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

* 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm: (416 commits)
  ARM: DMA: add support for DMA debugging
  ARM: PL011: add DMA burst threshold support for ST variants
  ARM: PL011: Add support for transmit DMA
  ARM: PL011: Ensure IRQs are disabled in UART interrupt handler
  ARM: PL011: Separate hardware FIFO size from TTY FIFO size
  ARM: PL011: Allow better handling of vendor data
  ARM: PL011: Ensure error flags are clear at startup
  ARM: PL011: include revision number in boot-time port printk
  ARM: vexpress: add sched_clock() for Versatile Express
  ARM i.MX53: Make MX53 EVK bootable
  ARM i.MX53: Some bug fix about MX53 MSL code
  ARM: 6607/1: sa1100: Update platform device registration
  ARM: 6606/1: sa1100: Fix platform device registration
  ARM i.MX51: rename IPU irqs
  ARM i.MX51: Add ipu clock support
  ARM: imx/mx27_3ds: Add PMIC support
  ARM: DMA: Replace page_to_dma()/dma_to_page() with pfn_to_dma()/dma_to_pfn()
  mx51: fix usb clock support
  MX51: Add support for usb host 2
  arch/arm/plat-mxc/ehci.c: fix errors/typos
  ...

30 files changed, 674 insertions, 323 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 749bb662240..bc2d2d75f70 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -18,6 +18,7 @@
 #endif
 
 #include <asm/ptrace.h>
+#include <asm/domain.h>
 
 /*
  * Endian independent macros for shifting bytes within registers.
@@ -157,16 +158,24 @@
 #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...)
@@ -177,16 +186,24 @@
 /*
  * SMP data memory barrier
  */
-	.macro	smp_dmb
+	.macro	smp_dmb mode
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
+	.ifeqs "\mode","arm"
 	ALT_SMP(dmb)
+	.else
+	ALT_SMP(W(dmb))
+	.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
 
@@ -206,12 +223,12 @@
  */
 #ifdef CONFIG_THUMB2_KERNEL
 
-	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort
+	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=T()
 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
@@ -246,13 +263,13 @@
 
 #else	/* !CONFIG_THUMB2_KERNEL */
 
-	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort
+	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort, t=T()
 	.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
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/clkdev.h b/arch/arm/include/asm/clkdev.h
index b56c1389b6f..765d3322236 100644
--- a/arch/arm/include/asm/clkdev.h
+++ b/arch/arm/include/asm/clkdev.h
@@ -12,23 +12,13 @@
 #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;
-};
+#include <mach/clkdev.h>
 
-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);
-
-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/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index c568da7dcae..4fff837363e 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -5,24 +5,29 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
 
 #include <asm-generic/dma-coherent.h>
 #include <asm/memory.h>
 
+#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));
+	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));
+	return __bus_to_pfn(addr);
 }
 
 static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
@@ -35,14 +40,14 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *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)
@@ -293,13 +298,13 @@ 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,
+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,
+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 *,
+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,
+extern void __dma_unmap_page(struct device *, dma_addr_t, size_t,
 		enum dma_data_direction);
 
 /*
@@ -323,6 +328,34 @@ static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
 }
 
 
+static inline dma_addr_t __dma_map_single(struct device *dev, void *cpu_addr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_single_cpu_to_dev(cpu_addr, size, dir);
+	return virt_to_dma(dev, cpu_addr);
+}
+
+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)
+{
+	__dma_page_cpu_to_dev(page, offset, size, dir);
+	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
+}
+
+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);
+}
+
+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(pfn_to_page(dma_to_pfn(dev, handle)),
+		handle & ~PAGE_MASK, size, dir);
+}
+#endif /* CONFIG_DMABOUNCE */
+
 /**
  * dma_map_single - map a single buffer for streaming DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
@@ -340,11 +373,16 @@ static inline int dmabounce_sync_for_device(struct device *d, dma_addr_t addr,
 static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
 		size_t size, enum dma_data_direction dir)
 {
+	dma_addr_t addr;
+
 	BUG_ON(!valid_dma_direction(dir));
 
-	__dma_single_cpu_to_dev(cpu_addr, size, dir);
+	addr = __dma_map_single(dev, cpu_addr, size, dir);
+	debug_dma_map_page(dev, virt_to_page(cpu_addr),
+			(unsigned long)cpu_addr & ~PAGE_MASK, size,
+			dir, addr, true);
 
-	return virt_to_dma(dev, cpu_addr);
+	return addr;
 }
 
 /**
@@ -364,11 +402,14 @@ static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
 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)
 {
+	dma_addr_t addr;
+
 	BUG_ON(!valid_dma_direction(dir));
 
-	__dma_page_cpu_to_dev(page, offset, size, dir);
+	addr = __dma_map_page(dev, page, offset, size, dir);
+	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
 
-	return page_to_dma(dev, page) + offset;
+	return addr;
 }
 
 /**
@@ -388,7 +429,8 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
 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);
+	debug_dma_unmap_page(dev, handle, size, dir, true);
+	__dma_unmap_single(dev, handle, size, dir);
 }
 
 /**
@@ -408,10 +450,9 @@ static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
 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);
+	debug_dma_unmap_page(dev, handle, size, dir, false);
+	__dma_unmap_page(dev, handle, size, dir);
 }
-#endif /* CONFIG_DMABOUNCE */
 
 /**
  * dma_sync_single_range_for_cpu
@@ -437,6 +478,8 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
 {
 	BUG_ON(!valid_dma_direction(dir));
 
+	debug_dma_sync_single_for_cpu(dev, handle + offset, size, dir);
+
 	if (!dmabounce_sync_for_cpu(dev, handle, offset, size, dir))
 		return;
 
@@ -449,6 +492,8 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
 {
 	BUG_ON(!valid_dma_direction(dir));
 
+	debug_dma_sync_single_for_device(dev, handle + offset, size, dir);
+
 	if (!dmabounce_sync_for_device(dev, handle, offset, size, dir))
 		return;
 
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index cc7ef408071..af18ceaacf5 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -45,13 +45,17 @@
  */
 #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
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define set_domain(x)					\
 	do {						\
 	__asm__ __volatile__(				\
@@ -74,5 +78,28 @@
 #define modify_domain(dom,type)	do { } while (0)
 #endif
 
