Merge branch 'linus' into stackprotector

Conflicts:
	arch/x86/kernel/Makefile
	include/asm-x86/pda.h

40 files changed, 778 insertions, 686 deletions

diff --git a/arch/arm/kernel/.gitignore b/arch/arm/kernel/.gitignore
new file mode 100644
index 00000000000..c5f676c3c22
--- /dev/null
+++ b/arch/arm/kernel/.gitignore
@@ -0,0 +1 @@
+vmlinux.lds
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index ad455ff5aeb..4305345987d 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -4,9 +4,13 @@
 
 AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET)
 
+ifdef CONFIG_DYNAMIC_FTRACE
+CFLAGS_REMOVE_ftrace.o = -pg
+endif
+
 # Object file lists.
 
-obj-y		:= compat.o entry-armv.o entry-common.o irq.o \
+obj-y		:= compat.o elf.o entry-armv.o entry-common.o irq.o \
 		   process.o ptrace.o setup.o signal.o \
 		   sys_arm.o stacktrace.o time.o traps.o
 
@@ -18,11 +22,13 @@ obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
 obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-decode.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags.o
 obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o
+obj-$(CONFIG_KGDB)		+= kgdb.o
 
 obj-$(CONFIG_CRUNCH)		+= crunch.o crunch-bits.o
 AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 688b7b1ee41..2357b1cf1cf 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -13,11 +13,12 @@
 #include <linux/delay.h>
 #include <linux/in6.h>
 #include <linux/syscalls.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
 
 #include <asm/checksum.h>
-#include <asm/io.h>
 #include <asm/system.h>
-#include <asm/uaccess.h>
+#include <asm/ftrace.h>
 
 /*
  * libgcc functions - functions that are used internally by the
@@ -181,3 +182,7 @@ EXPORT_SYMBOL(_find_next_bit_be);
 #endif
 
 EXPORT_SYMBOL(copy_page);
+
+#ifdef CONFIG_FTRACE
+EXPORT_SYMBOL(mcount);
+#endif
diff --git a/arch/arm/kernel/atags.c b/arch/arm/kernel/atags.c
index 64c420805e6..42a1a1415fa 100644
--- a/arch/arm/kernel/atags.c
+++ b/arch/arm/kernel/atags.c
@@ -1,5 +1,4 @@
 #include <linux/slab.h>
-#include <linux/kexec.h>
 #include <linux/proc_fs.h>
 #include <asm/setup.h>
 #include <asm/types.h>
@@ -7,9 +6,8 @@
 
 struct buffer {
 	size_t size;
-	char *data;
+	char data[];
 };
-static struct buffer tags_buffer;
 
 static int
 read_buffer(char* page, char** start, off_t off, int count,
@@ -29,58 +27,57 @@ read_buffer(char* page, char** start, off_t off, int count,
 	return count;
 }
 
-
-static int
-create_proc_entries(void)
-{
-	struct proc_dir_entry* tags_entry;
-
-	tags_entry = create_proc_read_entry("atags", 0400, NULL, read_buffer, &tags_buffer);
-	if (!tags_entry)
-		return -ENOMEM;
-
-	return 0;
-}
-
-
-static char __initdata atags_copy_buf[KEXEC_BOOT_PARAMS_SIZE];
-static char __initdata *atags_copy;
+#define BOOT_PARAMS_SIZE 1536
+static char __initdata atags_copy[BOOT_PARAMS_SIZE];
 
 void __init save_atags(const struct tag *tags)
 {
-	atags_copy = atags_copy_buf;
-	memcpy(atags_copy, tags, KEXEC_BOOT_PARAMS_SIZE);
+	memcpy(atags_copy, tags, sizeof(atags_copy));
 }
 
-
 static int __init init_atags_procfs(void)
 {
-	struct tag *tag;
-	int error;
+	/*
+	 * This cannot go into save_atags() because kmalloc and proc don't work
+	 * yet when it is called.
+	 */
+	struct proc_dir_entry *tags_entry;
+	struct tag *tag = (struct tag *)atags_copy;
+	struct buffer *b;
+	size_t size;
 
-	if (!atags_copy) {
-		printk(KERN_WARNING "Exporting ATAGs: No saved tags found\n");
-		return -EIO;
+	if (tag->hdr.tag != ATAG_CORE) {
+		printk(KERN_INFO "No ATAGs?");
+		return -EINVAL;
 	}
 
-	for (tag = (struct tag *) atags_copy; tag->hdr.size; tag = tag_next(tag))
+	for (; tag->hdr.size; tag = tag_next(tag))
 		;
 
