3769b0
--- /dev/null
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -0,0 +1,288 @@
+#ifndef __ASM_ARM_CMPXCHG_H
+#define __ASM_ARM_CMPXCHG_H
+
+#include <linux/irqflags.h>
+#include <linux/prefetch.h>
+#include <asm/barrier.h>
+
+#if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
+/*
+ * On the StrongARM, "swp" is terminally broken since it bypasses the
+ * cache totally.  This means that the cache becomes inconsistent, and,
+ * since we use normal loads/stores as well, this is really bad.
+ * Typically, this causes oopsen in filp_close, but could have other,
+ * more disastrous effects.  There are two work-arounds:
+ *  1. Disable interrupts and emulate the atomic swap
+ *  2. Clean the cache, perform atomic swap, flush the cache
+ *
+ * We choose (1) since its the "easiest" to achieve here and is not
+ * dependent on the processor type.
+ *
+ * NOTE that this solution won't work on an SMP system, so explcitly
+ * forbid it here.
+ */
+#define swp_is_buggy
+#endif
+
+static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
+{
+	extern void __bad_xchg(volatile void *, int);
+	unsigned long ret;
+#ifdef swp_is_buggy
+	unsigned long flags;
+#endif
+#if __LINUX_ARM_ARCH__ >= 6
+	unsigned int tmp;
+#endif
+
+	smp_mb();
+	prefetchw((const void *)ptr);
+
+	switch (size) {
+#if __LINUX_ARM_ARCH__ >= 6
+	case 1:
+		asm volatile("@	__xchg1\n"
+		"1:	ldrexb	%0, [%3]\n"
+		"	strexb	%1, %2, [%3]\n"
+		"	teq	%1, #0\n"
+		"	bne	1b"
+			: "=&r" (ret), "=&r" (tmp)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+	case 4:
+		asm volatile("@	__xchg4\n"
+		"1:	ldrex	%0, [%3]\n"
+		"	strex	%1, %2, [%3]\n"
+		"	teq	%1, #0\n"
+		"	bne	1b"
+			: "=&r" (ret), "=&r" (tmp)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+#elif defined(swp_is_buggy)
+#ifdef CONFIG_SMP
+#error SMP is not supported on this platform
+#endif
+	case 1:
+		raw_local_irq_save(flags);
+		ret = *(volatile unsigned char *)ptr;
+		*(volatile unsigned char *)ptr = x;
+		raw_local_irq_restore(flags);
+		break;
+
+	case 4:
+		raw_local_irq_save(flags);
+		ret = *(volatile unsigned long *)ptr;
+		*(volatile unsigned long *)ptr = x;
+		raw_local_irq_restore(flags);
+		break;
+#else
+	case 1:
+		asm volatile("@	__xchg1\n"
+		"	swpb	%0, %1, [%2]"
+			: "=&r" (ret)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+	case 4:
+		asm volatile("@	__xchg4\n"
+		"	swp	%0, %1, [%2]"
+			: "=&r" (ret)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+#endif
+	default:
+		__bad_xchg(ptr, size), ret = 0;
+		break;
+	}
+	smp_mb();
+
+	return ret;
+}
+
+#define xchg(ptr,x) \
+	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+#include <asm-generic/cmpxchg-local.h>
+
+#if __LINUX_ARM_ARCH__ < 6
+/* min ARCH < ARMv6 */
+
+#ifdef CONFIG_SMP
+#error "SMP is not supported on this platform"
+#endif
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#ifndef CONFIG_SMP
+#include <asm-generic/cmpxchg.h>
+#endif
+
+#else	/* min ARCH >= ARMv6 */
+
+extern void __bad_cmpxchg(volatile void *ptr, int size);
+
+/*
+ * cmpxchg only support 32-bits operands on ARMv6.
+ */
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	unsigned long oldval, res;
+
+	prefetchw((const void *)ptr);
+
+	switch (size) {
+#ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
+	case 1:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexb	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexbeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	case 2:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexh	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexheq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+#endif
+	case 4:
+		do {
+			asm volatile("@ __cmpxchg4\n"
+			"	ldrex	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	default:
+		__bad_cmpxchg(ptr, size);
+		oldval = 0;
+	}
+
+	return oldval;
+}
+
+static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
+					 unsigned long new, int size)
+{
+	unsigned long ret;
+
+	smp_mb();
+	ret = __cmpxchg(ptr, old, new, size);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
+					  (unsigned long)(o),		\
+					  (unsigned long)(n),		\
+					  sizeof(*(ptr))))
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+					    unsigned long old,
+					    unsigned long new, int size)
+{
+	unsigned long ret;
+
+	switch (size) {
+#ifdef CONFIG_CPU_V6	/* min ARCH == ARMv6 */
+	case 1:
+	case 2:
+		ret = __cmpxchg_local_generic(ptr, old, new, size);
+		break;
+#endif
+	default:
+		ret = __cmpxchg(ptr, old, new, size);
+	}
+
+	return ret;
+}
+
+static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
+					     unsigned long long old,
+					     unsigned long long new)
+{
+	unsigned long long oldval;
+	unsigned long res;
+
+	prefetchw(ptr);
+
+	__asm__ __volatile__(
+"1:	ldrexd		%1, %H1, [%3]\n"
+"	teq		%1, %4\n"
+"	teqeq		%H1, %H4\n"
+"	bne		2f\n"
+"	strexd		%0, %5, %H5, [%3]\n"
+"	teq		%0, #0\n"
+"	bne		1b\n"
+"2:"
+	: "=&r" (res), "=&r" (oldval), "+Qo" (*ptr)
+	: "r" (ptr), "r" (old), "r" (new)
+	: "cc");
+
+	return oldval;
+}
+
+static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
+						unsigned long long old,
+						unsigned long long new)
+{
+	unsigned long long ret;
+
+	smp_mb();
+	ret = __cmpxchg64(ptr, old, new);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg_local(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
+				       (unsigned long)(o),		\
+				       (unsigned long)(n),		\
+				       sizeof(*(ptr))))
+
+#define cmpxchg64(ptr, o, n)						\
+	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
+					(unsigned long long)(o),	\
+					(unsigned long long)(n)))
+
+#define cmpxchg64_relaxed(ptr, o, n)					\
+	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
+					(unsigned long long)(o),	\
+					(unsigned long long)(n)))
+
+#define cmpxchg64_local(ptr, o, n)	cmpxchg64_relaxed((ptr), (o), (n))
+
+#endif	/* __LINUX_ARM_ARCH__ >= 6 */
+
+#endif /* __ASM_ARM_CMPXCHG_H */
diff --git a/arch/arm/include/asm/compiler.h b/arch/arm/include/asm/compiler.h
new file mode 100644
index 00000000000..8155db2f7fa
--- /dev/null
+++ b/arch/arm/include/asm/compiler.h
@@ -0,0 +1,15 @@
+#ifndef __ASM_ARM_COMPILER_H
+#define __ASM_ARM_COMPILER_H
+
+/*
+ * This is used to ensure the compiler did actually allocate the register we
+ * asked it for some inline assembly sequences.  Apparently we can't trust
+ * the compiler from one version to another so a bit of paranoia won't hurt.
+ * This string is meant to be concatenated with the inline asm string and
+ * will cause compilation to stop on mismatch.
+ * (for details, see gcc PR 15089)
+ */
+#define __asmeq(x, y)  ".ifnc " x "," y " ; .err ; .endif\n\t"
+
+
+#endif /* __ASM_ARM_COMPILER_H */
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
new file mode 100644
index 00000000000..c3f11524f10
--- /dev/null
+++ b/arch/arm/include/asm/cp15.h
@@ -0,0 +1,119 @@
+#ifndef __ASM_ARM_CP15_H
+#define __ASM_ARM_CP15_H
+
+#include <asm/barrier.h>
+
+/*
+ * CR1 bits (CP#15 CR1)
+ */
+#define CR_M	(1 << 0)	/* MMU enable				*/
+#define CR_A	(1 << 1)	/* Alignment abort enable		*/
+#define CR_C	(1 << 2)	/* Dcache enable			*/
+#define CR_W	(1 << 3)	/* Write buffer enable			*/
+#define CR_P	(1 << 4)	/* 32-bit exception handler		*/
+#define CR_D	(1 << 5)	/* 32-bit data address range		*/
+#define CR_L	(1 << 6)	/* Implementation defined		*/
+#define CR_B	(1 << 7)	/* Big endian				*/
+#define CR_S	(1 << 8)	/* System MMU protection		*/
+#define CR_R	(1 << 9)	/* ROM MMU protection			*/
+#define CR_F	(1 << 10)	/* Implementation defined		*/
+#define CR_Z	(1 << 11)	/* Implementation defined		*/
+#define CR_I	(1 << 12)	/* Icache enable			*/
+#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
+#define CR_RR	(1 << 14)	/* Round Robin cache replacement	*/
+#define CR_L4	(1 << 15)	/* LDR pc can set T bit			*/
+#define CR_DT	(1 << 16)
+#ifdef CONFIG_MMU
+#define CR_HA	(1 << 17)	/* Hardware management of Access Flag   */
+#else
+#define CR_BR	(1 << 17)	/* MPU Background region enable (PMSA)  */
+#endif
+#define CR_IT	(1 << 18)
+#define CR_ST	(1 << 19)
+#define CR_FI	(1 << 21)	/* Fast interrupt (lower latency mode)	*/
+#define CR_U	(1 << 22)	/* Unaligned access operation		*/
+#define CR_XP	(1 << 23)	/* Extended page tables			*/
+#define CR_VE	(1 << 24)	/* Vectored interrupts			*/
+#define CR_EE	(1 << 25)	/* Exception (Big) Endian		*/
+#define CR_TRE	(1 << 28)	/* TEX remap enable			*/
+#define CR_AFE	(1 << 29)	/* Access flag enable			*/
+#define CR_TE	(1 << 30)	/* Thumb exception enable		*/
+
+#ifndef __ASSEMBLY__
+
+#if __LINUX_ARM_ARCH__ >= 4
+#define vectors_high()	(get_cr() & CR_V)
+#else
+#define vectors_high()	(0)
+#endif
+
+#ifdef CONFIG_CPU_CP15
+
+extern unsigned long cr_alignment;	/* defined in entry-armv.S */
+
+static inline unsigned long get_cr(void)
+{
+	unsigned long val;
+	asm("mrc p15, 0, %0, c1, c0, 0	@ get CR" : "=r" (val) : : "cc");
+	return val;
+}
+
+static inline void set_cr(unsigned long val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 0	@ set CR"
+	  : : "r" (val) : "cc");
+	isb();
+}
+
+static inline unsigned int get_auxcr(void)
+{
+	unsigned int val;
+	asm("mrc p15, 0, %0, c1, c0, 1	@ get AUXCR" : "=r" (val));
+	return val;
+}
+
+static inline void set_auxcr(unsigned int val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 1	@ set AUXCR"
+	  : : "r" (val));
+	isb();
+}
+
+#define CPACC_FULL(n)		(3 << (n * 2))
+#define CPACC_SVC(n)		(1 << (n * 2))
+#define CPACC_DISABLE(n)	(0 << (n * 2))
+
+static inline unsigned int get_copro_access(void)
+{
+	unsigned int val;
+	asm("mrc p15, 0, %0, c1, c0, 2 @ get copro access"
+	  : "=r" (val) : : "cc");
+	return val;
+}
+
+static inline void set_copro_access(unsigned int val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 2 @ set copro access"
+	  : : "r" (val) : "cc");
+	isb();
+}
+
+#else /* ifdef CONFIG_CPU_CP15 */
+
+/*
+ * cr_alignment is tightly coupled to cp15 (at least in the minds of the
+ * developers). Yielding 0 for machines without a cp15 (and making it
+ * read-only) is fine for most cases and saves quite some #ifdeffery.
+ */
+#define cr_alignment	UL(0)
+
+static inline unsigned long get_cr(void)
+{
+	return 0;
+}
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
+#endif /* ifndef __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arm/include/asm/cpu-multi32.h b/arch/arm/include/asm/cpu-multi32.h
deleted file mode 100644
index e2b5b0b2116..00000000000
--- a/arch/arm/include/asm/cpu-multi32.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- *  arch/arm/include/asm/cpu-multi32.h
- *
- *  Copyright (C) 2000 Russell King
- *
- * 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.
- */
-#include <asm/page.h>
-
-struct mm_struct;
-
-/*
- * Don't change this structure - ASM code
- * relies on it.
- */
-extern struct processor {
-	/* MISC
-	 * get data abort address/flags
-	 */
-	void (*_data_abort)(unsigned long pc);
-	/*
-	 * Retrieve prefetch fault address
-	 */
-	unsigned long (*_prefetch_abort)(unsigned long lr);
-	/*
-	 * Set up any processor specifics
-	 */
-	void (*_proc_init)(void);
-	/*
-	 * Disable any processor specifics
-	 */
-	void (*_proc_fin)(void);
-	/*
-	 * Special stuff for a reset
-	 */
-	void (*reset)(unsigned long addr) __attribute__((noreturn));
-	/*
-	 * Idle the processor
-	 */
-	int (*_do_idle)(void);
-	/*
-	 * Processor architecture specific
-	 */
-	/*
-	 * clean a virtual address range from the
-	 * D-cache without flushing the cache.
-	 */
-	void (*dcache_clean_area)(void *addr, int size);
-
-	/*
-	 * Set the page table
-	 */
-	void (*switch_mm)(unsigned long pgd_phys, struct mm_struct *mm);
-	/*
-	 * Set a possibly extended PTE.  Non-extended PTEs should
-	 * ignore 'ext'.
-	 */
-	void (*set_pte_ext)(pte_t *ptep, pte_t pte, unsigned int ext);
-} processor;
-
-#define cpu_proc_init()			processor._proc_init()
-#define cpu_proc_fin()			processor._proc_fin()
-#define cpu_reset(addr)			processor.reset(addr)
-#define cpu_do_idle()			processor._do_idle()
-#define cpu_dcache_clean_area(addr,sz)	processor.dcache_clean_area(addr,sz)
-#define cpu_set_pte_ext(ptep,pte,ext)	processor.set_pte_ext(ptep,pte,ext)
-#define cpu_do_switch_mm(pgd,mm)	processor.switch_mm(pgd,mm)
diff --git a/arch/arm/include/asm/cpu-single.h b/arch/arm/include/asm/cpu-single.h
deleted file mode 100644
index f073a6d2a40..00000000000
--- a/arch/arm/include/asm/cpu-single.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- *  arch/arm/include/asm/cpu-single.h
- *
- *  Copyright (C) 2000 Russell King
- *
- * 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.
- */
-/*
- * Single CPU
- */
-#ifdef __STDC__
-#define __catify_fn(name,x)	name##x
-#else
-#define __catify_fn(name,x)	name/**/x
-#endif
-#define __cpu_fn(name,x)	__catify_fn(name,x)
-
-/*
- * If we are supporting multiple CPUs, then we must use a table of
- * function pointers for this lot.  Otherwise, we can optimise the
- * table away.
- */
-#define cpu_proc_init			__cpu_fn(CPU_NAME,_proc_init)
-#define cpu_proc_fin			__cpu_fn(CPU_NAME,_proc_fin)
-#define cpu_reset			__cpu_fn(CPU_NAME,_reset)
-#define cpu_do_idle			__cpu_fn(CPU_NAME,_do_idle)
-#define cpu_dcache_clean_area		__cpu_fn(CPU_NAME,_dcache_clean_area)
-#define cpu_do_switch_mm		__cpu_fn(CPU_NAME,_switch_mm)
-#define cpu_set_pte_ext			__cpu_fn(CPU_NAME,_set_pte_ext)
-
-#include <asm/page.h>
-
-struct mm_struct;
-
-/* declare all the functions as extern */
-extern void cpu_proc_init(void);
-extern void cpu_proc_fin(void);
-extern int cpu_do_idle(void);
-extern void cpu_dcache_clean_area(void *, int);
-extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
-extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
-extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
diff --git a/arch/arm/include/asm/cpu.h b/arch/arm/include/asm/cpu.h
index 793968173be..2744f060255 100644
--- a/arch/arm/include/asm/cpu.h
+++ b/arch/arm/include/asm/cpu.h
@@ -15,8 +15,8 @@
 
 struct cpuinfo_arm {
 	struct cpu	cpu;
+	u32		cpuid;
 #ifdef CONFIG_SMP
-	struct task_struct *idle;
 	unsigned int	loops_per_jiffy;
 #endif
 };
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
new file mode 100644
index 00000000000..2fca60ab513
--- /dev/null
+++ b/arch/arm/include/asm/cpuidle.h
@@ -0,0 +1,29 @@
+#ifndef __ASM_ARM_CPUIDLE_H
+#define __ASM_ARM_CPUIDLE_H
+
+#ifdef CONFIG_CPU_IDLE
+extern int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index);
+#else
+static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
+		struct cpuidle_driver *drv, int index) { return -ENODEV; }
+#endif
+
+/* Common ARM WFI state */
+#define ARM_CPUIDLE_WFI_STATE_PWR(p) {\
+	.enter                  = arm_cpuidle_simple_enter,\
+	.exit_latency           = 1,\
+	.target_residency       = 1,\
+	.power_usage		= p,\
+	.flags                  = CPUIDLE_FLAG_TIME_VALID,\
+	.name                   = "WFI",\
+	.desc                   = "ARM WFI",\
+}
+
+/*
+ * in case power_specified == 1, give a default WFI power value needed
+ * by some governors
+ */
+#define ARM_CPUIDLE_WFI_STATE ARM_CPUIDLE_WFI_STATE_PWR(UINT_MAX)
+
+#endif
diff --git a/arch/arm/include/asm/cputime.h b/arch/arm/include/asm/cputime.h
deleted file mode 100644
index 3a8002a5fec..00000000000
--- a/arch/arm/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ARM_CPUTIME_H
-#define __ARM_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __ARM_CPUTIME_H */
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 20ae96cc002..8c2b7321a47 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -2,12 +2,32 @@
 #define __ASM_ARM_CPUTYPE_H
 