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions (inline assembly)
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define T(instr)	#instr "t"
+#else
+#define T(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 T(instr)	instr ## t
+#else
+#define T(instr)	instr
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* !__ASM_PROC_DOMAIN_H */
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 8bb66bca2e3..c3cd8755e64 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -99,6 +99,8 @@ 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)
 
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..ec0bbf79c71
--- /dev/null
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -0,0 +1,44 @@
+/*
+ * Interrupt handling.  Preserves r7, r8, r9
+ */
+	.macro	arch_irq_handler_default
+	get_irqnr_preamble r5, lr
+1:	get_irqnr_and_base r0, r6, r5, 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 (r6) and base (r5) are
+	 * preserved from get_irqnr_and_base above
+	 */
+	ALT_SMP(test_for_ipi r0, r6, r5, lr)
+	ALT_UP_B(9997f)
+	movne	r1, sp
+	adrne	lr, BSYM(1b)
+	bne	do_IPI
+
+#ifdef CONFIG_LOCAL_TIMERS
+	test_for_ltirq r0, r6, r5, lr
+	movne	r0, sp
+	adrne	lr, BSYM(1b)
+	bne	do_local_timer
+#endif
+#endif
+9997:
+	.endm
+
+	.macro	arch_irq_handler, symbol_name
+	.align	5
+	.global \symbol_name
+\symbol_name:
+	mov	r4, lr
+	arch_irq_handler_default
+	mov     pc, r4
+	.endm
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 540a044153a..b33fe7065b3 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -13,12 +13,13 @@
 #include <linux/preempt.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
 	__asm__ __volatile__(					\
-	"1:	ldrt	%1, [%2]\n"				\
+	"1:	" T(ldr) "	%1, [%2]\n"			\
 	"	" insn "\n"					\
-	"2:	strt	%0, [%2]\n"				\
+	"2:	" T(str) "	%0, [%2]\n"			\
 	"	mov	%0, #0\n"				\
 	"3:\n"							\
 	"	.pushsection __ex_table,\"a\"\n"		\
@@ -97,10 +98,10 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 	pagefault_disable();	/* implies preempt_disable() */
 
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	ldrt	%0, [%3]\n"
+	"1:	" T(ldr) "	%0, [%3]\n"
 	"	teq	%0, %1\n"
 	"	it	eq	@ explicit IT needed for the 2b label\n"
-	"2:	streqt	%2, [%3]\n"
+	"2:	" T(streq) "	%2, [%3]\n"
 	"3:\n"
 	"	.pushsection __ex_table,\"a\"\n"
 	"	.align	3\n"
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 6d7485aff95..89ad1805e57 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,13 +5,31 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
+#define NR_IPI	5
+
 typedef struct {
 	unsigned int __softirq_pending;
+#ifdef CONFIG_LOCAL_TIMERS
 	unsigned int local_timer_irqs;
+#endif
+#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 */
 
+#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 smp_irq_stat_cpu(cpu)	0
+#endif
+
+#define arch_irq_stat_cpu	smp_irq_stat_cpu
+
 #if NR_IRQS > 512
 #define HARDIRQ_BITS	10
 #elif NR_IRQS > 256
diff --git a/arch/arm/include/asm/hardware/entry-macro-gic.S b/arch/arm/include/asm/hardware/entry-macro-gic.S
new file mode 100644
index 00000000000..c115b82fe80
--- /dev/null
+++ b/arch/arm/include/asm/hardware/entry-macro-gic.S
@@ -0,0 +1,75 @@
+/*
+ * arch/arm/include/asm/hardware/entry-macro-gic.S
+ *
+ * Low-level IRQ helper macros for GIC
+ *
+ * This file is licensed under  the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <asm/hardware/gic.h>
+
+#ifndef HAVE_GET_IRQNR_PREAMBLE
+	.macro	get_irqnr_preamble, base, tmp
+	ldr	\base, =gic_cpu_base_addr
+	ldr	\base, [\base]
+	.endm
+#endif
+
+/*
+ * The interrupt numbering scheme is defined in the
+ * interrupt controller spec.  To wit:
+ *
+ * Interrupts 0-15 are IPI
+ * 16-28 are reserved
+ * 29-31 are local.  We allow 30 to be used for the watchdog.
+ * 32-1020 are global
+ * 1021-1022 are reserved
+ * 1023 is "spurious" (no interrupt)
+ *
+ * For now, we ignore all local interrupts so only return an interrupt if it's
+ * between 30 and 1020.  The test_for_ipi routine below will pick up on IPIs.
+ *
+ * A simple read from the controller will tell us the number of the highest
+ * priority enabled interrupt.  We then just need to check whether it is in the
+ * valid range for an IRQ (30-1020 inclusive).
+ */
+
+	.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
+
+	ldr     \irqstat, [\base, #GIC_CPU_INTACK]
+	/* bits 12-10 = src CPU, 9-0 = int # */
+
+	ldr	\tmp, =1021
+	bic     \irqnr, \irqstat, #0x1c00
+	cmp     \irqnr, #29
+	cmpcc	\irqnr, \irqnr
+	cmpne	\irqnr, \tmp
+	cmpcs	\irqnr, \irqnr
+	.endm
+
+/* We assume that irqstat (the raw value of the IRQ acknowledge
+ * register) is preserved from the macro above.
+ * If there is an IPI, we immediately signal end of interrupt on the
+ * controller, since this requires the original irqstat value which
+ * we won't easily be able to recreate later.
+ */
+
+	.macro test_for_ipi, irqnr, irqstat, base, tmp
+	bic	\irqnr, \irqstat, #0x1c00
+	cmp	\irqnr, #16
+	strcc	\irqstat, [\base, #GIC_CPU_EOI]
+	cmpcs	\irqnr, \irqnr
+	.endm
+
+/* As above, this assumes that irqstat and base are preserved.. */
+
+	.macro test_for_ltirq, irqnr, irqstat, base, tmp
+	bic	\irqnr, \irqstat, #0x1c00
+	mov 	\tmp, #0
+	cmp	\irqnr, #29
+	moveq	\tmp, #1
+	streq	\irqstat, [\base, #GIC_CPU_EOI]
+	cmp	\tmp, #0
+	.endm
diff --git a/arch/arm/include/asm/hardware/gic.h b/arch/arm/include/asm/hardware/gic.h
index 7f34333bb54..84557d32100 100644
--- a/arch/arm/include/asm/hardware/gic.h
+++ b/arch/arm/include/asm/hardware/gic.h
@@ -33,10 +33,13 @@
 #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);
+extern void __iomem *gic_cpu_base_addr;
+
+void gic_init(unsigned int, unsigned int, void __iomem *, void __iomem *);
+void gic_secondary_init(unsigned int);
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq);
+void gic_enable_ppi(unsigned int);
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/hardware/timer-sp.h b/arch/arm/include/asm/hardware/timer-sp.h
new file mode 100644
index 00000000000..21e75e30d49
--- /dev/null
+++ b/arch/arm/include/asm/hardware/timer-sp.h
@@ -0,0 +1,2 @@
+void sp804_clocksource_init(void __iomem *);
+void sp804_clockevents_init(void __iomem *, unsigned int);
diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index 4d8ae9d67ab..f389b2704d8 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -20,8 +20,8 @@ struct arch_hw_breakpoint_ctrl {
 struct arch_hw_breakpoint {
 	u32	address;
 	u32	trigger;
-	struct perf_event *suspended_wp;
-	struct arch_hw_breakpoint_ctrl ctrl;
+	struct	arch_hw_breakpoint_ctrl step_ctrl;
+	struct	arch_hw_breakpoint_ctrl ctrl;
 };
 