-	tags_buffer.size = ((char *) tag - atags_copy) + sizeof(tag->hdr);
-	tags_buffer.data = kmalloc(tags_buffer.size, GFP_KERNEL);
-	if (tags_buffer.data == NULL)
-		return -ENOMEM;
-	memcpy(tags_buffer.data, atags_copy, tags_buffer.size);
-
-	error = create_proc_entries();
-	if (error) {
-		printk(KERN_ERR "Exporting ATAGs: not enough memory\n");
-		kfree(tags_buffer.data);
-		tags_buffer.size = 0;
-		tags_buffer.data = NULL;
-	}
+	/* include the terminating ATAG_NONE */
+	size = (char *)tag - atags_copy + sizeof(struct tag_header);
 
-	return error;
-}
+	WARN_ON(tag->hdr.tag != ATAG_NONE);
+
+	b = kmalloc(sizeof(*b) + size, GFP_KERNEL);
+	if (!b)
+		goto nomem;
 
+	b->size = size;
+	memcpy(b->data, atags_copy, size);
+
+	tags_entry = create_proc_read_entry("atags", 0400,
+			NULL, read_buffer, b);
+
+	if (!tags_entry)
+		goto nomem;
+
+	return 0;
+
+nomem:
+	kfree(b);
+	printk(KERN_ERR "Exporting ATAGs: not enough memory\n");
+
+	return -ENOMEM;
+}
 arch_initcall(init_atags_procfs);
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index e5747547b44..17a59b6e521 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -10,8 +10,8 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/init.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/mach-types.h>
 #include <asm/mach/pci.h>
 
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 30a67a5a40a..09a061cb783 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -262,10 +262,10 @@
 /* 250 */	CALL(sys_epoll_create)
 		CALL(ABI(sys_epoll_ctl, sys_oabi_epoll_ctl))
 		CALL(ABI(sys_epoll_wait, sys_oabi_epoll_wait))
-	 	CALL(sys_remap_file_pages)
+		CALL(sys_remap_file_pages)
 		CALL(sys_ni_syscall)	/* sys_set_thread_area */
 /* 255 */	CALL(sys_ni_syscall)	/* sys_get_thread_area */
- 		CALL(sys_set_tid_address)
+		CALL(sys_set_tid_address)
 		CALL(sys_timer_create)
 		CALL(sys_timer_settime)
 		CALL(sys_timer_gettime)
@@ -364,6 +364,12 @@
 		CALL(sys_fallocate)
 		CALL(sys_timerfd_settime)
 		CALL(sys_timerfd_gettime)
+/* 355 */	CALL(sys_signalfd4)
+		CALL(sys_eventfd2)
+		CALL(sys_epoll_create1)
+		CALL(sys_dup3)
+		CALL(sys_pipe2)
+/* 360 */	CALL(sys_inotify_init1)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/crunch-bits.S b/arch/arm/kernel/crunch-bits.S
index a26886758c6..0ec9bb48fab 100644
--- a/arch/arm/kernel/crunch-bits.S
+++ b/arch/arm/kernel/crunch-bits.S
@@ -16,7 +16,7 @@
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm/arch/ep93xx-regs.h>
+#include <mach/ep93xx-regs.h>
 
 /*
  * We can't use hex constants here due to a bug in gas.
diff --git a/arch/arm/kernel/crunch.c b/arch/arm/kernel/crunch.c
index 627d79414c9..99995c2b231 100644
--- a/arch/arm/kernel/crunch.c
+++ b/arch/arm/kernel/crunch.c
@@ -15,9 +15,9 @@
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/init.h>
-#include <asm/arch/ep93xx-regs.h>
+#include <linux/io.h>
+#include <mach/ep93xx-regs.h>
 #include <asm/thread_notify.h>
-#include <asm/io.h>
 
 struct crunch_state *crunch_owner;
 
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 5617566477b..f53c5829054 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -80,7 +80,7 @@
 #endif	/* CONFIG_CPU_V6 */
 
 #else
-#include <asm/arch/debug-macro.S>
+#include <mach/debug-macro.S>
 #endif	/* CONFIG_DEBUG_ICEDCC */
 
 /*
@@ -89,10 +89,12 @@
 ENTRY(printhex8)
 		mov	r1, #8
 		b	printhex
+ENDPROC(printhex8)
 
 ENTRY(printhex4)
 		mov	r1, #4
 		b	printhex
+ENDPROC(printhex4)
 
 ENTRY(printhex2)
 		mov	r1, #2
@@ -110,6 +112,7 @@ printhex:	adr	r2, hexbuf
 		bne	1b
 		mov	r0, r2
 		b	printascii
+ENDPROC(printhex2)
 
 		.ltorg
 
@@ -127,11 +130,13 @@ ENTRY(printascii)
 		teqne	r1, #0
 		bne	1b
 		mov	pc, lr
+ENDPROC(printascii)
 