 #include <linux/stringify.h>
+#include <linux/kernel.h>
 
 #define CPUID_ID	0
 #define CPUID_CACHETYPE	1
 #define CPUID_TCM	2
 #define CPUID_TLBTYPE	3
+#define CPUID_MPUIR	4
+#define CPUID_MPIDR	5
+#define CPUID_REVIDR	6
 
+#ifdef CONFIG_CPU_V7M
+#define CPUID_EXT_PFR0	0x40
+#define CPUID_EXT_PFR1	0x44
+#define CPUID_EXT_DFR0	0x48
+#define CPUID_EXT_AFR0	0x4c
+#define CPUID_EXT_MMFR0	0x50
+#define CPUID_EXT_MMFR1	0x54
+#define CPUID_EXT_MMFR2	0x58
+#define CPUID_EXT_MMFR3	0x5c
+#define CPUID_EXT_ISAR0	0x60
+#define CPUID_EXT_ISAR1	0x64
+#define CPUID_EXT_ISAR2	0x68
+#define CPUID_EXT_ISAR3	0x6c
+#define CPUID_EXT_ISAR4	0x70
+#define CPUID_EXT_ISAR5	0x74
+#else
 #define CPUID_EXT_PFR0	"c1, 0"
 #define CPUID_EXT_PFR1	"c1, 1"
 #define CPUID_EXT_DFR0	"c1, 2"
@@ -22,6 +42,44 @@
 #define CPUID_EXT_ISAR3	"c2, 3"
 #define CPUID_EXT_ISAR4	"c2, 4"
 #define CPUID_EXT_ISAR5	"c2, 5"
+#endif
+
+#define MPIDR_SMP_BITMASK (0x3 << 30)
+#define MPIDR_SMP_VALUE (0x2 << 30)
+
+#define MPIDR_MT_BITMASK (0x1 << 24)
+
+#define MPIDR_HWID_BITMASK 0xFFFFFF
+
+#define MPIDR_INVALID (~MPIDR_HWID_BITMASK)
+
+#define MPIDR_LEVEL_BITS 8
+#define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1)
+
+#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
+	((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK)
+
+#define ARM_CPU_IMP_ARM			0x41
+#define ARM_CPU_IMP_INTEL		0x69
+
+#define ARM_CPU_PART_ARM1136		0xB360
+#define ARM_CPU_PART_ARM1156		0xB560
+#define ARM_CPU_PART_ARM1176		0xB760
+#define ARM_CPU_PART_ARM11MPCORE	0xB020
+#define ARM_CPU_PART_CORTEX_A8		0xC080
+#define ARM_CPU_PART_CORTEX_A9		0xC090
+#define ARM_CPU_PART_CORTEX_A5		0xC050
+#define ARM_CPU_PART_CORTEX_A15		0xC0F0
+#define ARM_CPU_PART_CORTEX_A7		0xC070
+#define ARM_CPU_PART_CORTEX_A12		0xC0D0
+#define ARM_CPU_PART_CORTEX_A17		0xC0E0
+
+#define ARM_CPU_XSCALE_ARCH_MASK	0xe000
+#define ARM_CPU_XSCALE_ARCH_V1		0x2000
+#define ARM_CPU_XSCALE_ARCH_V2		0x4000
+#define ARM_CPU_XSCALE_ARCH_V3		0x6000
+
+extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15
 #define read_cpuid(reg)							\
@@ -33,22 +91,56 @@
 		    : "cc");						\
 		__val;							\
 	})
+
+/*
+ * The memory clobber prevents gcc 4.5 from reordering the mrc before
+ * any is_smp() tests, which can cause undefined instruction aborts on
+ * ARM1136 r0 due to the missing extended CP15 registers.
+ */
 #define read_cpuid_ext(ext_reg)						\
 	({								\
 		unsigned int __val;					\
 		asm("mrc	p15, 0, %0, c0, " ext_reg		\
 		    : "=r" (__val)					\
 		    :							\
-		    : "cc");						\
+		    : "memory");					\
 		__val;							\
 	})
-#else
-extern unsigned int processor_id;
-#define read_cpuid(reg) (processor_id)
-#define read_cpuid_ext(reg) 0
-#endif
+
+#elif defined(CONFIG_CPU_V7M)
+
+#include <asm/io.h>
+#include <asm/v7m.h>
+
+#define read_cpuid(reg)							\
+	({								\
+		WARN_ON_ONCE(1);					\
+		0;							\
+	})
+
+static inline unsigned int __attribute_const__ read_cpuid_ext(unsigned offset)
+{
+	return readl(BASEADDR_V7M_SCB + offset);
+}
+
+#else /* ifdef CONFIG_CPU_CP15 / elif defined (CONFIG_CPU_V7M) */
 
 /*
+ * read_cpuid and read_cpuid_ext should only ever be called on machines that
+ * have cp15 so warn on other usages.
+ */
+#define read_cpuid(reg)							\
+	({								\
+		WARN_ON_ONCE(1);					\
+		0;							\
+	})
+
+#define read_cpuid_ext(reg) read_cpuid(reg)
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
+#ifdef CONFIG_CPU_CP15
+/*
  * The CPU ID never changes at run time, so we might as well tell the
  * compiler that it's constant.  Use this function to read the CPU ID
  * rather than directly reading processor_id or read_cpuid() directly.
@@ -58,6 +150,37 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void)
 	return read_cpuid(CPUID_ID);
 }
 
+#elif defined(CONFIG_CPU_V7M)
+
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return readl(BASEADDR_V7M_SCB + V7M_SCB_CPUID);
+}
+
+#else /* ifdef CONFIG_CPU_CP15 / elif defined(CONFIG_CPU_V7M) */
+
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return processor_id;
+}
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
+static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
+{
+	return (read_cpuid_id() & 0xFF000000) >> 24;
+}
+
+static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
+{
+	return read_cpuid_id() & 0xFFF0;
+}
+
+static inline unsigned int __attribute_const__ xscale_cpu_arch_version(void)
+{
+	return read_cpuid_part_number() & ARM_CPU_XSCALE_ARCH_MASK;
+}
+
 static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
 {
 	return read_cpuid(CPUID_CACHETYPE);
@@ -68,6 +191,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
 	return read_cpuid(CPUID_TCM);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mpidr(void)
+{
+	return read_cpuid(CPUID_MPIDR);
+}
+
 /*
  * Intel's XScale3 core supports some v6 features (supersections, L2)
  * but advertises itself as v5 as it does not support the v6 ISA.  For
@@ -94,4 +222,23 @@ static inline int cpu_is_xsc3(void)
 #define	cpu_is_xscale()	1
 #endif
 
+/*
+ * Marvell's PJ4 and PJ4B cores are based on V7 version,
+ * but require a specical sequence for enabling coprocessors.
+ * For this reason, we need a way to distinguish them.
+ */
+#if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B)
+static inline int cpu_is_pj4(void)
+{
+	unsigned int id;
+
+	id = read_cpuid_id();
+	if ((id & 0xff0fff00) == 0x560f5800)
+		return 1;
+
+	return 0;
+}
+#else
+#define cpu_is_pj4()	0
+#endif
 #endif
diff --git a/arch/arm/include/asm/cti.h b/arch/arm/include/asm/cti.h
new file mode 100644
index 00000000000..2381199acb7
--- /dev/null
+++ b/arch/arm/include/asm/cti.h
@@ -0,0 +1,159 @@
+#ifndef __ASMARM_CTI_H
+#define __ASMARM_CTI_H
+
+#include	<asm/io.h>
+#include	<asm/hardware/coresight.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
+
+/**
+ * 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)
+{
+	__raw_writel(CS_LAR_KEY, cti->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)
+{
+	__raw_writel(~CS_LAR_KEY, cti->base + LOCKACCESS);
+}
+#endif
diff --git a/arch/arm/include/asm/current.h b/arch/arm/include/asm/current.h
deleted file mode 100644
index 75d21e2a3ff..00000000000
--- a/arch/arm/include/asm/current.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef _ASMARM_CURRENT_H
-#define _ASMARM_CURRENT_H
-
-#include <linux/thread_info.h>
-
-static inline struct task_struct *get_current(void) __attribute_const__;
-
-static inline struct task_struct *get_current(void)
-{
-	return current_thread_info()->task;
-}
-
-#define current (get_current())
-
-#endif /* _ASMARM_CURRENT_H */
diff --git a/arch/arm/include/asm/dcc.h b/arch/arm/include/asm/dcc.h
new file mode 100644
index 00000000000..b74899de077
--- /dev/null
+++ b/arch/arm/include/asm/dcc.h
@@ -0,0 +1,41 @@
+/* Copyright (c) 2010, 2014 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only 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.
+ */
+
+#include <asm/barrier.h>
+
+static inline u32 __dcc_getstatus(void)
+{
+	u32 __ret;
+	asm volatile("mrc p14, 0, %0, c0, c1, 0	@ read comms ctrl reg"
+		: "=r" (__ret) : : "cc");
+
+	return __ret;
+}
+
+static inline char __dcc_getchar(void)
+{
+	char __c;
+
+	asm volatile("mrc p14, 0, %0, c0, c5, 0	@ read comms data reg"
+		: "=r" (__c));
+	isb();
+
+	return __c;
+}
+
+static inline void __dcc_putchar(char c)
+{
+	asm volatile("mcr p14, 0, %0, c0, c5, 0	@ write a char"
+		: /* no output register */
+		: "r" (c));
+	isb();
+}
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index b2deda18154..dff714d886d 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -6,9 +6,28 @@
 #ifndef __ASM_ARM_DELAY_H
 #define __ASM_ARM_DELAY_H
 
+#include <asm/memory.h>
 #include <asm/param.h>	/* HZ */
 
-extern void __delay(int loops);
+#define MAX_UDELAY_MS	2
+#define UDELAY_MULT	((UL(2199023) * HZ) >> 11)
+#define UDELAY_SHIFT	30
+
+#ifndef __ASSEMBLY__
+
+struct delay_timer {
+	unsigned long (*read_current_timer)(void);
+	unsigned long freq;
+};
+
+extern struct arm_delay_ops {
+	void (*delay)(unsigned long);
+	void (*const_udelay)(unsigned long);
+	void (*udelay)(unsigned long);
+	unsigned long ticks_per_jiffy;
+} arm_delay_ops;
+
+#define __delay(n)		arm_delay_ops.delay(n)
 
 /*
  * This function intentionally does not exist; if you see references to
@@ -23,22 +42,31 @@ extern void __bad_udelay(void);
  * division by multiplication: you don't have to worry about
  * loss of precision.
  *
- * Use only for very small delays ( < 1 msec).  Should probably use a
+ * Use only for very small delays ( < 2 msec).  Should probably use a
  * lookup table, really, as the multiplications take much too long with
  * short delays.  This is a "reasonable" implementation, though (and the
  * first constant multiplications gets optimized away if the delay is
  * a constant)
  */
-extern void __udelay(unsigned long usecs);
-extern void __const_udelay(unsigned long);
-
-#define MAX_UDELAY_MS 2
+#define __udelay(n)		arm_delay_ops.udelay(n)
+#define __const_udelay(n)	arm_delay_ops.const_udelay(n)
 
 #define udelay(n)							\
 	(__builtin_constant_p(n) ?					\
 	  ((n) > (MAX_UDELAY_MS * 1000) ? __bad_udelay() :		\
-			__const_udelay((n) * ((2199023U*HZ)>>11))) :	\
+			__const_udelay((n) * UDELAY_MULT)) :		\
 	  __udelay(n))
 
+/* Loop-based definitions for assembly code. */
+extern void __loop_delay(unsigned long loops);
+extern void __loop_udelay(unsigned long usecs);
+extern void __loop_const_udelay(unsigned long);
+
+/* Delay-loop timer registration. */
+#define ARCH_HAS_READ_CURRENT_TIMER
+extern void register_current_timer_delay(const struct delay_timer *timer);
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* defined(_ARM_DELAY_H) */
 
diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
index 9f390ce335c..dc662fca923 100644
--- a/arch/arm/include/asm/device.h
+++ b/arch/arm/include/asm/device.h
@@ -7,12 +7,30 @@
 #define ASMARM_DEVICE_H
 
 struct dev_archdata {
+	struct dma_map_ops	*dma_ops;
 #ifdef CONFIG_DMABOUNCE
 	struct dmabounce_device_info *dmabounce;
 #endif
+#ifdef CONFIG_IOMMU_API
+	void *iommu; /* private IOMMU data */
+#endif
+#ifdef CONFIG_ARM_DMA_USE_IOMMU
+	struct dma_iommu_mapping	*mapping;
+#endif
 };
 
+struct omap_device;
+
 struct pdev_archdata {
+#ifdef CONFIG_ARCH_OMAP
+	struct omap_device *od;
+#endif
 };
 
+#ifdef CONFIG_ARM_DMA_USE_IOMMU
+#define to_dma_iommu_mapping(dev) ((dev)->archdata.mapping)
+#else
+#define to_dma_iommu_mapping(dev) NULL
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
index d3f0a9eee9f..662c7bd0610 100644
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@@ -1,8 +1,8 @@
 #ifndef __ASM_ARM_DIV64
 #define __ASM_ARM_DIV64
 
-#include <asm/system.h>
 #include <linux/types.h>
+#include <asm/compiler.h>
 
 /*
  * The semantics of do_div() are:
@@ -46,7 +46,7 @@
 	__rem;							\
 })
 
-#if __GNUC__ < 4
+#if __GNUC__ < 4 || !defined(CONFIG_AEABI)
 
 /*
  * gcc versions earlier than 4.0 are simply too problematic for the
@@ -156,7 +156,7 @@
 		/* Select the best insn combination to perform the   */	\
 		/* actual __m * __n / (__p << 64) operation.         */	\
 		if (!__c) {						\
-			asm (	"umull	%Q0, %R0, %1, %Q2\n\t"		\
+			asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"		\
 				"mov	%Q0, #0"			\
 				: "=&r" (__res)				\
 				: "r" (__m), "r" (__n)			\
diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
new file mode 100644
index 00000000000..4f8e9e5514b
--- /dev/null
+++ b/arch/arm/include/asm/dma-contiguous.h
@@ -0,0 +1,14 @@
+#ifndef ASMARM_DMA_CONTIGUOUS_H
+#define ASMARM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_DMA_CMA
+
+#include <linux/types.h>
+
+void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
+
+#endif
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
new file mode 100644
index 00000000000..8e3fcb924db
--- /dev/null
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -0,0 +1,37 @@
+#ifndef ASMARM_DMA_IOMMU_H
+#define ASMARM_DMA_IOMMU_H
+
+#ifdef __KERNEL__
+
+#include <linux/mm_types.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
+#include <linux/kmemcheck.h>
+#include <linux/kref.h>
+
+struct dma_iommu_mapping {
+	/* iommu specific data */
+	struct iommu_domain	*domain;
+
+	unsigned long		**bitmaps;	/* array of bitmaps */
+	unsigned int		nr_bitmaps;	/* nr of elements in array */
+	unsigned int		extensions;
+	size_t			bitmap_size;	/* size of a single bitmap */
+	size_t			bits;		/* per bitmap */
+	dma_addr_t		base;
+
+	spinlock_t		lock;
+	struct kref		kref;
+};
+
+struct dma_iommu_mapping *
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size);
+
+void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping);
+
+int arm_iommu_attach_device(struct device *dev,
+					struct dma_iommu_mapping *mapping);
+void arm_iommu_detach_device(struct device *dev);
+
+#endif /* __KERNEL__ */
+#endif
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index c568da7dcae..c45b61a4b4a 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -5,44 +5,102 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-debug.h>
 