 static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 815efa2d4e0..20e0f7c9e03 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -241,18 +241,15 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
  *
  */
 #ifndef __arch_ioremap
-#define ioremap(cookie,size)		__arm_ioremap(cookie, size, MT_DEVICE)
-#define ioremap_nocache(cookie,size)	__arm_ioremap(cookie, size, MT_DEVICE)
-#define ioremap_cached(cookie,size)	__arm_ioremap(cookie, size, MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size)		__arm_ioremap(cookie, size, MT_DEVICE_WC)
-#define iounmap(cookie)			__iounmap(cookie)
-#else
+#define __arch_ioremap			__arm_ioremap
+#define __arch_iounmap			__iounmap
+#endif
+
 #define ioremap(cookie,size)		__arch_ioremap((cookie), (size), MT_DEVICE)
 #define ioremap_nocache(cookie,size)	__arch_ioremap((cookie), (size), MT_DEVICE)
 #define ioremap_cached(cookie,size)	__arch_ioremap((cookie), (size), MT_DEVICE_CACHED)
 #define ioremap_wc(cookie,size)		__arch_ioremap((cookie), (size), MT_DEVICE_WC)
-#define iounmap(cookie)			__arch_iounmap(cookie)
-#endif
+#define iounmap				__arch_iounmap
 
 /*
  * io{read,write}{8,16,32} macros
diff --git a/arch/arm/include/asm/kexec.h b/arch/arm/include/asm/kexec.h
index 8ec9ef5c3c7..c0094d8edae 100644
--- a/arch/arm/include/asm/kexec.h
+++ b/arch/arm/include/asm/kexec.h
@@ -33,10 +33,20 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 	if (oldregs) {
 		memcpy(newregs, oldregs, sizeof(*newregs));
 	} else {
-		__asm__ __volatile__ ("stmia %0, {r0 - r15}"
-				      : : "r" (&newregs->ARM_r0));
-		__asm__ __volatile__ ("mrs %0, cpsr"
-				      : "=r" (newregs->ARM_cpsr));
+		__asm__ __volatile__ (
+			"stmia	%[regs_base], {r0-r12}\n\t"
+			"mov	%[_ARM_sp], sp\n\t"
+			"str	lr, %[_ARM_lr]\n\t"
+			"adr	%[_ARM_pc], 1f\n\t"
+			"mrs	%[_ARM_cpsr], cpsr\n\t"
+		"1:"
+			: [_ARM_pc] "=r" (newregs->ARM_pc),
+			  [_ARM_cpsr] "=r" (newregs->ARM_cpsr),
+			  [_ARM_sp] "=r" (newregs->ARM_sp),
+			  [_ARM_lr] "=o" (newregs->ARM_lr)
+			: [regs_base] "r" (&newregs->ARM_r0)
+			: "memory"
+		);
 	}
 }
 
diff --git a/arch/arm/include/asm/localtimer.h b/arch/arm/include/asm/localtimer.h
index 50c7e7cfd67..6bc63ab498c 100644
--- a/arch/arm/include/asm/localtimer.h
+++ b/arch/arm/include/asm/localtimer.h
@@ -30,7 +30,6 @@ asmlinkage void do_local_timer(struct pt_regs *);
 #include "smp_twd.h"
 
 #define local_timer_ack()	twd_timer_ack()
-#define local_timer_stop()	twd_timer_stop()
 
 #else
 
@@ -40,11 +39,6 @@ asmlinkage void do_local_timer(struct pt_regs *);
  */
 int local_timer_ack(void);
 
-/*
- * Stop a local timer interrupt.
- */
-void local_timer_stop(void);
-
 #endif
 
 /*
@@ -52,12 +46,6 @@ void local_timer_stop(void);
  */
 void local_timer_setup(struct clock_event_device *);
 
-#else
-
-static inline void local_timer_stop(void)
-{
-}
-
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index d97a964207f..3a0893a76a3 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -37,12 +37,21 @@ struct machine_desc {
 					 struct meminfo *);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
+	void			(*init_early)(void);
 	void			(*init_irq)(void);
 	struct sys_timer	*timer;		/* system tick timer	*/
 	void			(*init_machine)(void);
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+	void			(*handle_irq)(struct pt_regs *);
+#endif
 };
 
 /*
+ * Current machine - only accessible during boot.
+ */
+extern struct machine_desc *machine_desc;
+
+/*
  * Set of macros to define architecture features.  This is built into
  * a table by the linker.
  */
diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h
index ce3eee9fe26..22ac140edd9 100644
--- a/arch/arm/include/asm/mach/irq.h
+++ b/arch/arm/include/asm/mach/irq.h
@@ -17,10 +17,12 @@ struct seq_file;
 /*
  * This is internal.  Do not use it.
  */
-extern unsigned int arch_nr_irqs;
-extern void (*init_arch_irq)(void);
 extern void init_FIQ(void);
-extern int show_fiq_list(struct seq_file *, void *);
+extern int show_fiq_list(struct seq_file *, int);
+
+#ifdef CONFIG_MULTI_IRQ_HANDLER
+extern void (*handle_arch_irq)(struct pt_regs *);
+#endif
 
 /*
  * This is for easy migration, but should be changed in the source
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index 35d408f6dcc..883f6be5117 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -43,7 +43,6 @@ struct sys_timer {
 #endif
 };
 
-extern struct sys_timer *system_timer;
 extern void timer_tick(void);
 
 #endif
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index cbb0bc295d2..12c8e680cbf 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -8,11 +8,6 @@
 struct unwind_table;
 
 #ifdef CONFIG_ARM_UNWIND
-struct arm_unwind_mapping {
-	Elf_Shdr *unw_sec;
-	Elf_Shdr *sec_text;
-	struct unwind_table *unwind;
-};
 enum {
 	ARM_SEC_INIT,
 	ARM_SEC_DEVINIT,
@@ -21,13 +16,13 @@ enum {
 	ARM_SEC_DEVEXIT,
 	ARM_SEC_MAX,
 };
+#endif
+
 struct mod_arch_specific {
-	struct arm_unwind_mapping map[ARM_SEC_MAX];
-};
-#else
-struct mod_arch_specific {
-};
+#ifdef CONFIG_ARM_UNWIND
+	struct unwind_table *unwind[ARM_SEC_MAX];
 #endif
+};
 
 /*
  * Include the ARM architecture version.
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index a485ac3c869..f51a69595f6 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -151,13 +151,15 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
 #define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
+typedef unsigned long pteval_t;
+
 #undef STRICT_MM_TYPECHECKS
 
 #ifdef STRICT_MM_TYPECHECKS
 /*
  * These are used to make use of C type-checking..
  */
-typedef struct { unsigned long pte; } pte_t;
+typedef struct { pteval_t pte; } pte_t;
 typedef struct { unsigned long pmd; } pmd_t;
 typedef struct { unsigned long pgd[2]; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
@@ -175,7 +177,7 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 /*
  * .. while these make it easier on the compiler
  */
-typedef unsigned long pte_t;
+typedef pteval_t pte_t;
 typedef unsigned long pmd_t;
 typedef unsigned long pgd_t[2];
 typedef unsigned long pgprot_t;
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index b12cc98bbe0..9763be04f77 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -30,14 +30,16 @@
 #define pmd_free(mm, pmd)		do { } while (0)
 #define pgd_populate(mm,pmd,pte)	BUG()
 
-extern pgd_t *get_pgd_slow(struct mm_struct *mm);
-extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd);
-
-#define pgd_alloc(mm)			get_pgd_slow(mm)
-#define pgd_free(mm, pgd)		free_pgd_slow(mm, pgd)
+extern pgd_t *pgd_alloc(struct mm_struct *mm);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
 #define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
 
+static inline void clean_pte_table(pte_t *pte)
+{
+	clean_dcache_area(pte + PTE_HWTABLE_PTRS, PTE_HWTABLE_SIZE);
+}
+
 /*
  * Allocate one PTE table.
  *
@@ -45,14 +47,14 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd);
  * into one table thus:
  *
  *  +------------+
- *  |  h/w pt 0  |
- *  +------------+
- *  |  h/w pt 1  |
- *  +------------+
  *  | Linux pt 0 |
  *  +------------+
  *  | Linux pt 1 |
  *  +------------+
+ *  |  h/w pt 0  |
+ *  +------------+
+ *  |  h/w pt 1  |
+ *  +------------+
  */
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
@@ -60,10 +62,8 @@ pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
 	pte_t *pte;
 
 	pte = (pte_t *)__get_free_page(PGALLOC_GFP);
-	if (pte) {
-		clean_dcache_area(pte, sizeof(pte_t) * PTRS_PER_PTE);
-		pte += PTRS_PER_PTE;
-	}
+	if (pte)
+		clean_pte_table(pte);
 
 	return pte;
 }
@@ -79,10 +79,8 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr)
 	pte = alloc_pages(PGALLOC_GFP, 0);
 #endif
 	if (pte) {
-		if (!PageHighMem(pte)) {
-			void *page = page_address(pte);
-			clean_dcache_area(page, sizeof(pte_t) * PTRS_PER_PTE);
-		}
+		if (!PageHighMem(pte))
+			clean_pte_table(page_address(pte));
 		pgtable_page_ctor(pte);
 	}
 
@@ -94,10 +92,8 @@ pte_alloc_one(struct mm_struct *mm, unsigned long addr)
  */
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
-	if (pte) {
-		pte -= PTRS_PER_PTE;
+	if (pte)
 		free_page((unsigned long)pte);
-	}
 }
 
 static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
@@ -106,8 +102,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
 	__free_page(pte);
 }
 
-static inline void __pmd_populate(pmd_t *pmdp, unsigned long pmdval)
+static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
+	unsigned long prot)
 {
+	unsigned long pmdval = (pte + PTE_HWTABLE_OFF) | prot;
 	pmdp[0] = __pmd(pmdval);
 	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
 	flush_pmd_entry(pmdp);
@@ -122,20 +120,16 @@ static inline void __pmd_populate(pmd_t *pmdp, unsigned long pmdval)
 static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
 {
-	unsigned long pte_ptr = (unsigned long)ptep;
-
 	/*
-	 * The pmd must be loaded with the physical
-	 * address of the PTE table
+	 * The pmd must be loaded with the physical address of the PTE table
 	 */
-	pte_ptr -= PTRS_PER_PTE * sizeof(void *);
-	__pmd_populate(pmdp, __pa(pte_ptr) | _PAGE_KERNEL_TABLE);
+	__pmd_populate(pmdp, __pa(ptep), _PAGE_KERNEL_TABLE);
 }
 
 static inline void
 pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
 {
-	__pmd_populate(pmdp, page_to_pfn(ptep) << PAGE_SHIFT | _PAGE_USER_TABLE);
+	__pmd_populate(pmdp, page_to_phys(ptep), _PAGE_USER_TABLE);
 }
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 53d1d5deb11..ebcb6432f45 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -10,6 +10,7 @@
 #ifndef _ASMARM_PGTABLE_H
 #define _ASMARM_PGTABLE_H
 
+#include <linux/const.h>
 #include <asm-generic/4level-fixup.h>
 #include <asm/proc-fns.h>
 