 #include <asm-generic/dma-coherent.h>
 #include <asm/memory.h>
 
+#include <xen/xen.h>
+#include <asm/xen/hypervisor.h>
+
+#define DMA_ERROR_CODE	(~0)
+extern struct dma_map_ops arm_dma_ops;
+extern struct dma_map_ops arm_coherent_dma_ops;
+
+static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
+{
+	if (dev && dev->archdata.dma_ops)
+		return dev->archdata.dma_ops;
+	return &arm_dma_ops;
+}
+
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (xen_initial_domain())
+		return xen_dma_ops;
+	else
+		return __generic_dma_ops(dev);
+}
+
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+	BUG_ON(!dev);
+	dev->archdata.dma_ops = ops;
+}
+
+#include <asm-generic/dma-mapping-common.h>
+
+static inline int dma_set_mask(struct device *dev, u64 mask)
+{
+	return get_dma_ops(dev)->set_dma_mask(dev, mask);
+}
+
+#ifdef __arch_page_to_dma
+#error Please update to __arch_pfn_to_dma
+#endif
+
 /*
- * page_to_dma/dma_to_virt/virt_to_dma are architecture private functions
- * used internally by the DMA-mapping API to provide DMA addresses. They
- * must not be used by drivers.
+ * dma_to_pfn/pfn_to_dma/dma_to_virt/virt_to_dma are architecture private
+ * functions used internally by the DMA-mapping API to provide DMA
+ * addresses. They must not be used by drivers.
  */
-#ifndef __arch_page_to_dma
-static inline dma_addr_t page_to_dma(struct device *dev, struct page *page)
+#ifndef __arch_pfn_to_dma
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-	return (dma_addr_t)__pfn_to_bus(page_to_pfn(page));
+	if (dev)
+		pfn -= dev->dma_pfn_offset;
+	return (dma_addr_t)__pfn_to_bus(pfn);
 }
 
-static inline struct page *dma_to_page(struct device *dev, dma_addr_t addr)
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
-	return pfn_to_page(__bus_to_pfn(addr));
+	unsigned long pfn = __bus_to_pfn(addr);
+
+	if (dev)
+		pfn += dev->dma_pfn_offset;
+
+	return pfn;
 }
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
 {
-	return (void *)__bus_to_virt(addr);
+	if (dev) {
+		unsigned long pfn = dma_to_pfn(dev, addr);
+
+		return phys_to_virt(__pfn_to_phys(pfn));
+	}
+
+	return (void *)__bus_to_virt((unsigned long)addr);
 }
 
 static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 {
+	if (dev)
+		return pfn_to_dma(dev, virt_to_pfn(addr));
+
 	return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
 }
+
 #else
-static inline dma_addr_t page_to_dma(struct device *dev, struct page *page)
+static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-	return __arch_page_to_dma(dev, page);
+	return __arch_pfn_to_dma(dev, pfn);
 }
 
-static inline struct page *dma_to_page(struct device *dev, dma_addr_t addr)
+static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
-	return __arch_dma_to_page(dev, addr);
+	return __arch_dma_to_pfn(dev, addr);
 }
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
@@ -56,100 +114,60 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 }
 #endif
 
-/*
- * The DMA API is built upon the notion of "buffer ownership".  A buffer
- * is either exclusively owned by the CPU (and therefore may be accessed
- * by it) or exclusively owned by the DMA device.  These helper functions
- * represent the transitions between these two ownership states.
- *
- * Note, however, that on later ARMs, this notion does not work due to
- * speculative prefetches.  We model our approach on the assumption that
- * the CPU does do speculative prefetches, which means we clean caches
- * before transfers and delay cache invalidation until transfer completion.
- *
- * Private support functions: these are not part of the API and are
- * liable to change.  Drivers must not use these.
- */
-static inline void __dma_single_cpu_to_dev(const void *kaddr, size_t size,
-	enum dma_data_direction dir)
+/* The ARM override for dma_max_pfn() */
+static inline unsigned long dma_max_pfn(struct device *dev)
 {
-	extern void ___dma_single_cpu_to_dev(const void *, size_t,
-		enum dma_data_direction);
-
-	if (!arch_is_coherent())
-		___dma_single_cpu_to_dev(kaddr, size, dir);
+	return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask);
 }
+#define dma_max_pfn(dev) dma_max_pfn(dev)
 
-static inline void __dma_single_dev_to_cpu(const void *kaddr, size_t size,
-	enum dma_data_direction dir)
+static inline int set_arch_dma_coherent_ops(struct device *dev)
 {
-	extern void ___dma_single_dev_to_cpu(const void *, size_t,
-		enum dma_data_direction);
-
-	if (!arch_is_coherent())
-		___dma_single_dev_to_cpu(kaddr, size, dir);
+	set_dma_ops(dev, &arm_coherent_dma_ops);
+	return 0;
 }
+#define set_arch_dma_coherent_ops(dev)	set_arch_dma_coherent_ops(dev)
 
-static inline void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
-	size_t size, enum dma_data_direction dir)
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	extern void ___dma_page_cpu_to_dev(struct page *, unsigned long,
-		size_t, enum dma_data_direction);
-
-	if (!arch_is_coherent())
-		___dma_page_cpu_to_dev(page, off, size, dir);
+	unsigned int offset = paddr & ~PAGE_MASK;
+	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
 }
 
-static inline void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
-	size_t size, enum dma_data_direction dir)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
-	extern void ___dma_page_dev_to_cpu(struct page *, unsigned long,
-		size_t, enum dma_data_direction);
-
-	if (!arch_is_coherent())
-		___dma_page_dev_to_cpu(page, off, size, dir);
+	unsigned int offset = dev_addr & ~PAGE_MASK;
+	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
 }
 
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask
- * to this function.
- *
- * FIXME: This should really be a platform specific issue - we should
- * return false if GFP_DMA allocations may not satisfy the supplied 'mask'.
- */
-static inline int dma_supported(struct device *dev, u64 mask)
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
-	if (mask < ISA_DMA_THRESHOLD)
+	u64 limit, mask;
+
+	if (!dev->dma_mask)
 		return 0;
-	return 1;
-}
 
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-#ifdef CONFIG_DMABOUNCE
-	if (dev->archdata.dmabounce) {
-		if (dma_mask >= ISA_DMA_THRESHOLD)
-			return 0;
-		else
-			return -EIO;
-	}
-#endif
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
+	mask = *dev->dma_mask;
 
-	*dev->dma_mask = dma_mask;
+	limit = (mask + 1) & ~mask;
+	if (limit && size > limit)
+		return 0;
 
-	return 0;
+	if ((addr | (addr + size - 1)) & ~mask)
+		return 0;
+
+	return 1;
 }
 
+static inline void dma_mark_clean(void *addr, size_t size) { }
+
 /*
  * DMA errors are defined by all-bits-set in the DMA address.
  */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-	return dma_addr == ~0;
+	debug_dma_mapping_error(dev, dma_addr);
+	return dma_addr == DMA_ERROR_CODE;
 }
 
 /*
@@ -167,72 +185,109 @@ static inline void dma_free_noncoherent(struct device *dev, size_t size,
 {
 }
 
+extern int dma_supported(struct device *dev, u64 mask);
+
+extern int arm_dma_set_mask(struct device *dev, u64 dma_mask);
+
 /**
- * dma_alloc_coherent - allocate consistent memory for DMA
+ * arm_dma_alloc - allocate consistent memory for DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @size: required memory size
  * @handle: bus-specific DMA address
+ * @attrs: optinal attributes that specific mapping properties
  *
- * Allocate some uncached, unbuffered memory for a device for
- * performing DMA.  This function allocates pages, and will
- * return the CPU-viewed address, and sets @handle to be the
- * device-viewed address.
+ * Allocate some memory for a device for performing DMA.  This function
+ * allocates pages, and will return the CPU-viewed address, and sets @handle
+ * to be the device-viewed address.
  */
-extern void *dma_alloc_coherent(struct device *, size_t, dma_addr_t *, gfp_t);
+extern void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+			   gfp_t gfp, struct dma_attrs *attrs);
+
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag,
+				       struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *cpu_addr;
+	BUG_ON(!ops);
+
+	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+	return cpu_addr;
+}
 
 /**
- * dma_free_coherent - free memory allocated by dma_alloc_coherent
+ * arm_dma_free - free memory allocated by arm_dma_alloc
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @size: size of memory originally requested in dma_alloc_coherent
  * @cpu_addr: CPU-view address returned from dma_alloc_coherent
  * @handle: device-view address returned from dma_alloc_coherent
+ * @attrs: optinal attributes that specific mapping properties
  *
  * Free (and unmap) a DMA buffer previously allocated by
- * dma_alloc_coherent().
+ * arm_dma_alloc().
  *
  * References to memory and mappings associated with cpu_addr/handle
  * during and after this call executing are illegal.
  */
-extern void dma_free_coherent(struct device *, size_t, void *, dma_addr_t);
+extern void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
+			 dma_addr_t handle, struct dma_attrs *attrs);
+
+#define dma_free_coherent(d, s, c, h) dma_free_attrs(d, s, c, h, NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle,
+				     struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	ops->free(dev, size, cpu_addr, dma_handle, attrs);
+}
 
 /**
- * dma_mmap_coherent - map a coherent DMA allocation into user space
+ * arm_dma_mmap - map a coherent DMA allocation into user space
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @vma: vm_area_struct describing requested user mapping
  * @cpu_addr: kernel CPU-view address returned from dma_alloc_coherent
  * @handle: device-view address returned from dma_alloc_coherent
  * @size: size of memory originally requested in dma_alloc_coherent
+ * @attrs: optinal attributes that specific mapping properties
  *
  * Map a coherent DMA buffer previously allocated by dma_alloc_coherent
  * into user space.  The coherent DMA buffer must not be freed by the
  * driver until the user space mapping has been released.
  */
-int dma_mmap_coherent(struct device *, struct vm_area_struct *,
-		void *, dma_addr_t, size_t);
-
-
-/**
- * dma_alloc_writecombine - allocate writecombining memory for DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: required memory size
- * @handle: bus-specific DMA address
- *
- * Allocate some uncached, buffered memory for a device for
- * performing DMA.  This function allocates pages, and will
- * return the CPU-viewed address, and sets @handle to be the
- * device-viewed address.
- */
-extern void *dma_alloc_writecombine(struct device *, size_t, dma_addr_t *,
-		gfp_t);
+extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+			void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			struct dma_attrs *attrs);
 
-#define dma_free_writecombine(dev,size,cpu_addr,handle) \
-	dma_free_coherent(dev,size,cpu_addr,handle)
+static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_alloc_attrs(dev, size, dma_handle, flag, &attrs);
+}
 
-int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
-		void *, dma_addr_t, size_t);
+static inline void dma_free_writecombine(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs);
+}
 
+/*
+ * This can be called during early boot to increase the size of the atomic
+ * coherent DMA pool above the default value of 256KiB. It must be called
+ * before postcore_initcall.
+ */
+extern void __init init_dma_coherent_pool_size(unsigned long size);
 
-#ifdef CONFIG_DMABOUNCE
 /*
  * For SA-1111, IXP425, and ADI systems  the dma-mapping functions are "magic"
  * and utilize bounce buffers as needed to work around limited DMA windows.
@@ -251,14 +306,14 @@ int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
  * @dev: valid struct device pointer
  * @small_buf_size: size of buffers to use with small buffer pool
  * @large_buf_size: size of buffers to use with large buffer pool (can be 0)
+ * @needs_bounce_fn: called to determine whether buffer needs bouncing
  *
  * This function should be called by low-level platform code to register
  * a device as requireing DMA buffer bouncing. The function will allocate
  * appropriate DMA pools for the device.
- *
  */
 extern int dmabounce_register_dev(struct device *, unsigned long,
-		unsigned long);
+		unsigned long, int (*)(struct device *, dma_addr_t, size_t));
 
 /**
  * dmabounce_unregister_dev
@@ -272,213 +327,22 @@ extern int dmabounce_register_dev(struct device *, unsigned long,
  */
 extern void dmabounce_unregister_dev(struct device *);
 
-/**
- * dma_needs_bounce
- *
- * @dev: valid struct device pointer
- * @dma_handle: dma_handle of unbounced buffer
- * @size: size of region being mapped
- *
- * Platforms that utilize the dmabounce mechanism must implement
- * this function.
- *
- * The dmabounce routines call this function whenever a dma-mapping
- * is requested to determine whether a given buffer needs to be bounced
- * or not. The function must return 0 if the buffer is OK for
- * DMA access and 1 if the buffer needs to be bounced.
- *
- */
-extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
-
-/*
- * The DMA API, implemented by dmabounce.c.  See below for descriptions.
- */
-extern dma_addr_t dma_map_single(struct device *, void *, size_t,
-		enum dma_data_direction);
-extern void dma_unmap_single(struct device *, dma_addr_t, size_t,
-		enum dma_data_direction);
-extern dma_addr_t dma_map_page(struct device *, struct page *,
-		unsigned long, size_t, enum dma_data_direction);
-extern void dma_unmap_page(struct device *, dma_addr_t, size_t,
-		enum dma_data_direction);
-
-/*
- * Private functions
- */
-int dmabounce_sync_for_cpu(struct device *, dma_addr_t, unsigned long,
-		size_t, enum dma_data_direction);
-int dmabounce_sync_for_device(struct device *, dma_addr_t, unsigned long,
-		size_t, enum dma_data_direction);
-#else
-static inline int dmabounce_sync_for_cpu(struct device *d, dma_addr_t addr,
-	unsigned long offset, size_t size, enum dma_data_direction dir)
-{
-	return 1;
-}
-
-static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
-	unsigned long offset, size_t size, enum dma_data_direction dir)
-{
-	return 1;
-}
-
-
-/**
- * dma_map_single - map a single buffer for streaming DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @cpu_addr: CPU direct mapped address of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Ensure that any data held in the cache is appropriately discarded
- * or written back.
- *
- * The device owns this memory once this call has completed.  The CPU
- * can regain ownership by calling dma_unmap_single() or
- * dma_sync_single_for_cpu().
- */
-static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-		size_t size, enum dma_data_direction dir)
-{
-	BUG_ON(!valid_dma_direction(dir));
-
-	__dma_single_cpu_to_dev(cpu_addr, size, dir);
-
-	return virt_to_dma(dev, cpu_addr);
-}
-
-/**
- * dma_map_page - map a portion of a page for streaming DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @page: page that buffer resides in
- * @offset: offset into page for start of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Ensure that any data held in the cache is appropriately discarded
- * or written back.
- *
- * The device owns this memory once this call has completed.  The CPU
- * can regain ownership by calling dma_unmap_page().
- */
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir)
-{
-	BUG_ON(!valid_dma_direction(dir));
-
-	__dma_page_cpu_to_dev(page, offset, size, dir);
-
-	return page_to_dma(dev, page) + offset;
-}
-
-/**
- * dma_unmap_single - unmap a single buffer previously mapped
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @size: size of buffer (same as passed to dma_map_single)
- * @dir: DMA transfer direction (same as passed to dma_map_single)
- *
- * Unmap a single streaming mode DMA translation.  The handle and size
- * must match what was provided in the previous dma_map_single() call.
- * All other usages are undefined.
- *
- * After this call, reads by the CPU to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	__dma_single_dev_to_cpu(dma_to_virt(dev, handle), size, dir);
-}
-
-/**
- * dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @size: size of buffer (same as passed to dma_map_page)
- * @dir: DMA transfer direction (same as passed to dma_map_page)
- *
- * Unmap a page streaming mode DMA translation.  The handle and size
- * must match what was provided in the previous dma_map_page() call.
- * All other usages are undefined.
- *
- * After this call, reads by the CPU to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-static inline void dma_unmap_page(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	__dma_page_dev_to_cpu(dma_to_page(dev, handle), handle & ~PAGE_MASK,
-		size, dir);
-}
-#endif /* CONFIG_DMABOUNCE */
-
-/**
- * dma_sync_single_range_for_cpu
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @offset: offset of region to start sync
- * @size: size of region to sync
- * @dir: DMA transfer direction (same as passed to dma_map_single)
- *
- * Make physical memory consistent for a single streaming mode DMA
- * translation after a transfer.
- *
- * If you perform a dma_map_single() but wish to interrogate the
- * buffer using the cpu, yet do not wish to teardown the PCI dma
- * mapping, you must call this function before doing so.  At the
- * next point you give the PCI dma address back to the card, you
- * must first the perform a dma_sync_for_device, and then the
- * device again owns the buffer.
- */
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t handle, unsigned long offset, size_t size,
-		enum dma_data_direction dir)
-{
-	BUG_ON(!valid_dma_direction(dir));
-
-	if (!dmabounce_sync_for_cpu(dev, handle, offset, size, dir))
-		return;
-
-	__dma_single_dev_to_cpu(dma_to_virt(dev, handle) + offset, size, dir);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t handle, unsigned long offset, size_t size,
-		enum dma_data_direction dir)
-{
-	BUG_ON(!valid_dma_direction(dir));
-
-	if (!dmabounce_sync_for_device(dev, handle, offset, size, dir))
-		return;
 
-	__dma_single_cpu_to_dev(dma_to_virt(dev, handle) + offset, size, dir);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	dma_sync_single_range_for_cpu(dev, handle, 0, size, dir);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	dma_sync_single_range_for_device(dev, handle, 0, size, dir);
-}
 
 /*
  * The scatter list versions of the above methods.
  */
-extern int dma_map_sg(struct device *, struct scatterlist *, int,
-		enum dma_data_direction);
-extern void dma_unmap_sg(struct device *, struct scatterlist *, int,
+extern int arm_dma_map_sg(struct device *, struct scatterlist *, int,
+		enum dma_data_direction, struct dma_attrs *attrs);
+extern void arm_dma_unmap_sg(struct device *, struct scatterlist *, int,
+		enum dma_data_direction, struct dma_attrs *attrs);
+extern void arm_dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
 		enum dma_data_direction);
-extern void dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
+extern void arm_dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
 		enum dma_data_direction);
-extern void dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
-		enum dma_data_direction);
-
+extern int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs);
 