@@ -54,7 +55,7 @@
  * Therefore, we tweak the implementation slightly - we tell Linux that we
  * have 2048 entries in the first level, each of which is 8 bytes (iow, two
  * hardware pointers to the second level.)  The second level contains two
- * hardware PTE tables arranged contiguously, followed by Linux versions
+ * hardware PTE tables arranged contiguously, preceded by Linux versions
  * which contain the state information Linux needs.  We, therefore, end up
  * with 512 entries in the "PTE" level.
  *
@@ -62,15 +63,15 @@
  *
  *    pgd             pte
  * |        |
- * +--------+ +0
- * |        |-----> +------------+ +0
+ * +--------+
+ * |        |       +------------+ +0
+ * +- - - - +       | Linux pt 0 |
+ * |        |       +------------+ +1024
+ * +--------+ +0    | Linux pt 1 |
+ * |        |-----> +------------+ +2048
  * +- - - - + +4    |  h/w pt 0  |
- * |        |-----> +------------+ +1024
+ * |        |-----> +------------+ +3072
  * +--------+ +8    |  h/w pt 1  |
- * |        |       +------------+ +2048
- * +- - - - +       | Linux pt 0 |
- * |        |       +------------+ +3072
- * +--------+       | Linux pt 1 |
  * |        |       +------------+ +4096
  *
  * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
@@ -102,6 +103,10 @@
 #define PTRS_PER_PMD		1
 #define PTRS_PER_PGD		2048
 
+#define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
+#define PTE_HWTABLE_OFF		(PTE_HWTABLE_PTRS * sizeof(pte_t))
+#define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u32))
+
 /*
  * PMD_SHIFT determines the size of the area a second-level page table can map
  * PGDIR_SHIFT determines what a third-level page table entry can map
@@ -112,13 +117,13 @@
 #define LIBRARY_TEXT_START	0x0c000000
 
 #ifndef __ASSEMBLY__
-extern void __pte_error(const char *file, int line, unsigned long val);
-extern void __pmd_error(const char *file, int line, unsigned long val);
-extern void __pgd_error(const char *file, int line, unsigned long val);
+extern void __pte_error(const char *file, int line, pte_t);
+extern void __pmd_error(const char *file, int line, pmd_t);
+extern void __pgd_error(const char *file, int line, pgd_t);
 
-#define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
-#define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd_val(pmd))
-#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
+#define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte)
+#define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd)
+#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd)
 #endif /* !__ASSEMBLY__ */
 
 #define PMD_SIZE		(1UL << PMD_SHIFT)
@@ -133,8 +138,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
  */
 #define FIRST_USER_ADDRESS	PAGE_SIZE
 
-#define FIRST_USER_PGD_NR	1
-#define USER_PTRS_PER_PGD	((TASK_SIZE/PGDIR_SIZE) - FIRST_USER_PGD_NR)
+#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
 
 /*
  * section address mask and size definitions.
@@ -161,30 +165,30 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
  * The PTE table pointer refers to the hardware entries; the "Linux"
  * entries are stored 1024 bytes below.
  */
-#define L_PTE_PRESENT		(1 << 0)
-#define L_PTE_YOUNG		(1 << 1)
-#define L_PTE_FILE		(1 << 2)	/* only when !PRESENT */
-#define L_PTE_DIRTY		(1 << 6)
-#define L_PTE_WRITE		(1 << 7)
-#define L_PTE_USER		(1 << 8)
-#define L_PTE_EXEC		(1 << 9)
-#define L_PTE_SHARED		(1 << 10)	/* shared(v6), coherent(xsc3) */
+#define L_PTE_PRESENT		(_AT(pteval_t, 1) << 0)
+#define L_PTE_YOUNG		(_AT(pteval_t, 1) << 1)
+#define L_PTE_FILE		(_AT(pteval_t, 1) << 2)	/* only when !PRESENT */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 6)
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)
+#define L_PTE_USER		(_AT(pteval_t, 1) << 8)
+#define L_PTE_XN		(_AT(pteval_t, 1) << 9)
+#define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
 
 /*
  * These are the memory types, defined to be compatible with
  * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
  */
-#define L_PTE_MT_UNCACHED	(0x00 << 2)	/* 0000 */
-#define L_PTE_MT_BUFFERABLE	(0x01 << 2)	/* 0001 */
-#define L_PTE_MT_WRITETHROUGH	(0x02 << 2)	/* 0010 */
-#define L_PTE_MT_WRITEBACK	(0x03 << 2)	/* 0011 */
-#define L_PTE_MT_MINICACHE	(0x06 << 2)	/* 0110 (sa1100, xscale) */
-#define L_PTE_MT_WRITEALLOC	(0x07 << 2)	/* 0111 */
-#define L_PTE_MT_DEV_SHARED	(0x04 << 2)	/* 0100 */
-#define L_PTE_MT_DEV_NONSHARED	(0x0c << 2)	/* 1100 */
-#define L_PTE_MT_DEV_WC		(0x09 << 2)	/* 1001 */
-#define L_PTE_MT_DEV_CACHED	(0x0b << 2)	/* 1011 */
-#define L_PTE_MT_MASK		(0x0f << 2)
+#define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
+#define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
+#define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 0x02) << 2)	/* 0010 */
+#define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 0x03) << 2)	/* 0011 */
+#define L_PTE_MT_MINICACHE	(_AT(pteval_t, 0x06) << 2)	/* 0110 (sa1100, xscale) */
+#define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 0x07) << 2)	/* 0111 */
+#define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 0x04) << 2)	/* 0100 */
+#define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
+#define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
+#define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
+#define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
 
 #ifndef __ASSEMBLY__
 
@@ -201,23 +205,44 @@ extern pgprot_t		pgprot_kernel;
 
 #define _MOD_PROT(p, b)	__pgprot(pgprot_val(p) | (b))
 