 #endif /* __KERNEL__ */
 #endif
diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
index ca51143f97f..99084431d6a 100644
--- a/arch/arm/include/asm/dma.h
+++ b/arch/arm/include/asm/dma.h
@@ -1,13 +1,16 @@
 #ifndef __ASM_ARM_DMA_H
 #define __ASM_ARM_DMA_H
 
-#include <asm/memory.h>
-
 /*
  * This is the maximum virtual address which can be DMA'd from.
  */
-#ifndef MAX_DMA_ADDRESS
-#define MAX_DMA_ADDRESS	0xffffffff
+#ifndef CONFIG_ZONE_DMA
+#define MAX_DMA_ADDRESS	0xffffffffUL
+#else
+#define MAX_DMA_ADDRESS	({ \
+	extern phys_addr_t arm_dma_zone_size; \
+	arm_dma_zone_size && arm_dma_zone_size < (0x10000000 - PAGE_OFFSET) ? \
+		(PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; })
 #endif
 
 #ifdef CONFIG_ISA_DMA_API
@@ -16,7 +19,6 @@
  * It should not be re-used except for that purpose.
  */
 #include <linux/spinlock.h>
-#include <asm/system.h>
 #include <asm/scatterlist.h>
 
 #include <mach/isa-dma.h>
@@ -31,18 +33,18 @@
 #define DMA_MODE_CASCADE 0xc0
 #define DMA_AUTOINIT	 0x10
 
-extern spinlock_t  dma_spin_lock;
+extern raw_spinlock_t  dma_spin_lock;
 
 static inline unsigned long claim_dma_lock(void)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&dma_spin_lock, flags);
+	raw_spin_lock_irqsave(&dma_spin_lock, flags);
 	return flags;
 }
 
 static inline void release_dma_lock(unsigned long flags)
 {
-	spin_unlock_irqrestore(&dma_spin_lock, flags);
+	raw_spin_unlock_irqrestore(&dma_spin_lock, flags);
 }
 
 /* Clear the 'DMA Pointer Flip Flop'.
@@ -103,7 +105,7 @@ extern void set_dma_sg(unsigned int chan, struct scatterlist *sg, int nr_sg);
  */
 extern void __set_dma_addr(unsigned int chan, void *addr);
 #define set_dma_addr(chan, addr)				\
-	__set_dma_addr(chan, bus_to_virt(addr))
+	__set_dma_addr(chan, (void *)__bus_to_virt(addr))
 
 /* Set the DMA byte count for this channel
  *
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index cc7ef408071..6ddbe446425 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -10,6 +10,10 @@
 #ifndef __ASM_PROC_DOMAIN_H
 #define __ASM_PROC_DOMAIN_H
 
+#ifndef __ASSEMBLY__
+#include <asm/barrier.h>
+#endif
+
 /*
  * Domain numbers
  *
@@ -45,20 +49,24 @@
  */
 #define DOMAIN_NOACCESS	0
 #define DOMAIN_CLIENT	1
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define DOMAIN_MANAGER	3
+#else
+#define DOMAIN_MANAGER	1
+#endif
 
 #define domain_val(dom,type)	((type) << (2*(dom)))
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_MMU
-#define set_domain(x)					\
-	do {						\
-	__asm__ __volatile__(				\
-	"mcr	p15, 0, %0, c3, c0	@ set domain"	\
-	  : : "r" (x));					\
-	isb();						\
-	} while (0)
+#ifdef CONFIG_CPU_USE_DOMAINS
+static inline void set_domain(unsigned val)
+{
+	asm volatile(
+	"mcr	p15, 0, %0, c3, c0	@ set domain"
+	  : : "r" (val));
+	isb();
+}
 
 #define modify_domain(dom,type)					\
 	do {							\
@@ -70,9 +78,32 @@
 	} while (0)
 
 #else
-#define set_domain(x)		do { } while (0)
-#define modify_domain(dom,type)	do { } while (0)
+static inline void set_domain(unsigned val) { }
+static inline void modify_domain(unsigned dom, unsigned type)	{ }
 #endif
 
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions (inline assembly)
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define TUSER(instr)	#instr "t"
+#else
+#define TUSER(instr)	#instr
 #endif
-#endif /* !__ASSEMBLY__ */
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define TUSER(instr)	instr ## t
+#else
+#define TUSER(instr)	instr
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* !__ASM_PROC_DOMAIN_H */
diff --git a/arch/arm/include/asm/ecard.h b/arch/arm/include/asm/ecard.h
index 29f2610efc7..eaea14676d5 100644
--- a/arch/arm/include/asm/ecard.h
+++ b/arch/arm/include/asm/ecard.h
@@ -161,7 +161,6 @@ struct expansion_card {
 
 	/* Private internal data */
 	const char		*card_desc;	/* Card description		*/
-	CONST unsigned int	podaddr;	/* Base Linux address for card	*/
 	CONST loader_t		loader;		/* loader program */
 	u64			dma_mask;
 };
diff --git a/arch/arm/include/asm/edac.h b/arch/arm/include/asm/edac.h
new file mode 100644
index 00000000000..0df7a2c1fc3
--- /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/elf.h b/arch/arm/include/asm/elf.h
index 8bb66bca2e3..f4b46d39b9c 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -19,8 +19,6 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
 typedef struct user_fp elf_fpregset_t;
 
-#define EM_ARM	40
-
 #define EF_ARM_EABI_MASK	0xff000000
 #define EF_ARM_EABI_UNKNOWN	0x00000000
 #define EF_ARM_EABI_VER1	0x01000000
@@ -99,6 +97,8 @@ struct elf32_hdr;
 extern int elf_check_arch(const struct elf32_hdr *);
 #define elf_check_arch elf_check_arch
 
+#define vmcore_elf64_check_arch(x) (0)
+
 extern int arm_elf_read_implies_exec(const struct elf32_hdr *, int);
 #define elf_read_implies_exec(ex,stk) arm_elf_read_implies_exec(&(ex), stk)
 
@@ -106,6 +106,7 @@ struct task_struct;
 int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
 #define ELF_CORE_COPY_TASK_REGS dump_task_regs
 
+#define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	4096
 
 /* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
@@ -127,8 +128,10 @@ struct mm_struct;
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
-extern int vectors_user_mapping(void);
-#define arch_setup_additional_pages(bprm, uses_interp) vectors_user_mapping()
-#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+#ifdef CONFIG_MMU
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+int arch_setup_additional_pages(struct linux_binprm *, int);
+#endif
 
 #endif
diff --git a/arch/arm/include/asm/emergency-restart.h b/arch/arm/include/asm/emergency-restart.h
deleted file mode 100644
index 108d8c48e42..00000000000
--- a/arch/arm/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
new file mode 100644
index 00000000000..88d61815f0c
--- /dev/null
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -0,0 +1,39 @@
+#include <asm/assembler.h>
+
+/*
+ * Interrupt handling.  Preserves r7, r8, r9
+ */
+	.macro	arch_irq_handler_default
+	get_irqnr_preamble r6, lr
+1:	get_irqnr_and_base r0, r2, r6, lr
+	movne	r1, sp
+	@
+	@ routine called with r0 = irq number, r1 = struct pt_regs *
+	@
+	adrne	lr, BSYM(1b)
+	bne	asm_do_IRQ
+
+#ifdef CONFIG_SMP
+	/*
+	 * XXX
+	 *
+	 * this macro assumes that irqstat (r2) and base (r6) are
+	 * preserved from get_irqnr_and_base above
+	 */
+	ALT_SMP(test_for_ipi r0, r2, r6, lr)
+	ALT_UP_B(9997f)
+	movne	r1, sp
+	adrne	lr, BSYM(1b)
+	bne	do_IPI
+#endif
+9997:
+	.endm
+
+	.macro	arch_irq_handler, symbol_name
+	.align	5
+	.global \symbol_name
+\symbol_name:
+	mov	r8, lr
+	arch_irq_handler_default
+	mov     pc, r8
+	.endm
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 3ceb85e4385..00000000000
--- 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/errno.h b/arch/arm/include/asm/errno.h
deleted file mode 100644
index 6e60f0612bb..00000000000
--- a/arch/arm/include/asm/errno.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ARM_ERRNO_H
-#define _ARM_ERRNO_H
-
-#include <asm-generic/errno.h>
-
-#endif
diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h
new file mode 100644
index 00000000000..5abaf5bbd98
--- /dev/null
+++ b/arch/arm/include/asm/exception.h
@@ -0,0 +1,19 @@
+/*
+ * Annotations for marking C functions as exception handlers.
+ *
+ * These should only be used for C functions that are called from the low
+ * level exception entry code and not any intervening C code.
+ */
+#ifndef __ASM_ARM_EXCEPTION_H
+#define __ASM_ARM_EXCEPTION_H
+
+#include <linux/ftrace.h>
+
+#define __exception	__attribute__((section(".exception.text")))
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry	__irq_entry
+#else
+#define __exception_irq_entry	__exception
+#endif
+
+#endif /* __ASM_ARM_EXCEPTION_H */
diff --git a/arch/arm/include/asm/fiq.h b/arch/arm/include/asm/fiq.h
index 2242ce22ec6..d493d0b742a 100644
--- a/arch/arm/include/asm/fiq.h
+++ b/arch/arm/include/asm/fiq.h
@@ -4,6 +4,13 @@
  * Support for FIQ on ARM architectures.
  * Written by Philip Blundell <philb@gnu.org>, 1998
  * Re-written by Russell King
+ *
+ * NOTE: The FIQ mode registers are not magically preserved across
+ * suspend/resume.
+ *
+ * Drivers which require these registers to be preserved across power
+ * management operations must implement appropriate suspend/resume handlers to
+ * save and restore them.
  */
 
 #ifndef __ASM_FIQ_H
@@ -29,9 +36,21 @@ struct fiq_handler {
 extern int claim_fiq(struct fiq_handler *f);
 extern void release_fiq(struct fiq_handler *f);
 extern void set_fiq_handler(void *start, unsigned int length);
-extern void set_fiq_regs(struct pt_regs *regs);
-extern void get_fiq_regs(struct pt_regs *regs);
 extern void enable_fiq(int fiq);
 extern void disable_fiq(int fiq);
 
+/* helpers defined in fiqasm.S: */
+extern void __set_fiq_regs(unsigned long const *regs);
+extern void __get_fiq_regs(unsigned long *regs);
+
+static inline void set_fiq_regs(struct pt_regs const *regs)
+{
+	__set_fiq_regs(&regs->ARM_r8);
+}
+
+static inline void get_fiq_regs(struct pt_regs *regs)
+{
+	__get_fiq_regs(&regs->ARM_r8);
+}
+
 #endif
diff --git a/arch/arm/include/asm/firmware.h b/arch/arm/include/asm/firmware.h
new file mode 100644
index 00000000000..2c9f10df756
--- /dev/null
+++ b/arch/arm/include/asm/firmware.h
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2012 Samsung Electronics.
+ * Kyungmin Park <kyungmin.park@samsung.com>
+ * Tomasz Figa <t.figa@samsung.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.
+ */
+
+#ifndef __ASM_ARM_FIRMWARE_H
+#define __ASM_ARM_FIRMWARE_H
+
+#include <linux/bug.h>
+
+/*
+ * struct firmware_ops
+ *
+ * A structure to specify available firmware operations.
+ *
+ * A filled up structure can be registered with register_firmware_ops().
+ */
+struct firmware_ops {
+	/*
+	 * Inform the firmware we intend to enter CPU idle mode
+	 */
+	int (*prepare_idle)(void);
+	/*
+	 * Enters CPU idle mode
+	 */
+	int (*do_idle)(void);
+	/*
+	 * Sets boot address of specified physical CPU
+	 */
+	int (*set_cpu_boot_addr)(int cpu, unsigned long boot_addr);
+	/*
+	 * Boots specified physical CPU
+	 */
+	int (*cpu_boot)(int cpu);
+	/*
+	 * Initializes L2 cache
+	 */
+	int (*l2x0_init)(void);
+};
+
+/* Global pointer for current firmware_ops structure, can't be NULL. */
+extern const struct firmware_ops *firmware_ops;
+
+/*
+ * call_firmware_op(op, ...)
+ *
+ * Checks if firmware operation is present and calls it,
+ * otherwise returns -ENOSYS
+ */
+#define call_firmware_op(op, ...)					\
+	((firmware_ops->op) ? firmware_ops->op(__VA_ARGS__) : (-ENOSYS))
+
+/*
+ * register_firmware_ops(ops)
+ *
+ * A function to register platform firmware_ops struct.
+ */
+static inline void register_firmware_ops(const struct firmware_ops *ops)
+{
+	BUG_ON(!ops);
+
+	firmware_ops = ops;
+}
+
+#endif
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index bbae919bceb..74124b0d0d7 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -1,24 +1,11 @@
 #ifndef _ASM_FIXMAP_H
 #define _ASM_FIXMAP_H
 
-/*
- * Nothing too fancy for now.
- *
- * On ARM we already have well known fixed virtual addresses imposed by
- * the architecture such as the vector page which is located at 0xffff0000,
- * therefore a second level page table is already allocated covering
- * 0xfff00000 upwards.
- *
- * The cache flushing code in proc-xscale.S uses the virtual area between
- * 0xfffe0000 and 0xfffeffff.
- */
-
-#define FIXADDR_START		0xfff00000UL
-#define FIXADDR_TOP		0xfffe0000UL
+#define FIXADDR_START		0xffc00000UL
+#define FIXADDR_TOP		0xffe00000UL
 #define FIXADDR_SIZE		(FIXADDR_TOP - FIXADDR_START)
 
-#define FIX_KMAP_BEGIN		0
-#define FIX_KMAP_END		(FIXADDR_SIZE >> PAGE_SHIFT)
+#define FIX_KMAP_NR_PTES	(FIXADDR_SIZE >> PAGE_SHIFT)
 
 #define __fix_to_virt(x)	(FIXADDR_START + ((x) << PAGE_SHIFT))
 #define __virt_to_fix(x)	(((x) - FIXADDR_START) >> PAGE_SHIFT)
@@ -27,7 +14,7 @@ extern void __this_fixmap_does_not_exist(void);
 
 static inline unsigned long fix_to_virt(const unsigned int idx)
 {
-	if (idx >= FIX_KMAP_END)
+	if (idx >= FIX_KMAP_NR_PTES)
 		__this_fixmap_does_not_exist();
 	return __fix_to_virt(idx);
 }
diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h
index 59426a4595c..e847d23351e 100644
--- a/arch/arm/include/asm/flat.h
+++ b/arch/arm/include/asm/flat.h
@@ -8,7 +8,7 @@
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
-#define	flat_get_addr_from_rp(rp, relval, flags, persistent) get_unaligned(rp)
+#define	flat_get_addr_from_rp(rp, relval, flags, persistent) ((void)persistent,get_unaligned(rp))
 #define	flat_put_addr_at_rp(rp, val, relval)	put_unaligned(val,rp)
 #define	flat_get_relocate_addr(rel)		(rel)
 #define	flat_set_persistent(relval, p)		0
diff --git a/arch/arm/include/asm/floppy.h b/arch/arm/include/asm/floppy.h
index c9f03eccc9d..f4882553fbb 100644
--- a/arch/arm/include/asm/floppy.h
+++ b/arch/arm/include/asm/floppy.h
@@ -25,7 +25,7 @@
 