-#define PAGE_NONE		pgprot_user
-#define PAGE_SHARED		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_WRITE)
-#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_WRITE | L_PTE_EXEC)
-#define PAGE_COPY		_MOD_PROT(pgprot_user, L_PTE_USER)
-#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_EXEC)
-#define PAGE_READONLY		_MOD_PROT(pgprot_user, L_PTE_USER)
-#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_EXEC)
-#define PAGE_KERNEL		pgprot_kernel
-#define PAGE_KERNEL_EXEC	_MOD_PROT(pgprot_kernel, L_PTE_EXEC)
-
-#define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT)
-#define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_WRITE)
-#define __PAGE_SHARED_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_WRITE | L_PTE_EXEC)
-#define __PAGE_COPY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER)
-#define __PAGE_COPY_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_EXEC)
-#define __PAGE_READONLY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER)
-#define __PAGE_READONLY_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_EXEC)
+#define PAGE_NONE		_MOD_PROT(pgprot_user, L_PTE_XN | L_PTE_RDONLY)
+#define PAGE_SHARED		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_XN)
+#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER)
+#define PAGE_COPY		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
+#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
+#define PAGE_READONLY		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
+#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
+#define PAGE_KERNEL		_MOD_PROT(pgprot_kernel, L_PTE_XN)
+#define PAGE_KERNEL_EXEC	pgprot_kernel
+
+#define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN)
+#define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
+#define __PAGE_SHARED_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER)
+#define __PAGE_COPY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
+#define __PAGE_COPY_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY)
+#define __PAGE_READONLY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY | L_PTE_XN)
+#define __PAGE_READONLY_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_RDONLY)
+
+#define __pgprot_modify(prot,mask,bits)		\
+	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+
+#define pgprot_noncached(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
+
+#define pgprot_writecombine(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE)
+
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+#define pgprot_dmacoherent(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE | L_PTE_XN)
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+#else
+#define pgprot_dmacoherent(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED | L_PTE_XN)
+#endif
 
 #endif /* __ASSEMBLY__ */
 
@@ -255,26 +280,84 @@ extern pgprot_t		pgprot_kernel;
 extern struct page *empty_zero_page;
 #define ZERO_PAGE(vaddr)	(empty_zero_page)
 
-#define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
-#define pfn_pte(pfn,prot)	(__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)))
 
-#define pte_none(pte)		(!pte_val(pte))
-#define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
-#define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))
-#define pte_offset_kernel(dir,addr)	(pmd_page_vaddr(*(dir)) + __pte_index(addr))
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+
+/* to find an entry in a page-table-directory */
+#define pgd_index(addr)		((addr) >> PGDIR_SHIFT)
+
+#define pgd_offset(mm, addr)	((mm)->pgd + pgd_index(addr))
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
+
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pgd is never bad, and a pmd always exists (as it's folded
+ * into the pgd entry)
+ */
+#define pgd_none(pgd)		(0)
+#define pgd_bad(pgd)		(0)
+#define pgd_present(pgd)	(1)
+#define pgd_clear(pgdp)		do { } while (0)
+#define set_pgd(pgd,pgdp)	do { } while (0)
+
+
+/* Find an entry in the second-level page table.. */
+#define pmd_offset(dir, addr)	((pmd_t *)(dir))
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define pmd_present(pmd)	(pmd_val(pmd))
+#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
+
+#define copy_pmd(pmdpd,pmdps)		\
+	do {				\
+		pmdpd[0] = pmdps[0];	\
+		pmdpd[1] = pmdps[1];	\
+		flush_pmd_entry(pmdpd);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		pmdp[0] = __pmd(0);	\
+		pmdp[1] = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+static inline pte_t *pmd_page_vaddr(pmd_t pmd)
+{
+	return __va(pmd_val(pmd) & PAGE_MASK);
+}
+
+#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd)))
+
+/* we don't need complex calculations here as the pmd is folded into the pgd */
+#define pmd_addr_end(addr,end)	(end)
 
-#define pte_offset_map(dir,addr)	(__pte_map(dir) + __pte_index(addr))
-#define pte_unmap(pte)			__pte_unmap(pte)
 
 #ifndef CONFIG_HIGHPTE
-#define __pte_map(dir)		pmd_page_vaddr(*(dir))
+#define __pte_map(pmd)		pmd_page_vaddr(*(pmd))
 #define __pte_unmap(pte)	do { } while (0)
 #else
-#define __pte_map(dir)		((pte_t *)kmap_atomic(pmd_page(*(dir))) + PTRS_PER_PTE)
-#define __pte_unmap(pte)	kunmap_atomic((pte - PTRS_PER_PTE))
+#define __pte_map(pmd)		(pte_t *)kmap_atomic(pmd_page(*(pmd)))
+#define __pte_unmap(pte)	kunmap_atomic(pte)
 #endif
 
+#define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+
+#define pte_offset_kernel(pmd,addr)	(pmd_page_vaddr(*(pmd)) + pte_index(addr))
+
+#define pte_offset_map(pmd,addr)	(__pte_map(pmd) + pte_index(addr))
+#define pte_unmap(pte)			__pte_unmap(pte)
+
+#define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
+#define pfn_pte(pfn,prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
+
+#define pte_page(pte)		pfn_to_page(pte_pfn(pte))
+#define mk_pte(page,prot)	pfn_pte(page_to_pfn(page), prot)
+
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+#define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
 #if __LINUX_ARM_ARCH__ < 6
 static inline void __sync_icache_dcache(pte_t pteval)
@@ -295,15 +378,12 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	}
 }
 
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
+#define pte_none(pte)		(!pte_val(pte))
 #define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
-#define pte_write(pte)		(pte_val(pte) & L_PTE_WRITE)
+#define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
 #define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
 #define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
-#define pte_exec(pte)		(pte_val(pte) & L_PTE_EXEC)
+#define pte_exec(pte)		(!(pte_val(pte) & L_PTE_XN))
 #define pte_special(pte)	(0)
 
 #define pte_present_user(pte) \
@@ -313,8 +393,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
 
-PTE_BIT_FUNC(wrprotect, &= ~L_PTE_WRITE);
-PTE_BIT_FUNC(mkwrite,   |= L_PTE_WRITE);
+PTE_BIT_FUNC(wrprotect, |= L_PTE_RDONLY);
+PTE_BIT_FUNC(mkwrite,   &= ~L_PTE_RDONLY);
 PTE_BIT_FUNC(mkclean,   &= ~L_PTE_DIRTY);
 PTE_BIT_FUNC(mkdirty,   |= L_PTE_DIRTY);
 PTE_BIT_FUNC(mkold,     &= ~L_PTE_YOUNG);
@@ -322,101 +402,13 @@ PTE_BIT_FUNC(mkyoung,   |= L_PTE_YOUNG);
 
 static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 
-#define __pgprot_modify(prot,mask,bits)		\
-	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
-
-/*
- * Mark the prot value as uncacheable and unbufferable.
- */
-#define pgprot_noncached(prot) \
-	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
-#define pgprot_writecombine(prot) \
-	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE)
-#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
-#define pgprot_dmacoherent(prot) \
-	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE)
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-struct file;
-extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-				     unsigned long size, pgprot_t vma_prot);
-#else
-#define pgprot_dmacoherent(prot) \
-	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED)
-#endif
-
-#define pmd_none(pmd)		(!pmd_val(pmd))
-#define pmd_present(pmd)	(pmd_val(pmd))
-#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
-
-#define copy_pmd(pmdpd,pmdps)		\
-	do {				\
-		pmdpd[0] = pmdps[0];	\
-		pmdpd[1] = pmdps[1];	\
-		flush_pmd_entry(pmdpd);	\
-	} while (0)
-
-#define pmd_clear(pmdp)			\
-	do {				\
-		pmdp[0] = __pmd(0);	\
-		pmdp[1] = __pmd(0);	\
-		clean_pmd_entry(pmdp);	\
-	} while (0)
-
-static inline pte_t *pmd_page_vaddr(pmd_t pmd)
-{
-	unsigned long ptr;
-
-	ptr = pmd_val(pmd) & ~(PTRS_PER_PTE * sizeof(void *) - 1);
-	ptr += PTRS_PER_PTE * sizeof(void *);
-
-	return __va(ptr);
-}
-
-#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd)))
-
-/* we don't need complex calculations here as the pmd is folded into the pgd */
-#define pmd_addr_end(addr,end)	(end)
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page,prot)	pfn_pte(page_to_pfn(page),prot)
-
-/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
- * setup: the pgd is never bad, and a pmd always exists (as it's folded
- * into the pgd entry)
- */
-#define pgd_none(pgd)		(0)
-#define pgd_bad(pgd)		(0)
-#define pgd_present(pgd)	(1)
-#define pgd_clear(pgdp)		do { } while (0)
-#define set_pgd(pgd,pgdp)	do { } while (0)
-
-/* to find an entry in a page-table-directory */
-#define pgd_index(addr)		((addr) >> PGDIR_SHIFT)
-
-#define pgd_offset(mm, addr)	((mm)->pgd+pgd_index(addr))
-
-/* to find an entry in a kernel page-table-directory */
-#define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(dir, addr)	((pmd_t *)(dir))
-
-/* Find an entry in the third-level page table.. */
-#define __pte_index(addr)	(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	const unsigned long mask = L_PTE_EXEC | L_PTE_WRITE | L_PTE_USER;
+	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }
 
-extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-
 /*
  * Encode and decode a swap entry.  Swap entries are stored in the Linux
  * page tables as follows:
@@ -481,6 +473,9 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 #define pgtable_cache_init() do { } while (0)
 
+void identity_mapping_add(pgd_t *, unsigned long, unsigned long);
+void identity_mapping_del(pgd_t *, unsigned long, unsigned long);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* CONFIG_MMU */
diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
new file mode 100644
index 00000000000..a84628be1a7
--- /dev/null
+++ b/arch/arm/include/asm/sched_clock.h
@@ -0,0 +1,118 @@
+/*
+ * sched_clock.h: support for extending counters to full 64-bit ns counter
+ *
+ * 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_SCHED_CLOCK
+#define ASM_SCHED_CLOCK
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+struct clock_data {
+	u64 epoch_ns;
+	u32 epoch_cyc;
+	u32 epoch_cyc_copy;
+	u32 mult;
+	u32 shift;
+};
+
+#define DEFINE_CLOCK_DATA(name)	struct clock_data name
+
+static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+{
+	return (cyc * mult) >> shift;
+}
+
+/*
+ * Atomically update the sched_clock epoch.  Your update callback will
+ * be called from a timer before the counter wraps - read the current
+ * counter value, and call this function to safely move the epochs
+ * forward.  Only use this from the update callback.
+ */
+static inline void update_sched_clock(struct clock_data *cd, u32 cyc, u32 mask)
+{
+	unsigned long flags;
+	u64 ns = cd->epoch_ns +
+		cyc_to_ns((cyc - cd->epoch_cyc) & mask, cd->mult, cd->shift);
+
+	/*
+	 * Write epoch_cyc and epoch_ns in a way that the update is
+	 * detectable in cyc_to_fixed_sched_clock().
+	 */
+	raw_local_irq_save(flags);
+	cd->epoch_cyc = cyc;
+	smp_wmb();
+	cd->epoch_ns = ns;
+	smp_wmb();
+	cd->epoch_cyc_copy = cyc;
+	raw_local_irq_restore(flags);
+}
+
+/*
+ * If your clock rate is known at compile time, using this will allow
+ * you to optimize the mult/shift loads away.  This is paired with
+ * init_fixed_sched_clock() to ensure that your mult/shift are correct.
+ */
+static inline unsigned long long cyc_to_fixed_sched_clock(struct clock_data *cd,
+	u32 cyc, u32 mask, u32 mult, u32 shift)
+{
+	u64 epoch_ns;
+	u32 epoch_cyc;
+
+	/*
+	 * Load the epoch_cyc and epoch_ns atomically.  We do this by
+	 * ensuring that we always write epoch_cyc, epoch_ns and
+	 * epoch_cyc_copy in strict order, and read them in strict order.
+	 * If epoch_cyc and epoch_cyc_copy are not equal, then we're in
+	 * the middle of an update, and we should repeat the load.
+	 */
+	do {
+		epoch_cyc = cd->epoch_cyc;
+		smp_rmb();
+		epoch_ns = cd->epoch_ns;
+		smp_rmb();
+	} while (epoch_cyc != cd->epoch_cyc_copy);
+
+	return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, mult, shift);
+}
+
+/*
+ * Otherwise, you need to use this, which will obtain the mult/shift
+ * from the clock_data structure.  Use init_sched_clock() with this.
+ */
+static inline unsigned long long cyc_to_sched_clock(struct clock_data *cd,
+	u32 cyc, u32 mask)
+{
+	return cyc_to_fixed_sched_clock(cd, cyc, mask, cd->mult, cd->shift);
+}
+
+/*
+ * Initialize the clock data - calculate the appropriate multiplier
+ * and shift.  Also setup a timer to ensure that the epoch is refreshed
+ * at the appropriate time interval, which will call your update
+ * handler.
+ */
+void init_sched_clock(struct clock_data *, void (*)(void),
+	unsigned int, unsigned long);
+
+/*
+ * Use this initialization function rather than init_sched_clock() if
+ * you're using cyc_to_fixed_sched_clock, which will warn if your
+ * constants are incorrect.
+ */
+static inline void init_fixed_sched_clock(struct clock_data *cd,
+	void (*update)(void), unsigned int bits, unsigned long rate,
+	u32 mult, u32 shift)
+{
+	init_sched_clock(cd, update, bits, rate);
+	if (cd->mult != mult || cd->shift != shift) {
+		pr_crit("sched_clock: wrong multiply/shift: %u>>%u vs calculated %u>>%u\n"
+			"sched_clock: fix multiply/shift to avoid scheduler hiccups\n",
+			mult, shift, cd->mult, cd->shift);
+	}
+}
+
+#endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 3d05190797c..96ed521f240 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -33,27 +33,23 @@ struct seq_file;
 /*
  * generate IPI list text
  */
-extern void show_ipi_list(struct seq_file *p);
+extern void show_ipi_list(struct seq_file *, int);
 