 #define fd_inb(port)		inb((port))
 #define fd_request_irq()	request_irq(IRQ_FLOPPYDISK,floppy_interrupt,\
-					    IRQF_DISABLED,"floppy",NULL)
+					    0,"floppy",NULL)
 #define fd_free_irq()		free_irq(IRQ_FLOPPYDISK,NULL)
 #define fd_disable_irq()	disable_irq(IRQ_FLOPPYDISK)
 #define fd_enable_irq()		enable_irq(IRQ_FLOPPYDISK)
diff --git a/arch/arm/include/asm/fncpy.h b/arch/arm/include/asm/fncpy.h
new file mode 100644
index 00000000000..de535474692
--- /dev/null
+++ b/arch/arm/include/asm/fncpy.h
@@ -0,0 +1,94 @@
+/*
+ * arch/arm/include/asm/fncpy.h - helper macros for function body copying
+ *
+ * Copyright (C) 2011 Linaro Limited
+ *
+ * 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
+ */
+
+/*
+ * These macros are intended for use when there is a need to copy a low-level
+ * function body into special memory.
+ *
+ * For example, when reconfiguring the SDRAM controller, the code doing the
+ * reconfiguration may need to run from SRAM.
+ *
+ * NOTE: that the copied function body must be entirely self-contained and
+ * position-independent in order for this to work properly.
+ *
+ * NOTE: in order for embedded literals and data to get referenced correctly,
+ * the alignment of functions must be preserved when copying.  To ensure this,
+ * the source and destination addresses for fncpy() must be aligned to a
+ * multiple of 8 bytes: you will be get a BUG() if this condition is not met.
+ * You will typically need a ".align 3" directive in the assembler where the
+ * function to be copied is defined, and ensure that your allocator for the
+ * destination buffer returns 8-byte-aligned pointers.
+ *
+ * Typical usage example:
+ *
+ * extern int f(args);
+ * extern uint32_t size_of_f;
+ * int (*copied_f)(args);
+ * void *sram_buffer;
+ *
+ * copied_f = fncpy(sram_buffer, &f, size_of_f);
+ *
+ * ... later, call the function: ...
+ *
+ * copied_f(args);
+ *
+ * The size of the function to be copied can't be determined from C:
+ * this must be determined by other means, such as adding assmbler directives
+ * in the file where f is defined.
+ */
+
+#ifndef __ASM_FNCPY_H
+#define __ASM_FNCPY_H
+
+#include <linux/types.h>
+#include <linux/string.h>
+
+#include <asm/bug.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Minimum alignment requirement for the source and destination addresses
+ * for function copying.
+ */
+#define FNCPY_ALIGN 8
+
+#define fncpy(dest_buf, funcp, size) ({					\
+	uintptr_t __funcp_address;					\
+	typeof(funcp) __result;						\
+									\
+	asm("" : "=r" (__funcp_address) : "0" (funcp));			\
+									\
+	/*								\
+	 * Ensure alignment of source and destination addresses,	\
+	 * disregarding the function's Thumb bit:			\
+	 */								\
+	BUG_ON((uintptr_t)(dest_buf) & (FNCPY_ALIGN - 1) ||		\
+		(__funcp_address & ~(uintptr_t)1 & (FNCPY_ALIGN - 1)));	\
+									\
+	memcpy(dest_buf, (void const *)(__funcp_address & ~1), size);	\
+	flush_icache_range((unsigned long)(dest_buf),			\
+		(unsigned long)(dest_buf) + (size));			\
+									\
+	asm("" : "=r" (__result)					\
+		: "0" ((uintptr_t)(dest_buf) | (__funcp_address & 1)));	\
+									\
+	__result;							\
+})
+
+#endif /* !__ASM_FNCPY_H */
diff --git a/arch/arm/include/asm/fpstate.h b/arch/arm/include/asm/fpstate.h
index ee5e03efc1b..3ad4c10d0d8 100644
--- a/arch/arm/include/asm/fpstate.h
+++ b/arch/arm/include/asm/fpstate.h
@@ -18,7 +18,7 @@
  * VFP storage area has:
  *  - FPEXC, FPSCR, FPINST and FPINST2.
  *  - 16 or 32 double precision data registers
- *  - an implementation-dependant word of state for FLDMX/FSTMX (pre-ARMv6)
+ *  - an implementation-dependent word of state for FLDMX/FSTMX (pre-ARMv6)
  * 
  *  FPEXC will always be non-zero once the VFP has been used in this process.
  */
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index f89515adac6..39eb16b0066 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -52,15 +52,7 @@ extern inline void *return_address(unsigned int level)
 
 #endif
 
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* ifndef __ASSEMBLY__ */
 
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 540a044153a..53e69dae796 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -3,68 +3,144 @@
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_SMP
-
-#include <asm-generic/futex.h>
-
-#else /* !SMP, we can work around lack of atomic ops by disabling preemption */
-
 #include <linux/futex.h>
-#include <linux/preempt.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
-	__asm__ __volatile__(					\
-	"1:	ldrt	%1, [%2]\n"				\
-	"	" insn "\n"					\
-	"2:	strt	%0, [%2]\n"				\
-	"	mov	%0, #0\n"				\
+#define __futex_atomic_ex_table(err_reg)			\
 	"3:\n"							\
 	"	.pushsection __ex_table,\"a\"\n"		\
 	"	.align	3\n"					\
 	"	.long	1b, 4f, 2b, 4f\n"			\
 	"	.popsection\n"					\
 	"	.pushsection .fixup,\"ax\"\n"			\
-	"4:	mov	%0, %4\n"				\
+	"	.align	2\n"					\
+	"4:	mov	%0, " err_reg "\n"			\
 	"	b	3b\n"					\
-	"	.popsection"					\
-	: "=&r" (ret), "=&r" (oldval)				\
+	"	.popsection"
+
+#ifdef CONFIG_SMP
+
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+	smp_mb();						\
+	prefetchw(uaddr);					\
+	__asm__ __volatile__(					\
+	"1:	ldrex	%1, [%3]\n"				\
+	"	" insn "\n"					\
+	"2:	strex	%2, %0, [%3]\n"				\
+	"	teq	%2, #0\n"				\
+	"	bne	1b\n"					\
+	"	mov	%0, #0\n"				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
+	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
+	: "cc", "memory")
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret;
+	u32 val;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	smp_mb();
+	/* Prefetching cannot fault */
+	prefetchw(uaddr);
+	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
+	"1:	ldrex	%1, [%4]\n"
+	"	teq	%1, %2\n"
+	"	ite	eq	@ explicit IT needed for the 2b label\n"
+	"2:	strexeq	%0, %3, [%4]\n"
+	"	movne	%0, #0\n"
+	"	teq	%0, #0\n"
+	"	bne	1b\n"
+	__futex_atomic_ex_table("%5")
+	: "=&r" (ret), "=&r" (val)
+	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
+	: "cc", "memory");
+	smp_mb();
+
+	*uval = val;
+	return ret;
+}
+
+#else /* !SMP, we can work around lack of atomic ops by disabling preemption */
+
+#include <linux/preempt.h>
+#include <asm/domain.h>
+
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+	__asm__ __volatile__(					\
+	"1:	" TUSER(ldr) "	%1, [%3]\n"			\
+	"	" insn "\n"					\
+	"2:	" TUSER(str) "	%0, [%3]\n"			\
+	"	mov	%0, #0\n"				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret = 0;
+	u32 val;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
+	"1:	" TUSER(ldr) "	%1, [%4]\n"
+	"	teq	%1, %2\n"
+	"	it	eq	@ explicit IT needed for the 2b label\n"
+	"2:	" TUSER(streq) "	%3, [%4]\n"
+	__futex_atomic_ex_table("%5")
+	: "+r" (ret), "=&r" (val)
+	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
+	: "cc", "memory");
+
+	*uval = val;
+	return ret;
+}
+
+#endif /* !SMP */
+
+static inline int
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
 	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret;
+	int oldval = 0, ret, tmp;
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();	/* implies preempt_disable() */
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%0, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("mov	%0, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("add	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("orr	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%0, %1, %3", ret, oldval, uaddr, ~oparg);
+		__futex_atomic_op("and	%0, %1, %4", ret, oldval, tmp, uaddr, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("eor	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	default:
 		ret = -ENOSYS;
@@ -86,40 +162,5 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
-{
-	int val;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
-
-	pagefault_disable();	/* implies preempt_disable() */
-
-	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	ldrt	%0, [%3]\n"
-	"	teq	%0, %1\n"
-	"	it	eq	@ explicit IT needed for the 2b label\n"
-	"2:	streqt	%2, [%3]\n"
-	"3:\n"
-	"	.pushsection __ex_table,\"a\"\n"
-	"	.align	3\n"
-	"	.long	1b, 4f, 2b, 4f\n"
-	"	.popsection\n"
-	"	.pushsection .fixup,\"ax\"\n"
-	"4:	mov	%0, %4\n"
-	"	b	3b\n"
-	"	.popsection"
-	: "=&r" (val)
-	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
-	: "cc", "memory");
-
-	pagefault_enable();	/* subsumes preempt_enable() */
-
-	return val;
-}
-
-#endif /* !SMP */
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_ARM_FUTEX_H */
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
new file mode 100644
index 00000000000..a3c24cd5b7c
--- /dev/null
+++ b/arch/arm/include/asm/glue-cache.h
@@ -0,0 +1,166 @@
+/*
+ *  arch/arm/include/asm/glue-cache.h
+ *
+ *  Copyright (C) 1999-2002 Russell King
+ *
+ * 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_GLUE_CACHE_H
+#define ASM_GLUE_CACHE_H
+
+#include <asm/glue.h>
+
+/*
+ *	Cache Model
+ *	===========
+ */
+#undef _CACHE
+#undef MULTI_CACHE
+
+#if defined(CONFIG_CPU_CACHE_V4)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v4
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM920T) || defined(CONFIG_CPU_ARM922T) || \
+    defined(CONFIG_CPU_ARM925T) || defined(CONFIG_CPU_ARM1020) || \
+    defined(CONFIG_CPU_ARM1026)
+# define MULTI_CACHE 1
+#endif
+
+#if defined(CONFIG_CPU_FA526)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE fa
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM926T)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE arm926
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM940T)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE arm940
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM946E)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE arm946
+# endif
+#endif
+
+#if defined(CONFIG_CPU_CACHE_V4WB)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v4wb
+# endif
+#endif
+
+#if defined(CONFIG_CPU_XSCALE)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE xscale
+# endif
+#endif
+
+#if defined(CONFIG_CPU_XSC3)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE xsc3
+# endif
+#endif
+
+#if defined(CONFIG_CPU_MOHAWK)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE mohawk
+# endif
+#endif
+
+#if defined(CONFIG_CPU_FEROCEON)
+# define MULTI_CACHE 1
+#endif
+
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v6
+# endif
+#endif
+
+#if defined(CONFIG_CPU_V7)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v7
+# endif
+#endif
+
+#if defined(CONFIG_CPU_V7M)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE nop
+# endif
+#endif
+
+#if !defined(_CACHE) && !defined(MULTI_CACHE)
+#error Unknown cache maintenance model
+#endif
+
+#ifndef __ASSEMBLER__
+static inline void nop_flush_icache_all(void) { }
+static inline void nop_flush_kern_cache_all(void) { }
+static inline void nop_flush_kern_cache_louis(void) { }
+static inline void nop_flush_user_cache_all(void) { }
+static inline void nop_flush_user_cache_range(unsigned long a,
+		unsigned long b, unsigned int c) { }
+
+static inline void nop_coherent_kern_range(unsigned long a, unsigned long b) { }
+static inline int nop_coherent_user_range(unsigned long a,
+		unsigned long b) { return 0; }
+static inline void nop_flush_kern_dcache_area(void *a, size_t s) { }
+
+static inline void nop_dma_flush_range(const void *a, const void *b) { }
+
+static inline void nop_dma_map_area(const void *s, size_t l, int f) { }
+static inline void nop_dma_unmap_area(const void *s, size_t l, int f) { }
+#endif
+
+#ifndef MULTI_CACHE
+#define __cpuc_flush_icache_all		__glue(_CACHE,_flush_icache_all)
+#define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
+#define __cpuc_flush_kern_louis		__glue(_CACHE,_flush_kern_cache_louis)
+#define __cpuc_flush_user_all		__glue(_CACHE,_flush_user_cache_all)
+#define __cpuc_flush_user_range		__glue(_CACHE,_flush_user_cache_range)
+#define __cpuc_coherent_kern_range	__glue(_CACHE,_coherent_kern_range)
+#define __cpuc_coherent_user_range	__glue(_CACHE,_coherent_user_range)
+#define __cpuc_flush_dcache_area	__glue(_CACHE,_flush_kern_dcache_area)
+
+#define dmac_map_area			__glue(_CACHE,_dma_map_area)
+#define dmac_unmap_area			__glue(_CACHE,_dma_unmap_area)
+#define dmac_flush_range		__glue(_CACHE,_dma_flush_range)
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/glue-df.h b/arch/arm/include/asm/glue-df.h
new file mode 100644
index 00000000000..04e18b65665
--- /dev/null
+++ b/arch/arm/include/asm/glue-df.h
@@ -0,0 +1,102 @@
+/*
+ *  arch/arm/include/asm/glue-df.h
+ *
+ *  Copyright (C) 1997-1999 Russell King
+ *  Copyright (C) 2000-2002 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.
+ */
+#ifndef ASM_GLUE_DF_H
+#define ASM_GLUE_DF_H
+
+#include <asm/glue.h>
+
+/*
+ *	Data Abort Model
+ *	================
+ *
+ *	We have the following to choose from:
+ *	  arm7		- ARM7 style
+ *	  v4_early	- ARMv4 without Thumb early abort handler
+ *	  v4t_late	- ARMv4 with Thumb late abort handler
+ *	  v4t_early	- ARMv4 with Thumb early abort handler
+ *	  v5t_early	- ARMv5 with Thumb early abort handler
+ *	  v5tj_early	- ARMv5 with Thumb and Java early abort handler
+ *	  xscale	- ARMv5 with Thumb with Xscale extensions
+ *	  v6_early	- ARMv6 generic early abort handler
+ *	  v7_early	- ARMv7 generic early abort handler
+ */
+#undef CPU_DABORT_HANDLER
+#undef MULTI_DABORT
+
+#ifdef CONFIG_CPU_ABRT_EV4
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v4_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_LV4T
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v4t_late_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV4T
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v4t_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV5T
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v5t_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV5TJ
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v5tj_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV6
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v6_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_EV7
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER v7_early_abort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ABRT_NOMMU
+# ifdef CPU_DABORT_HANDLER
+#  define MULTI_DABORT 1
+# else
+#  define CPU_DABORT_HANDLER nommu_early_abort
+# endif
+#endif
+
+#ifndef CPU_DABORT_HANDLER
+#error Unknown data abort handler type
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/glue-pf.h b/arch/arm/include/asm/glue-pf.h
new file mode 100644
index 00000000000..d385f37c13f
--- /dev/null
+++ b/arch/arm/include/asm/glue-pf.h
@@ -0,0 +1,57 @@
+/*
+ *  arch/arm/include/asm/glue-pf.h
+ *
+ *  Copyright (C) 1997-1999 Russell King
+ *  Copyright (C) 2000-2002 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.
+ */
+#ifndef ASM_GLUE_PF_H
+#define ASM_GLUE_PF_H
+
+#include <asm/glue.h>
+
+/*
+ *	Prefetch Abort Model
+ *	================
+ *
+ *	We have the following to choose from:
+ *	  legacy	- no IFSR, no IFAR
+ *	  v6		- ARMv6: IFSR, no IFAR
+ *	  v7		- ARMv7: IFSR and IFAR
+ */
+
+#undef CPU_PABORT_HANDLER
+#undef MULTI_PABORT
+
+#ifdef CONFIG_CPU_PABRT_LEGACY
+# ifdef CPU_PABORT_HANDLER
+#  define MULTI_PABORT 1
+# else
+#  define CPU_PABORT_HANDLER legacy_pabort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_PABRT_V6
+# ifdef CPU_PABORT_HANDLER
+#  define MULTI_PABORT 1
+# else
+#  define CPU_PABORT_HANDLER v6_pabort
+# endif
+#endif
+
+#ifdef CONFIG_CPU_PABRT_V7
+# ifdef CPU_PABORT_HANDLER
+#  define MULTI_PABORT 1
+# else
+#  define CPU_PABORT_HANDLER v7_pabort
+# endif
+#endif
+
+#ifndef CPU_PABORT_HANDLER
+#error Unknown prefetch abort handler type
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/glue-proc.h b/arch/arm/include/asm/glue-proc.h
new file mode 100644
index 00000000000..74a8b84f3cb
--- /dev/null
+++ b/arch/arm/include/asm/glue-proc.h
@@ -0,0 +1,264 @@
+/*
+ *  arch/arm/include/asm/glue-proc.h
+ *
+ *  Copyright (C) 1997-1999 Russell King
+ *  Copyright (C) 2000 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.
+ */
+#ifndef ASM_GLUE_PROC_H
+#define ASM_GLUE_PROC_H
+
+#include <asm/glue.h>
+
+/*
+ * Work out if we need multiple CPU support
+ */
+#undef MULTI_CPU
+#undef CPU_NAME
+
+/*
+ * CPU_NAME - the prefix for CPU related functions
+ */
+
+#ifdef CONFIG_CPU_ARM7TDMI
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm7tdmi
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM720T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm720
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM740T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm740
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM9TDMI
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm9tdmi
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM920T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm920
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM922T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm922
+# endif
+#endif
+
+#ifdef CONFIG_CPU_FA526
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_fa526
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM925T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm925
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM926T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm926
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM940T
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm940
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM946E
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm946
+# endif
+#endif
+
+#ifdef CONFIG_CPU_SA110
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_sa110
+# endif
+#endif
+
+#ifdef CONFIG_CPU_SA1100
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_sa1100
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM1020
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm1020
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM1020E
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm1020e
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM1022
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm1022
+# endif
+#endif
+
+#ifdef CONFIG_CPU_ARM1026
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_arm1026
+# endif
+#endif
+
+#ifdef CONFIG_CPU_XSCALE
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_xscale
+# endif
+#endif
+
+#ifdef CONFIG_CPU_XSC3
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_xsc3
+# endif
+#endif
+
+#ifdef CONFIG_CPU_MOHAWK
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_mohawk
+# endif
+#endif
+
+#ifdef CONFIG_CPU_FEROCEON
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_feroceon
+# endif
+#endif
+
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_v6
+# endif
+#endif
+
+#ifdef CONFIG_CPU_V7
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_v7
+# endif
+#endif
+
+#ifdef CONFIG_CPU_V7M
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_v7m
+# endif
+#endif
+
+#ifdef CONFIG_CPU_PJ4B
+# ifdef CPU_NAME
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+# else
+#  define CPU_NAME cpu_pj4b
+# endif
+#endif
+
+#ifndef MULTI_CPU
+#define cpu_proc_init			__glue(CPU_NAME,_proc_init)
+#define cpu_proc_fin			__glue(CPU_NAME,_proc_fin)
+#define cpu_reset			__glue(CPU_NAME,_reset)
+#define cpu_do_idle			__glue(CPU_NAME,_do_idle)
+#define cpu_dcache_clean_area		__glue(CPU_NAME,_dcache_clean_area)
+#define cpu_do_switch_mm		__glue(CPU_NAME,_switch_mm)
+#define cpu_set_pte_ext			__glue(CPU_NAME,_set_pte_ext)
+#define cpu_suspend_size		__glue(CPU_NAME,_suspend_size)
+#define cpu_do_suspend			__glue(CPU_NAME,_do_suspend)
+#define cpu_do_resume			__glue(CPU_NAME,_do_resume)
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/glue.h b/arch/arm/include/asm/glue.h
index 234a3fc1c78..fbf71d75ec8 100644
--- a/arch/arm/include/asm/glue.h
+++ b/arch/arm/include/asm/glue.h
@@ -10,12 +10,11 @@
  *
  *  This file provides the glue to stick the processor-specific bits
  *  into the kernel in an efficient manner.  The idea is to use branches
- *  when we're only targetting one class of TLB, or indirect calls
- *  when we're targetting multiple classes of TLBs.
+ *  when we're only targeting one class of TLB, or indirect calls
+ *  when we're targeting multiple classes of TLBs.
  */
 #ifdef __KERNEL__
 