 /*
  * Called from assembly code, this handles an IPI.
  */
-asmlinkage void do_IPI(struct pt_regs *regs);
+asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
 
 /*
  * Setup the set of possible CPUs (via set_cpu_possible)
  */
 extern void smp_init_cpus(void);
 
-/*
- * Move global data into per-processor storage.
- */
-extern void smp_store_cpu_info(unsigned int cpuid);
 
 /*
  * Raise an IPI cross call on CPUs in callmap.
  */
-extern void smp_cross_call(const struct cpumask *mask);
+extern void smp_cross_call(const struct cpumask *mask, int ipi);
 
 /*
  * Boot a secondary CPU, and assign it the specified idle task.
@@ -73,6 +69,11 @@ asmlinkage void secondary_start_kernel(void);
 extern void platform_secondary_init(unsigned int cpu);
 
 /*
+ * Initialize cpu_possible map, and enable coherency
+ */
+extern void platform_smp_prepare_cpus(unsigned int);
+
+/*
  * Initial data for bringing up a secondary CPU.
  */
 struct secondary_data {
@@ -97,6 +98,6 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 /*
  * show local interrupt info
  */
-extern void show_local_irqs(struct seq_file *);
+extern void show_local_irqs(struct seq_file *, int);
 
 #endif /* ifndef __ASM_ARM_SMP_H */
diff --git a/arch/arm/include/asm/smp_mpidr.h b/arch/arm/include/asm/smp_mpidr.h
deleted file mode 100644
index 6a9307d6490..00000000000
--- a/arch/arm/include/asm/smp_mpidr.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef ASMARM_SMP_MIDR_H
-#define ASMARM_SMP_MIDR_H
-
-#define hard_smp_processor_id()						\
-	({								\
-		unsigned int cpunum;					\
-		__asm__("\n"						\
-			"1:	mrc p15, 0, %0, c0, c0, 5\n"		\
-			"	.pushsection \".alt.smp.init\", \"a\"\n"\
-			"	.long	1b\n"				\
-			"	mov	%0, #0\n"			\
-			"	.popsection"				\
-			: "=r" (cpunum));				\
-		cpunum &= 0x0F;						\
-	})
-
-#endif
diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h
index 634f357be6b..fed9981fba0 100644
--- a/arch/arm/include/asm/smp_twd.h
+++ b/arch/arm/include/asm/smp_twd.h
@@ -22,7 +22,6 @@ struct clock_event_device;
 
 extern void __iomem *twd_base;
 
-void twd_timer_stop(void);
 int twd_timer_ack(void);
 void twd_timer_setup(struct clock_event_device *);
 
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 80025948b8a..97f6d60297d 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -63,6 +63,11 @@
 #include <asm/outercache.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
 
 struct thread_info;
 struct task_struct;
@@ -119,6 +124,13 @@ extern unsigned int user_debug;
 #define vectors_high()	(0)
 #endif
 
+#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() __asm__ __volatile__ ("isb" : : : "memory")
 #define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index 491960bf426..1b960d5ef6a 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -15,16 +15,37 @@ struct undef_hook {
 void register_undef_hook(struct undef_hook *hook);
 void unregister_undef_hook(struct undef_hook *hook);
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	extern char __irqentry_text_start[];
+	extern char __irqentry_text_end[];
+
+	return ptr >= (unsigned long)&__irqentry_text_start &&
+	       ptr < (unsigned long)&__irqentry_text_end;
+}
+#else
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	return 0;
+}
+#endif
+
 static inline int in_exception_text(unsigned long ptr)
 {
 	extern char __exception_text_start[];
 	extern char __exception_text_end[];
+	int in;
 
-	return ptr >= (unsigned long)&__exception_text_start &&
-	       ptr < (unsigned long)&__exception_text_end;
+	in = ptr >= (unsigned long)&__exception_text_start &&
+	     ptr < (unsigned long)&__exception_text_end;
+
+	return in ? : __in_irqentry_text(ptr);
 }
 
 extern void __init early_trap_init(void);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
 
+extern void *vectors_page;
+
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 33e4a48fe10..b293616a1a1 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -227,7 +227,7 @@ do {									\
 
 #define __get_user_asm_byte(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrbt	%1,[%2]\n"				\
+	"1:	" T(ldrb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -263,7 +263,7 @@ do {									\
 
 #define __get_user_asm_word(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrt	%1,[%2]\n"				\
+	"1:	" T(ldr) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -308,7 +308,7 @@ do {									\
 
 #define __put_user_asm_byte(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strbt	%1,[%2]\n"				\
+	"1:	" T(strb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -341,7 +341,7 @@ do {									\
 
 #define __put_user_asm_word(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strt	%1,[%2]\n"				\
+	"1:	" T(str) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -366,10 +366,10 @@ do {									\
 
 #define __put_user_asm_dword(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
- ARM(	"1:	strt	" __reg_oper1 ", [%1], #4\n"	)	\
- ARM(	"2:	strt	" __reg_oper0 ", [%1]\n"	)	\
- THUMB(	"1:	strt	" __reg_oper1 ", [%1]\n"	)	\
- THUMB(	"2:	strt	" __reg_oper0 ", [%1, #4]\n"	)	\
+ ARM(	"1:	" T(str) "	" __reg_oper1 ", [%1], #4\n"	)	\
+ ARM(	"2:	" T(str) "	" __reg_oper0 ", [%1]\n"	)	\
+ THUMB(	"1:	" T(str) "	" __reg_oper1 ", [%1]\n"	)	\
+ THUMB(	"2:	" T(str) "	" __reg_oper0 ", [%1, #4]\n"	)	\
 	"3:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\