-
 #ifdef __STDC__
 #define ____glue(name,fn)	name##fn
 #else
@@ -23,141 +22,4 @@
 #endif
 #define __glue(name,fn)		____glue(name,fn)
 
-
-
-/*
- *	Data Abort Model
- *	================
- *
- *	We have the following to choose from:
- *	  arm6          - ARM6 style
- *	  arm7		- ARM7 style
- *	  v4_early	- ARMv4 without Thumb early abort handler
- *	  v4t_late	- ARMv4 with Thumb late abort handler
- *	  v4t_early	- ARMv4 with Thumb early abort handler
- *	  v5tej_early	- ARMv5 with Thumb and Java early abort handler
- *	  xscale	- ARMv5 with Thumb with Xscale extensions
- *	  v6_early	- ARMv6 generic early abort handler
- *	  v7_early	- ARMv7 generic early abort handler
- */
-#undef CPU_DABORT_HANDLER
-#undef MULTI_DABORT
-
-#if defined(CONFIG_CPU_ARM610)
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER cpu_arm6_data_abort
-# endif
-#endif
-
-#if defined(CONFIG_CPU_ARM710)
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER cpu_arm7_data_abort
-# endif
-#endif
-
-#ifdef CONFIG_CPU_ABRT_LV4T
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER v4t_late_abort
-# endif
-#endif
-
-#ifdef CONFIG_CPU_ABRT_EV4
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER v4_early_abort
-# endif
-#endif
-
-#ifdef CONFIG_CPU_ABRT_EV4T
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER v4t_early_abort
-# endif
-#endif
-
-#ifdef CONFIG_CPU_ABRT_EV5TJ
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER v5tj_early_abort
-# endif
-#endif
-
-#ifdef CONFIG_CPU_ABRT_EV5T
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER v5t_early_abort
-# endif
-#endif
-
-#ifdef CONFIG_CPU_ABRT_EV6
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER v6_early_abort
-# endif
-#endif
-
-#ifdef CONFIG_CPU_ABRT_EV7
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER v7_early_abort
-# endif
-#endif
-
-#ifndef CPU_DABORT_HANDLER
-#error Unknown data abort handler type
-#endif
-
-/*
- *	Prefetch Abort Model
- *	================
- *
- *	We have the following to choose from:
- *	  legacy	- no IFSR, no IFAR
- *	  v6		- ARMv6: IFSR, no IFAR
- *	  v7		- ARMv7: IFSR and IFAR
- */
-
-#undef CPU_PABORT_HANDLER
-#undef MULTI_PABORT
-
-#ifdef CONFIG_CPU_PABRT_LEGACY
-# ifdef CPU_PABORT_HANDLER
-#  define MULTI_PABORT 1
-# else
-#  define CPU_PABORT_HANDLER legacy_pabort
-# endif
-#endif
-
-#ifdef CONFIG_CPU_PABRT_V6
-# ifdef CPU_PABORT_HANDLER
-#  define MULTI_PABORT 1
-# else
-#  define CPU_PABORT_HANDLER v6_pabort
-# endif
-#endif
-
-#ifdef CONFIG_CPU_PABRT_V7
-# ifdef CPU_PABORT_HANDLER
-#  define MULTI_PABORT 1
-# else
-#  define CPU_PABORT_HANDLER v7_pabort
-# endif
-#endif
-
-#ifndef CPU_PABORT_HANDLER
-#error Unknown prefetch abort handler type
-#endif
-
 #endif
diff --git a/arch/arm/include/asm/gpio.h b/arch/arm/include/asm/gpio.h
index 166a7a3e284..477e0206e01 100644
--- a/arch/arm/include/asm/gpio.h
+++ b/arch/arm/include/asm/gpio.h
@@ -1,7 +1,32 @@
 #ifndef _ARCH_ARM_GPIO_H
 #define _ARCH_ARM_GPIO_H
 
+#if CONFIG_ARCH_NR_GPIO > 0
+#define ARCH_NR_GPIOS CONFIG_ARCH_NR_GPIO
+#endif
+
 /* not all ARM platforms necessarily support this API ... */
+#ifdef CONFIG_NEED_MACH_GPIO_H
 #include <mach/gpio.h>
+#endif
+
+#ifndef __ARM_GPIOLIB_COMPLEX
+/* Note: this may rely upon the value of ARCH_NR_GPIOS set in mach/gpio.h */
+#include <asm-generic/gpio.h>
+
+/* The trivial gpiolib dispatchers */
+#define gpio_get_value  __gpio_get_value
+#define gpio_set_value  __gpio_set_value
+#define gpio_cansleep   __gpio_cansleep
+#endif
+
+/*
+ * Provide a default gpio_to_irq() which should satisfy every case.
+ * However, some platforms want to do this differently, so allow them
+ * to override it.
+ */
+#ifndef gpio_to_irq
+#define gpio_to_irq	__gpio_to_irq
+#endif
 
 #endif /* _ARCH_ARM_GPIO_H */
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 6d7485aff95..fe3ea776dc3 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,29 +5,27 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
+#define NR_IPI	8
+
 typedef struct {
 	unsigned int __softirq_pending;
-	unsigned int local_timer_irqs;
+#ifdef CONFIG_SMP
+	unsigned int ipi_irqs[NR_IPI];
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
 
-#if NR_IRQS > 512
-#define HARDIRQ_BITS	10
-#elif NR_IRQS > 256
-#define HARDIRQ_BITS	9
+#define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
+#define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
+
+#ifdef CONFIG_SMP
+u64 smp_irq_stat_cpu(unsigned int cpu);
 #else
-#define HARDIRQ_BITS	8
+#define smp_irq_stat_cpu(cpu)	0
 #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_stat_cpu	smp_irq_stat_cpu
 
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
diff --git a/arch/arm/include/asm/hardware/arm_timer.h b/arch/arm/include/asm/hardware/arm_timer.h
index c0f4e7bf22d..d6030ff599d 100644
--- a/arch/arm/include/asm/hardware/arm_timer.h
+++ b/arch/arm/include/asm/hardware/arm_timer.h
@@ -9,7 +9,12 @@
  *
  * Integrator AP has 16-bit timers, Integrator CP, Versatile and Realview
  * can have 16-bit or 32-bit selectable via a bit in the control register.
+ *
+ * Every SP804 contains two identical timers.
  */
+#define TIMER_1_BASE	0x00
+#define TIMER_2_BASE	0x20
+
 #define TIMER_LOAD	0x00			/* ACVR rw */
 #define TIMER_VALUE	0x04			/* ACVR ro */
 #define TIMER_CTRL	0x08			/* ACVR rw */
diff --git a/arch/arm/include/asm/hardware/cache-feroceon-l2.h b/arch/arm/include/asm/hardware/cache-feroceon-l2.h
new file mode 100644
index 00000000000..12e1588dc4f
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cache-feroceon-l2.h
@@ -0,0 +1,13 @@
+/*
+ * arch/arm/include/asm/hardware/cache-feroceon-l2.h
+ *
+ * Copyright (C) 2008 Marvell Semiconductor
+ *
+ * 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.
+ */
+
+extern void __init feroceon_l2_init(int l2_wt_override);
+extern int __init feroceon_of_init(void);
+
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index cc42d5fdee1..3a5ec1c2565 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -20,12 +20,14 @@
 #ifndef __ASM_ARM_HARDWARE_L2X0_H
 #define __ASM_ARM_HARDWARE_L2X0_H
 
+#include <linux/errno.h>
+
 #define L2X0_CACHE_ID			0x000
 #define L2X0_CACHE_TYPE			0x004
 #define L2X0_CTRL			0x100
 #define L2X0_AUX_CTRL			0x104
-#define L2X0_TAG_LATENCY_CTRL		0x108
-#define L2X0_DATA_LATENCY_CTRL		0x10C
+#define L310_TAG_LATENCY_CTRL		0x108
+#define L310_DATA_LATENCY_CTRL		0x10C
 #define L2X0_EVENT_CNT_CTRL		0x200
 #define L2X0_EVENT_CNT1_CFG		0x204
 #define L2X0_EVENT_CNT0_CFG		0x208
@@ -36,6 +38,7 @@
 #define L2X0_RAW_INTR_STAT		0x21C
 #define L2X0_INTR_CLEAR			0x220
 #define L2X0_CACHE_SYNC			0x730
+#define L2X0_DUMMY_REG			0x740
 #define L2X0_INV_LINE_PA		0x770
 #define L2X0_INV_WAY			0x77C
 #define L2X0_CLEAN_LINE_PA		0x7B0
@@ -44,25 +47,135 @@
 #define L2X0_CLEAN_INV_LINE_PA		0x7F0
 #define L2X0_CLEAN_INV_LINE_IDX		0x7F8
 #define L2X0_CLEAN_INV_WAY		0x7FC
-#define L2X0_LOCKDOWN_WAY_D		0x900
-#define L2X0_LOCKDOWN_WAY_I		0x904
+/*
+ * The lockdown registers repeat 8 times for L310, the L210 has only one
+ * D and one I lockdown register at 0x0900 and 0x0904.
+ */
+#define L2X0_LOCKDOWN_WAY_D_BASE	0x900
+#define L2X0_LOCKDOWN_WAY_I_BASE	0x904
+#define L2X0_LOCKDOWN_STRIDE		0x08
+#define L310_ADDR_FILTER_START		0xC00
+#define L310_ADDR_FILTER_END		0xC04
 #define L2X0_TEST_OPERATION		0xF00
 #define L2X0_LINE_DATA			0xF10
 #define L2X0_LINE_TAG			0xF30
 #define L2X0_DEBUG_CTRL			0xF40
-#define L2X0_PREFETCH_CTRL		0xF60
-#define L2X0_POWER_CTRL			0xF80
-#define   L2X0_DYNAMIC_CLK_GATING_EN	(1 << 1)
-#define   L2X0_STNDBY_MODE_EN		(1 << 0)
+#define L310_PREFETCH_CTRL		0xF60
+#define L310_POWER_CTRL			0xF80
+#define   L310_DYNAMIC_CLK_GATING_EN	(1 << 1)
+#define   L310_STNDBY_MODE_EN		(1 << 0)
 
 /* Registers shifts and masks */
 #define L2X0_CACHE_ID_PART_MASK		(0xf << 6)
 #define L2X0_CACHE_ID_PART_L210		(1 << 6)
+#define L2X0_CACHE_ID_PART_L220		(2 << 6)
 #define L2X0_CACHE_ID_PART_L310		(3 << 6)
-#define L2X0_AUX_CTRL_WAY_SIZE_MASK	(0x3 << 17)
+#define L2X0_CACHE_ID_RTL_MASK          0x3f
+#define L210_CACHE_ID_RTL_R0P2_02	0x00
+#define L210_CACHE_ID_RTL_R0P1		0x01
+#define L210_CACHE_ID_RTL_R0P2_01	0x02
+#define L210_CACHE_ID_RTL_R0P3		0x03
+#define L210_CACHE_ID_RTL_R0P4		0x0b
+#define L210_CACHE_ID_RTL_R0P5		0x0f
+#define L220_CACHE_ID_RTL_R1P7_01REL0	0x06
+#define L310_CACHE_ID_RTL_R0P0		0x00
+#define L310_CACHE_ID_RTL_R1P0		0x02
+#define L310_CACHE_ID_RTL_R2P0		0x04
+#define L310_CACHE_ID_RTL_R3P0		0x05
+#define L310_CACHE_ID_RTL_R3P1		0x06
+#define L310_CACHE_ID_RTL_R3P1_50REL0	0x07
+#define L310_CACHE_ID_RTL_R3P2		0x08
+#define L310_CACHE_ID_RTL_R3P3		0x09
+
+/* L2C auxiliary control register - bits common to L2C-210/220/310 */
+#define L2C_AUX_CTRL_WAY_SIZE_SHIFT		17
+#define L2C_AUX_CTRL_WAY_SIZE_MASK		(7 << 17)
+#define L2C_AUX_CTRL_WAY_SIZE(n)		((n) << 17)
+#define L2C_AUX_CTRL_EVTMON_ENABLE		BIT(20)
+#define L2C_AUX_CTRL_PARITY_ENABLE		BIT(21)
+#define L2C_AUX_CTRL_SHARED_OVERRIDE		BIT(22)
+/* L2C-210/220 common bits */
+#define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT	0
+#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK	(7 << 0)
+#define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT	3
+#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK	(7 << 3)
+#define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT		6
+#define L2X0_AUX_CTRL_TAG_LATENCY_MASK		(7 << 6)
+#define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT	9
+#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK	(7 << 9)
+#define L2X0_AUX_CTRL_ASSOC_SHIFT		13
+#define L2X0_AUX_CTRL_ASSOC_MASK		(15 << 13)
+/* L2C-210 specific bits */
+#define L210_AUX_CTRL_WRAP_DISABLE		BIT(12)
+#define L210_AUX_CTRL_WA_OVERRIDE		BIT(23)
+#define L210_AUX_CTRL_EXCLUSIVE_ABORT		BIT(24)
+/* L2C-220 specific bits */
+#define L220_AUX_CTRL_EXCLUSIVE_CACHE		BIT(12)
+#define L220_AUX_CTRL_FWA_SHIFT			23
+#define L220_AUX_CTRL_FWA_MASK			(3 << 23)
+#define L220_AUX_CTRL_NS_LOCKDOWN		BIT(26)
+#define L220_AUX_CTRL_NS_INT_CTRL		BIT(27)
+/* L2C-310 specific bits */
+#define L310_AUX_CTRL_FULL_LINE_ZERO		BIT(0)	/* R2P0+ */
+#define L310_AUX_CTRL_HIGHPRIO_SO_DEV		BIT(10)	/* R2P0+ */
+#define L310_AUX_CTRL_STORE_LIMITATION		BIT(11)	/* R2P0+ */
+#define L310_AUX_CTRL_EXCLUSIVE_CACHE		BIT(12)
+#define L310_AUX_CTRL_ASSOCIATIVITY_16		BIT(16)
+#define L310_AUX_CTRL_CACHE_REPLACE_RR		BIT(25)	/* R2P0+ */
+#define L310_AUX_CTRL_NS_LOCKDOWN		BIT(26)
+#define L310_AUX_CTRL_NS_INT_CTRL		BIT(27)
+#define L310_AUX_CTRL_DATA_PREFETCH		BIT(28)
+#define L310_AUX_CTRL_INSTR_PREFETCH		BIT(29)
+#define L310_AUX_CTRL_EARLY_BRESP		BIT(30)	/* R2P0+ */
+
+#define L310_LATENCY_CTRL_SETUP(n)		((n) << 0)
+#define L310_LATENCY_CTRL_RD(n)			((n) << 4)
+#define L310_LATENCY_CTRL_WR(n)			((n) << 8)
+
+#define L310_ADDR_FILTER_EN		1
+
+#define L310_PREFETCH_CTRL_OFFSET_MASK		0x1f
+#define L310_PREFETCH_CTRL_DBL_LINEFILL_INCR	BIT(23)
+#define L310_PREFETCH_CTRL_PREFETCH_DROP	BIT(24)
+#define L310_PREFETCH_CTRL_DBL_LINEFILL_WRAP	BIT(27)
+#define L310_PREFETCH_CTRL_DATA_PREFETCH	BIT(28)
+#define L310_PREFETCH_CTRL_INSTR_PREFETCH	BIT(29)
+#define L310_PREFETCH_CTRL_DBL_LINEFILL		BIT(30)
+
+#define L2X0_CTRL_EN			1
+
+#define L2X0_WAY_SIZE_SHIFT		3
 
 #ifndef __ASSEMBLY__
-extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask);
+extern void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask);
+#if defined(CONFIG_CACHE_L2X0) && defined(CONFIG_OF)
+extern int l2x0_of_init(u32 aux_val, u32 aux_mask);
+#else
+static inline int l2x0_of_init(u32 aux_val, u32 aux_mask)
+{
+	return -ENODEV;
+}
 #endif
 
+struct l2x0_regs {
+	unsigned long phy_base;
+	unsigned long aux_ctrl;
+	/*
+	 * Whether the following registers need to be saved/restored
+	 * depends on platform
+	 */
+	unsigned long tag_latency;
+	unsigned long data_latency;
+	unsigned long filter_start;
+	unsigned long filter_end;
+	unsigned long prefetch_ctrl;
+	unsigned long pwr_ctrl;
+	unsigned long ctrl;
+	unsigned long aux2_ctrl;
+};
+
+extern struct l2x0_regs l2x0_saved_regs;
+
+#endif /* __ASSEMBLY__ */
+
 #endif
diff --git a/arch/arm/include/asm/hardware/cache-tauros2.h b/arch/arm/include/asm/hardware/cache-tauros2.h
index 538f17ca905..295e2e40151 100644
--- a/arch/arm/include/asm/hardware/cache-tauros2.h
+++ b/arch/arm/include/asm/hardware/cache-tauros2.h
@@ -8,4 +8,7 @@
  * warranty of any kind, whether express or implied.
  */
 
-extern void __init tauros2_init(void);
+#define CACHE_TAUROS2_PREFETCH_ON	(1 << 0)
+#define CACHE_TAUROS2_LINEFILL_BURST8	(1 << 1)
+
+extern void __init tauros2_init(unsigned int features);
diff --git a/arch/arm/include/asm/hardware/clps7111.h b/arch/arm/include/asm/hardware/clps7111.h
deleted file mode 100644
index 44477225aed..00000000000
--- a/arch/arm/include/asm/hardware/clps7111.h
+++ /dev/null
@@ -1,184 +0,0 @@
-/*
- *  arch/arm/include/asm/hardware/clps7111.h
- *
- *  This file contains the hardware definitions of the CLPS7111 internal
- *  registers.
- *
- *  Copyright (C) 2000 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 as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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_HARDWARE_CLPS7111_H
-#define __ASM_HARDWARE_CLPS7111_H
-
-#define CLPS7111_PHYS_BASE	(0x80000000)
-
-#ifndef __ASSEMBLY__
-#define clps_readb(off)		__raw_readb(CLPS7111_BASE + (off))
-#define clps_readw(off)		__raw_readw(CLPS7111_BASE + (off))
-#define clps_readl(off)		__raw_readl(CLPS7111_BASE + (off))
-#define clps_writeb(val,off)	__raw_writeb(val, CLPS7111_BASE + (off))
-#define clps_writew(val,off)	__raw_writew(val, CLPS7111_BASE + (off))
-#define clps_writel(val,off)	__raw_writel(val, CLPS7111_BASE + (off))
-#endif
-
-#define PADR		(0x0000)
-#define PBDR		(0x0001)
-#define PDDR		(0x0003)
-#define PADDR		(0x0040)
-#define PBDDR		(0x0041)
-#define PDDDR		(0x0043)
-#define PEDR		(0x0080)
-#define PEDDR		(0x00c0)
-#define SYSCON1		(0x0100)
-#define SYSFLG1		(0x0140)
-#define MEMCFG1		(0x0180)
-#define MEMCFG2		(0x01c0)
-#define DRFPR		(0x0200)
-#define INTSR1		(0x0240)
-#define INTMR1		(0x0280)
-#define LCDCON		(0x02c0)
-#define TC1D            (0x0300)
-#define TC2D		(0x0340)
-#define RTCDR		(0x0380)
-#define RTCMR		(0x03c0)
-#define PMPCON		(0x0400)
-#define CODR		(0x0440)
-#define UARTDR1		(0x0480)
-#define UBRLCR1		(0x04c0)
-#define SYNCIO		(0x0500)
-#define PALLSW		(0x0540)
-#define PALMSW		(0x0580)
-#define STFCLR		(0x05c0)
-#define BLEOI		(0x0600)
-#define MCEOI		(0x0640)
-#define TEOI		(0x0680)
-#define TC1EOI		(0x06c0)
-#define TC2EOI		(0x0700)
-#define RTCEOI		(0x0740)
-#define UMSEOI		(0x0780)
-#define COEOI		(0x07c0)
-#define HALT		(0x0800)
-#define STDBY		(0x0840)
-
-#define FBADDR		(0x1000)
-#define SYSCON2		(0x1100)
-#define SYSFLG2		(0x1140)
-#define INTSR2		(0x1240)
-#define INTMR2		(0x1280)
-#define UARTDR2		(0x1480)
-#define UBRLCR2		(0x14c0)
-#define SS2DR		(0x1500)
-#define SRXEOF		(0x1600)
-#define SS2POP		(0x16c0)
-#define KBDEOI		(0x1700)
-
-/* common bits: SYSCON1 / SYSCON2 */
-#define SYSCON_UARTEN		(1 << 8)
-
-#define SYSCON1_KBDSCAN(x)	((x) & 15)
-#define SYSCON1_KBDSCANMASK	(15)
-#define SYSCON1_TC1M		(1 << 4)
-#define SYSCON1_TC1S		(1 << 5)
-#define SYSCON1_TC2M		(1 << 6)
-#define SYSCON1_TC2S		(1 << 7)
-#define SYSCON1_UART1EN		SYSCON_UARTEN
-#define SYSCON1_BZTOG		(1 << 9)
-#define SYSCON1_BZMOD		(1 << 10)
-#define SYSCON1_DBGEN		(1 << 11)
-#define SYSCON1_LCDEN		(1 << 12)
-#define SYSCON1_CDENTX		(1 << 13)
-#define SYSCON1_CDENRX		(1 << 14)
-#define SYSCON1_SIREN		(1 << 15)
-#define SYSCON1_ADCKSEL(x)	(((x) & 3) << 16)
-#define SYSCON1_ADCKSEL_MASK	(3 << 16)
-#define SYSCON1_EXCKEN		(1 << 18)
-#define SYSCON1_WAKEDIS		(1 << 19)
-#define SYSCON1_IRTXM		(1 << 20)
-
-/* common bits: SYSFLG1 / SYSFLG2 */
-#define SYSFLG_UBUSY		(1 << 11)
-#define SYSFLG_URXFE		(1 << 22)
-#define SYSFLG_UTXFF		(1 << 23)
-
-#define SYSFLG1_MCDR		(1 << 0)
-#define SYSFLG1_DCDET		(1 << 1)
-#define SYSFLG1_WUDR		(1 << 2)
-#define SYSFLG1_WUON		(1 << 3)
-#define SYSFLG1_CTS		(1 << 8)
-#define SYSFLG1_DSR		(1 << 9)
-#define SYSFLG1_DCD		(1 << 10)
-#define SYSFLG1_UBUSY		SYSFLG_UBUSY
-#define SYSFLG1_NBFLG		(1 << 12)
-#define SYSFLG1_RSTFLG		(1 << 13)
-#define SYSFLG1_PFFLG		(1 << 14)
-#define SYSFLG1_CLDFLG		(1 << 15)
-#define SYSFLG1_URXFE		SYSFLG_URXFE
-#define SYSFLG1_UTXFF		SYSFLG_UTXFF
-#define SYSFLG1_CRXFE		(1 << 24)
-#define SYSFLG1_CTXFF		(1 << 25)
-#define SYSFLG1_SSIBUSY		(1 << 26)
-#define SYSFLG1_ID		(1 << 29)
-
-#define SYSFLG2_SSRXOF		(1 << 0)
-#define SYSFLG2_RESVAL		(1 << 1)
-#define SYSFLG2_RESFRM		(1 << 2)
-#define SYSFLG2_SS2RXFE		(1 << 3)
-#define SYSFLG2_SS2TXFF		(1 << 4)
-#define SYSFLG2_SS2TXUF		(1 << 5)
-#define SYSFLG2_CKMODE		(1 << 6)
-#define SYSFLG2_UBUSY		SYSFLG_UBUSY
-#define SYSFLG2_URXFE		SYSFLG_URXFE
-#define SYSFLG2_UTXFF		SYSFLG_UTXFF
-
-#define LCDCON_GSEN		(1 << 30)
-#define LCDCON_GSMD		(1 << 31)
-
-#define SYSCON2_SERSEL		(1 << 0)
-#define SYSCON2_KBD6		(1 << 1)
-#define SYSCON2_DRAMZ		(1 << 2)
-#define SYSCON2_KBWEN		(1 << 3)
-#define SYSCON2_SS2TXEN		(1 << 4)
-#define SYSCON2_PCCARD1		(1 << 5)
-#define SYSCON2_PCCARD2		(1 << 6)
-#define SYSCON2_SS2RXEN		(1 << 7)
-#define SYSCON2_UART2EN		SYSCON_UARTEN
-#define SYSCON2_SS2MAEN		(1 << 9)
-#define SYSCON2_OSTB		(1 << 12)
-#define SYSCON2_CLKENSL		(1 << 13)
-#define SYSCON2_BUZFREQ		(1 << 14)
-
-/* common bits: UARTDR1 / UARTDR2 */
-#define UARTDR_FRMERR		(1 << 8)
-#define UARTDR_PARERR		(1 << 9)
-#define UARTDR_OVERR		(1 << 10)
-
-/* common bits: UBRLCR1 / UBRLCR2 */
-#define UBRLCR_BAUD_MASK	((1 << 12) - 1)
-#define UBRLCR_BREAK		(1 << 12)
-#define UBRLCR_PRTEN		(1 << 13)
-#define UBRLCR_EVENPRT		(1 << 14)
-#define UBRLCR_XSTOP		(1 << 15)
-#define UBRLCR_FIFOEN		(1 << 16)
-#define UBRLCR_WRDLEN5		(0 << 17)
-#define UBRLCR_WRDLEN6		(1 << 17)
-#define UBRLCR_WRDLEN7		(2 << 17)
-#define UBRLCR_WRDLEN8		(3 << 17)
-#define UBRLCR_WRDLEN_MASK	(3 << 17)
-
-#define SYNCIO_SMCKEN		(1 << 13)
-#define SYNCIO_TXFRMEN		(1 << 14)
-
-#endif /* __ASM_HARDWARE_CLPS7111_H */
diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h
index 7ecd793b8f5..ad774f37c47 100644
--- a/arch/arm/include/asm/hardware/coresight.h
+++ b/arch/arm/include/asm/hardware/coresight.h
@@ -24,8 +24,8 @@
 #define TRACER_TIMEOUT 10000
 
 #define etm_writel(t, v, x) \
-	(__raw_writel((v), (t)->etm_regs + (x)))
-#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x)))
+	(writel_relaxed((v), (t)->etm_regs + (x)))
+#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x)))
 
 /* CoreSight Management Registers */
 #define CSMR_LOCKACCESS 0xfb0
@@ -36,7 +36,7 @@
 /* CoreSight Component Registers */
 #define CSCR_CLASS	0xff4
 
-#define UNLOCK_MAGIC	0xc5acce55
+#define CS_LAR_KEY	0xc5acce55
 
 /* ETM control register, "ETM Architecture", 3.3.1 */
 #define ETMR_CTRL		0
@@ -142,16 +142,16 @@
 #define ETBFF_TRIGFL		BIT(10)
 
 #define etb_writel(t, v, x) \
-	(__raw_writel((v), (t)->etb_regs + (x)))
-#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x)))
+	(writel_relaxed((v), (t)->etb_regs + (x)))
+#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x)))
 
 #define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0)
 #define etm_unlock(t) \
-	do { etm_writel((t), UNLOCK_MAGIC, CSMR_LOCKACCESS); } while (0)
+	do { etm_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
 
 #define etb_lock(t) do { etb_writel((t), 0, CSMR_LOCKACCESS); } while (0)
 #define etb_unlock(t) \
-	do { etb_writel((t), UNLOCK_MAGIC, CSMR_LOCKACCESS); } while (0)
+	do { etb_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
 
 #endif /* __ASM_HARDWARE_CORESIGHT_H */
 
diff --git a/arch/arm/include/asm/hardware/cs89712.h b/arch/arm/include/asm/hardware/cs89712.h
deleted file mode 100644
index f75626933e9..00000000000
--- a/arch/arm/include/asm/hardware/cs89712.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- *  arch/arm/include/asm/hardware/cs89712.h
- *
- *  This file contains the hardware definitions of the CS89712
- *  additional internal registers.
- *
- *  Copyright (C) 2001 Thomas Gleixner autronix automation <gleixner@autronix.de>
- *			
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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_HARDWARE_CS89712_H
-#define __ASM_HARDWARE_CS89712_H
-
-/*
-*	CS89712 additional registers
-*/
-                                  
-#define PCDR			0x0002	/* Port C Data register ---------------------------- */
-#define PCDDR			0x0042	/* Port C Data Direction register ------------------ */
-#define SDCONF			0x2300  /* SDRAM Configuration register ---------------------*/
-#define SDRFPR			0x2340  /* SDRAM Refresh period register --------------------*/
-
-#define SDCONF_ACTIVE		(1 << 10)
-#define SDCONF_CLKCTL		(1 << 9)
-#define SDCONF_WIDTH_4		(0 << 7)
-#define SDCONF_WIDTH_8		(1 << 7)
-#define SDCONF_WIDTH_16		(2 << 7)
-#define SDCONF_WIDTH_32		(3 << 7)
-#define SDCONF_SIZE_16		(0 << 5)
-#define SDCONF_SIZE_64		(1 << 5)
-#define SDCONF_SIZE_128		(2 << 5)
-#define SDCONF_SIZE_256		(3 << 5)
-#define SDCONF_CASLAT_2		(2)
-#define SDCONF_CASLAT_3		(3)
-
-#endif /* __ASM_HARDWARE_CS89712_H */
diff --git a/arch/arm/include/asm/hardware/debug-8250.S b/arch/arm/include/asm/hardware/debug-8250.S
deleted file mode 100644
index 22c689255e6..00000000000
--- a/arch/arm/include/asm/hardware/debug-8250.S
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * arch/arm/include/asm/hardware/debug-8250.S
- *
- *  Copyright (C) 1994-1999 Russell King
- *
- * 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.
- */
-#include <linux/serial_reg.h>
-
-		.macro	senduart,rd,rx
-		strb	\rd, [\rx, #UART_TX << UART_SHIFT]
-		.endm
-
-		.macro	busyuart,rd,rx
-1002:		ldrb	\rd, [\rx, #UART_LSR << UART_SHIFT]
-		and	\rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE
-		teq	\rd, #UART_LSR_TEMT | UART_LSR_THRE
-		bne	1002b
-		.endm
-
-		.macro	waituart,rd,rx
-#ifdef FLOW_CONTROL
-1001:		ldrb	\rd, [\rx, #UART_MSR << UART_SHIFT]
-		tst	\rd, #UART_MSR_CTS
-		beq	1001b
-#endif
-		.endm
diff --git a/arch/arm/include/asm/hardware/entry-macro-iomd.S b/arch/arm/include/asm/hardware/entry-macro-iomd.S
index e0af4983723..8c215acd9b5 100644
--- a/arch/arm/include/asm/hardware/entry-macro-iomd.S
+++ b/arch/arm/include/asm/hardware/entry-macro-iomd.S
@@ -11,14 +11,6 @@
 /* IOC / IOMD based hardware */
 #include <asm/hardware/iomd.h>
 
-		.macro	disable_fiq
-		mov	r12, #ioc_base_high
-		.if	ioc_base_low
-		orr	r12, r12, #ioc_base_low
-		.endif
-		strb	r12, [r12, #0x38]	@ Disable FIQ register
-		.endm
-
 		.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
 		ldrb	\irqstat, [\base, #IOMD_IRQREQB]	@ get high priority first
 		ldr	\tmp, =irq_prio_h
diff --git a/arch/arm/include/asm/hardware/ep7211.h b/arch/arm/include/asm/hardware/ep7211.h
deleted file mode 100644
index 654d5f625c4..00000000000
--- a/arch/arm/include/asm/hardware/ep7211.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- *  arch/arm/include/asm/hardware/ep7211.h
- *
- *  This file contains the hardware definitions of the EP7211 internal
- *  registers.
- *
- *  Copyright (C) 2001 Blue Mug, Inc.  All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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_HARDWARE_EP7211_H
-#define __ASM_HARDWARE_EP7211_H
-
-#include <asm/hardware/clps7111.h>
-
-/*
- * define EP7211_BASE to be the base address of the region
- * you want to access.
- */
-
-#define EP7211_PHYS_BASE	(0x80000000)
-
-/*
- * XXX miket@bluemug.com: need to introduce EP7211 registers (those not
- * present in 7212) here.
- */
-
-#endif /* __ASM_HARDWARE_EP7211_H */
diff --git a/arch/arm/include/asm/hardware/ep7212.h b/arch/arm/include/asm/hardware/ep7212.h
deleted file mode 100644
index 3b43bbeaf1d..00000000000
--- a/arch/arm/include/asm/hardware/ep7212.h
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- *  arch/arm/include/asm/hardware/ep7212.h
- *
- *  This file contains the hardware definitions of the EP7212 internal
- *  registers.
- *
- *  Copyright (C) 2000 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 as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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_HARDWARE_EP7212_H
-#define __ASM_HARDWARE_EP7212_H
-
-/*
- * define EP7212_BASE to be the base address of the region
- * you want to access.
- */
-
-#define EP7212_PHYS_BASE	(0x80000000)
-
-#ifndef __ASSEMBLY__
-#define ep_readl(off)		__raw_readl(EP7212_BASE + (off))
-#define ep_writel(val,off)	__raw_writel(val, EP7212_BASE + (off))
-#endif
-
-/*
- * These registers are specific to the EP7212 only
- */
-#define DAIR			0x2000
-#define DAIR0			0x2040
-#define DAIDR1			0x2080
-#define DAIDR2			0x20c0
-#define DAISR			0x2100
-#define SYSCON3			0x2200
-#define INTSR3			0x2240
-#define INTMR3			0x2280
-#define LEDFLSH			0x22c0
-
-#define DAIR_DAIEN		(1 << 16)
-#define DAIR_ECS		(1 << 17)
-#define DAIR_LCTM		(1 << 19)
-#define DAIR_LCRM		(1 << 20)
-#define DAIR_RCTM		(1 << 21)
-#define DAIR_RCRM		(1 << 22)
-#define DAIR_LBM		(1 << 23)
-
-#define DAIDR2_FIFOEN		(1 << 15)
-#define DAIDR2_FIFOLEFT		(0x0d << 16)
-#define DAIDR2_FIFORIGHT	(0x11 << 16)
-
-#define DAISR_RCTS		(1 << 0)
-#define DAISR_RCRS		(1 << 1)
-#define DAISR_LCTS		(1 << 2)
-#define DAISR_LCRS		(1 << 3)
-#define DAISR_RCTU		(1 << 4)
-#define DAISR_RCRO		(1 << 5)
-#define DAISR_LCTU		(1 << 6)
-#define DAISR_LCRO		(1 << 7)
-#define DAISR_RCNF		(1 << 8)
-#define DAISR_RCNE		(1 << 9)
-#define DAISR_LCNF		(1 << 10)
-#define DAISR_LCNE		(1 << 11)
-#define DAISR_FIFO		(1 << 12)
-
-#define SYSCON3_ADCCON		(1 << 0)
-#define SYSCON3_DAISEL		(1 << 3)
-#define SYSCON3_ADCCKNSEN	(1 << 4)
-#define SYSCON3_FASTWAKE	(1 << 8)
-#define SYSCON3_DAIEN		(1 << 9)
-
-#endif /* __ASM_HARDWARE_EP7212_H */
diff --git a/arch/arm/include/asm/hardware/gic.h b/arch/arm/include/asm/hardware/gic.h
deleted file mode 100644
index 7f34333bb54..00000000000
--- a/arch/arm/include/asm/hardware/gic.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- *  arch/arm/include/asm/hardware/gic.h
- *
- *  Copyright (C) 2002 ARM Limited, All Rights Reserved.
- *
- * 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_HARDWARE_GIC_H
-#define __ASM_ARM_HARDWARE_GIC_H
-
-#include <linux/compiler.h>
-
-#define GIC_CPU_CTRL			0x00
-#define GIC_CPU_PRIMASK			0x04
-#define GIC_CPU_BINPOINT		0x08
-#define GIC_CPU_INTACK			0x0c
-#define GIC_CPU_EOI			0x10
-#define GIC_CPU_RUNNINGPRI		0x14
-#define GIC_CPU_HIGHPRI			0x18
-
-#define GIC_DIST_CTRL			0x000
-#define GIC_DIST_CTR			0x004
-#define GIC_DIST_ENABLE_SET		0x100
-#define GIC_DIST_ENABLE_CLEAR		0x180
-#define GIC_DIST_PENDING_SET		0x200
-#define GIC_DIST_PENDING_CLEAR		0x280
-#define GIC_DIST_ACTIVE_BIT		0x300
-#define GIC_DIST_PRI			0x400
-#define GIC_DIST_TARGET			0x800
-#define GIC_DIST_CONFIG			0xc00
-#define GIC_DIST_SOFTINT		0xf00
-
-#ifndef __ASSEMBLY__
-void gic_dist_init(unsigned int gic_nr, void __iomem *base, unsigned int irq_start);
-void gic_cpu_init(unsigned int gic_nr, void __iomem *base);
-void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
-void gic_raise_softirq(const struct cpumask *mask, unsigned int irq);
-#endif
-
-#endif
diff --git a/arch/arm/include/asm/hardware/iop3xx-adma.h b/arch/arm/include/asm/hardware/iop3xx-adma.h
index 9b28f1243bd..240b29ef17d 100644
--- a/arch/arm/include/asm/hardware/iop3xx-adma.h
+++ b/arch/arm/include/asm/hardware/iop3xx-adma.h
@@ -393,36 +393,6 @@ static inline int iop_chan_zero_sum_slot_count(size_t len, int src_cnt,
 	return slot_cnt;
 }
 
-static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc)
-{
-	return 0;
-}
-
-static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
-					struct iop_adma_chan *chan)
-{
-	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
-
-	switch (chan->device->id) {
-	case DMA0_ID:
-	case DMA1_ID:
-		return hw_desc.dma->dest_addr;
-	case AAU_ID:
-		return hw_desc.aau->dest_addr;
-	default:
-		BUG();
-	}
-	return 0;
-}
-
-
-static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc,
-					  struct iop_adma_chan *chan)
-{
-	BUG();
-	return 0;
-}
-
 static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan)
 {
diff --git a/arch/arm/include/asm/hardware/iop3xx-gpio.h b/arch/arm/include/asm/hardware/iop3xx-gpio.h
deleted file mode 100644
index b69d972b1f7..00000000000
--- a/arch/arm/include/asm/hardware/iop3xx-gpio.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * arch/arm/include/asm/hardware/iop3xx-gpio.h
- *
- * IOP3xx GPIO wrappers
- *
- * Copyright (c) 2008 Arnaud Patard <arnaud.patard@rtp-net.org>
- * Based on IXP4XX gpio.h file
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-
-#ifndef __ASM_ARM_HARDWARE_IOP3XX_GPIO_H
-#define __ASM_ARM_HARDWARE_IOP3XX_GPIO_H
-
-#include <mach/hardware.h>
-#include <asm-generic/gpio.h>
-
-#define IOP3XX_N_GPIOS	8
-
-static inline int gpio_get_value(unsigned gpio)
-{
-	if (gpio > IOP3XX_N_GPIOS)
-		return __gpio_get_value(gpio);
-
-	return gpio_line_get(gpio);
-}
-
-static inline void gpio_set_value(unsigned gpio, int value)
-{
-	if (gpio > IOP3XX_N_GPIOS) {
-		__gpio_set_value(gpio, value);
-		return;
-	}
-	gpio_line_set(gpio, value);
-}
-
-static inline int gpio_cansleep(unsigned gpio)
-{
-	if (gpio < IOP3XX_N_GPIOS)
-		return 0;
-	else
-		return __gpio_cansleep(gpio);
-}
-
-/*
- * The GPIOs are not generating any interrupt
- * Note : manuals are not clear about this
- */
-static inline int gpio_to_irq(int gpio)
-{
-	return -EINVAL;
-}
-
-static inline int irq_to_gpio(int gpio)
-{
-	return -EINVAL;
-}
-
-#endif
-
diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h
index 5daea2961d4..2594a95ff19 100644
--- a/arch/arm/include/asm/hardware/iop3xx.h
+++ b/arch/arm/include/asm/hardware/iop3xx.h
@@ -18,16 +18,9 @@
 /*
  * IOP3XX GPIO handling
  */
-#define GPIO_IN			0
-#define GPIO_OUT		1
-#define GPIO_LOW		0
-#define GPIO_HIGH		1
 #define IOP3XX_GPIO_LINE(x)	(x)
 
 #ifndef __ASSEMBLY__
-extern void gpio_line_config(int line, int direction);
-extern int  gpio_line_get(int line);
-extern void gpio_line_set(int line, int value);
 extern int init_atu;
 extern int iop3xx_get_init_atu(void);
 #endif
@@ -37,7 +30,7 @@ extern int iop3xx_get_init_atu(void);
  * IOP3XX processor registers
  */
 #define IOP3XX_PERIPHERAL_PHYS_BASE	0xffffe000
-#define IOP3XX_PERIPHERAL_VIRT_BASE	0xfeffe000
+#define IOP3XX_PERIPHERAL_VIRT_BASE	0xfedfe000
 #define IOP3XX_PERIPHERAL_SIZE		0x00002000
 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\
 					IOP3XX_PERIPHERAL_SIZE - 1)
@@ -168,11 +161,6 @@ extern int iop3xx_get_init_atu(void);
 /* PERCR0 DOESN'T EXIST - index from 1! */
 #define IOP3XX_PERCR0		(volatile u32 *)IOP3XX_REG_ADDR(0x0710)
 
-/* General Purpose I/O  */
-#define IOP3XX_GPOE		(volatile u32 *)IOP3XX_GPIO_REG(0x0000)
-#define IOP3XX_GPID		(volatile u32 *)IOP3XX_GPIO_REG(0x0004)
-#define IOP3XX_GPOD		(volatile u32 *)IOP3XX_GPIO_REG(0x0008)
-
 /* Timers  */
 #define IOP3XX_TU_TMR0		(volatile u32 *)IOP3XX_TIMER_REG(0x0000)
 #define IOP3XX_TU_TMR1		(volatile u32 *)IOP3XX_TIMER_REG(0x0004)
@@ -217,23 +205,18 @@ extern int iop3xx_get_init_atu(void);
 #define IOP3XX_PCI_LOWER_MEM_PA	0x80000000
 #define IOP3XX_PCI_MEM_WINDOW_SIZE	0x08000000
 
-#define IOP3XX_PCI_IO_WINDOW_SIZE	0x00010000
 #define IOP3XX_PCI_LOWER_IO_PA		0x90000000
-#define IOP3XX_PCI_LOWER_IO_VA		0xfe000000
-#define IOP3XX_PCI_LOWER_IO_BA		0x90000000
-#define IOP3XX_PCI_UPPER_IO_PA		(IOP3XX_PCI_LOWER_IO_PA +\
-					IOP3XX_PCI_IO_WINDOW_SIZE - 1)
-#define IOP3XX_PCI_UPPER_IO_VA		(IOP3XX_PCI_LOWER_IO_VA +\
-					IOP3XX_PCI_IO_WINDOW_SIZE - 1)
-#define IOP3XX_PCI_IO_PHYS_TO_VIRT(addr) (((u32) (addr) -\
-					IOP3XX_PCI_LOWER_IO_PA) +\
-					IOP3XX_PCI_LOWER_IO_VA)
-
+#define IOP3XX_PCI_LOWER_IO_BA		0x00000000
 
 #ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/reboot.h>
+
 void iop3xx_map_io(void);
 void iop_init_cp6_handler(void);
 void iop_init_time(unsigned long tickrate);
+void iop3xx_restart(enum reboot_mode, const char *);
 
 static inline u32 read_tmr0(void)
 {
diff --git a/arch/arm/include/asm/hardware/iop_adma.h b/arch/arm/include/asm/hardware/iop_adma.h
index 59b8c3892f7..250760e0810 100644
--- a/arch/arm/include/asm/hardware/iop_adma.h
+++ b/arch/arm/include/asm/hardware/iop_adma.h
@@ -49,7 +49,6 @@ struct iop_adma_device {
 /**
  * struct iop_adma_chan - internal representation of an ADMA device
  * @pending: allows batching of hardware operations
- * @completed_cookie: identifier for the most recently completed operation
  * @lock: serializes enqueue/dequeue operations to the slot pool
  * @mmr_base: memory mapped register base
  * @chain: device chain view of the descriptors
@@ -62,7 +61,6 @@ struct iop_adma_device {
  */
 struct iop_adma_chan {
 	int pending;
-	dma_cookie_t completed_cookie;
 	spinlock_t lock; /* protects the descriptor slot pool */
 	void __iomem *mmr_base;
 	struct list_head chain;
@@ -84,8 +82,6 @@ struct iop_adma_chan {
  * @slot_cnt: total slots used in an transaction (group of operations)
  * @slots_per_op: number of slots per operation
  * @idx: pool index
- * @unmap_src_cnt: number of xor sources
- * @unmap_len: transaction bytecount
  * @tx_list: list of descriptors that are associated with one operation
  * @async_tx: support for the async_tx api
  * @group_list: list of slots that make up a multi-descriptor transaction
@@ -101,8 +97,6 @@ struct iop_adma_desc_slot {
 	u16 slot_cnt;
 	u16 slots_per_op;
 	u16 idx;
-	u16 unmap_src_cnt;
-	size_t unmap_len;
 	struct list_head tx_list;
 	struct dma_async_tx_descriptor async_tx;
 	union {
diff --git a/arch/arm/include/asm/hardware/it8152.h b/arch/arm/include/asm/hardware/it8152.h
index 21fa272301f..d36a73d7c0e 100644
--- a/arch/arm/include/asm/hardware/it8152.h
+++ b/arch/arm/include/asm/hardware/it8152.h
@@ -9,7 +9,10 @@
 
 #ifndef __ASM_HARDWARE_IT8152_H
 #define __ASM_HARDWARE_IT8152_H
-extern unsigned long it8152_base_address;
+
+#include <mach/irqs.h>
+
+extern void __iomem *it8152_base_address;
 
 #define IT8152_IO_BASE			(it8152_base_address + 0x03e00000)
 #define IT8152_CFGREG_BASE		(it8152_base_address + 0x03f00000)
@@ -76,6 +79,7 @@ extern unsigned long it8152_base_address;
   IT8152_PD_IRQ(0)  Audio controller (ACR)
  */
 #define IT8152_IRQ(x)   (IRQ_BOARD_START + (x))
+#define IT8152_LAST_IRQ	(IRQ_BOARD_START + 40)
 
 /* IRQ-sources in 3 groups - local devices, LPC (serial), and external PCI */
 #define IT8152_LD_IRQ_COUNT     9
@@ -104,8 +108,8 @@ struct pci_sys_data;
 
 extern void it8152_irq_demux(unsigned int irq, struct irq_desc *desc);
 extern void it8152_init_irq(void);
-extern int it8152_pci_map_irq(struct pci_dev *dev, u8 slot, u8 pin);
+extern int it8152_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin);
 extern int it8152_pci_setup(int nr, struct pci_sys_data *sys);
-extern struct pci_bus *it8152_pci_scan_bus(int nr, struct pci_sys_data *sys);
+extern struct pci_ops it8152_ops;
 
 #endif /* __ASM_HARDWARE_IT8152_H */
diff --git a/arch/arm/include/asm/hardware/linkup-l1110.h b/arch/arm/include/asm/hardware/linkup-l1110.h
deleted file mode 100644
index 7ec91168a57..00000000000
--- a/arch/arm/include/asm/hardware/linkup-l1110.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
-*
-* Definitions for H3600 Handheld Computer
-*
-* Copyright 2001 Compaq Computer Corporation.
-*
-* Use consistent with the GNU GPL is permitted,
-* provided that this copyright notice is
-* preserved in its entirety in all copies and derived works.
-*
-* COMPAQ COMPUTER CORPORATION MAKES NO WARRANTIES, EXPRESSED OR IMPLIED,
-* AS TO THE USEFULNESS OR CORRECTNESS OF THIS CODE OR ITS
-* FITNESS FOR ANY PARTICULAR PURPOSE.
-*
-* Author: Jamey Hicks.
-*
-*/
-
-/* LinkUp Systems PCCard/CompactFlash Interface for SA-1100 */
-
-/* PC Card Status Register */
-#define LINKUP_PRS_S1	(1 << 0) /* voltage control bits S1-S4 */
-#define LINKUP_PRS_S2	(1 << 1)
-#define LINKUP_PRS_S3	(1 << 2)
-#define LINKUP_PRS_S4	(1 << 3)
-#define LINKUP_PRS_BVD1	(1 << 4)
-#define LINKUP_PRS_BVD2	(1 << 5)
-#define LINKUP_PRS_VS1	(1 << 6)
-#define LINKUP_PRS_VS2	(1 << 7)
-#define LINKUP_PRS_RDY	(1 << 8)
-#define LINKUP_PRS_CD1	(1 << 9)
-#define LINKUP_PRS_CD2	(1 << 10)
-
-/* PC Card Command Register */
-#define LINKUP_PRC_S1	(1 << 0)
-#define LINKUP_PRC_S2	(1 << 1)
-#define LINKUP_PRC_S3	(1 << 2)
-#define LINKUP_PRC_S4	(1 << 3)
-#define LINKUP_PRC_RESET (1 << 4)
-#define LINKUP_PRC_APOE	(1 << 5) /* Auto Power Off Enable: clears S1-S4 when either nCD goes high */
-#define LINKUP_PRC_CFE	(1 << 6) /* CompactFlash mode Enable: addresses A[10:0] only, A[25:11] high */
-#define LINKUP_PRC_SOE	(1 << 7) /* signal output driver enable */
-#define LINKUP_PRC_SSP	(1 << 8) /* sock select polarity: 0 for socket 0, 1 for socket 1 */
-#define LINKUP_PRC_MBZ	(1 << 15) /* must be zero */
-
-struct linkup_l1110 {
-	volatile short prc;
-};
diff --git a/arch/arm/include/asm/hardware/pci_v3.h b/arch/arm/include/asm/hardware/pci_v3.h
deleted file mode 100644