 ENTRY(printch)
 		addruart r3
 		mov	r1, r0
 		mov	r0, #0
 		b	1b
+ENDPROC(printch)
 
 hexbuf:		.space 16
diff --git a/arch/arm/kernel/dma-isa.c b/arch/arm/kernel/dma-isa.c
index 2f080a35a2d..4a3a50495c6 100644
--- a/arch/arm/kernel/dma-isa.c
+++ b/arch/arm/kernel/dma-isa.c
@@ -19,10 +19,9 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
+#include <linux/io.h>
 
 #include <asm/dma.h>
-#include <asm/io.h>
-
 #include <asm/mach/dma.h>
 
 #define ISA_DMA_MODE_READ	0x44
diff --git a/arch/arm/kernel/dma.c b/arch/arm/kernel/dma.c
index ba99a203552..d006085ed7e 100644
--- a/arch/arm/kernel/dma.c
+++ b/arch/arm/kernel/dma.c
@@ -26,23 +26,6 @@ EXPORT_SYMBOL(dma_spin_lock);
 static dma_t dma_chan[MAX_DMA_CHANNELS];
 
 /*
- * Get dma list for /proc/dma
- */
-int get_dma_list(char *buf)
-{
-	dma_t *dma;
-	char *p = buf;
-	int i;
-
-	for (i = 0, dma = dma_chan; i < MAX_DMA_CHANNELS; i++, dma++)
-		if (dma->lock)
-			p += sprintf(p, "%2d: %14s %s\n", i,
-				     dma->d_ops->type, dma->device_id);
-
-	return p - buf;
-}
-
-/*
  * Request DMA channel
  *
  * On certain platforms, we have to allocate an interrupt as well...
diff --git a/arch/arm/kernel/ecard.c b/arch/arm/kernel/ecard.c
index a53c0aba5c1..60c079d8535 100644
--- a/arch/arm/kernel/ecard.c
+++ b/arch/arm/kernel/ecard.c
@@ -46,7 +46,7 @@
 
 #include <asm/dma.h>
 #include <asm/ecard.h>
-#include <asm/hardware.h>
+#include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/mach/irq.h>
@@ -587,8 +587,7 @@ ecard_irq_handler(unsigned int irq, struct irq_desc *desc)
 			pending = ecard_default_ops.irqpending(ec);
 
 		if (pending) {
-			struct irq_desc *d = irq_desc + ec->irq;
-			desc_handle_irq(ec->irq, d);
+			generic_handle_irq(ec->irq);
 			called ++;
 		}
 	}
@@ -622,7 +621,6 @@ ecard_irqexp_handler(unsigned int irq, struct irq_desc *desc)
 		ecard_t *ec = slot_to_ecard(slot);
 
 		if (ec->claimed) {
-			struct irq_desc *d = irq_desc + ec->irq;
 			/*
 			 * this ugly code is so that we can operate a
 			 * prioritorising system:
@@ -635,7 +633,7 @@ ecard_irqexp_handler(unsigned int irq, struct irq_desc *desc)
 			 * Serial cards should go in 0/1, ethernet/scsi in 2/3
 			 * otherwise you will lose serial data at high speeds!
 			 */
-			desc_handle_irq(ec->irq, d);
+			generic_handle_irq(ec->irq);
 		} else {
 			printk(KERN_WARNING "card%d: interrupt from unclaimed "
 			       "card???\n", slot);
@@ -680,7 +678,7 @@ static int __init ecard_probeirqhw(void)
 #define IO_EC_MEMC8_BASE 0
 #endif
 
-unsigned int __ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed)
+static unsigned int __ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed)
 {
 	unsigned long address = 0;
 	int slot = ec->slot_no;
@@ -783,7 +781,7 @@ static void ecard_proc_init(void)
 
 #define ec_set_resource(ec,nr,st,sz)				\
 	do {							\
-		(ec)->resource[nr].name = ec->dev.bus_id;	\
+		(ec)->resource[nr].name = dev_name(&ec->dev);	\
 		(ec)->resource[nr].start = st;			\
 		(ec)->resource[nr].end = (st) + (sz) - 1;	\
 		(ec)->resource[nr].flags = IORESOURCE_MEM;	\
@@ -853,8 +851,7 @@ static struct expansion_card *__init ecard_alloc_card(int type, int slot)
 	for (i = 0; i < ECARD_NUM_RESOURCES; i++) {
 		if (ec->resource[i].flags &&
 		    request_resource(&iomem_resource, &ec->resource[i])) {
-			printk(KERN_ERR "%s: resource(s) not available\n",
-				ec->dev.bus_id);
+			dev_err(&ec->dev, "resource(s) not available\n");
 			ec->resource[i].end -= ec->resource[i].start;
 			ec->resource[i].start = 0;
 			ec->resource[i].flags = 0;
@@ -1002,7 +999,7 @@ ecard_probe(int slot, card_type_t type)
 	}
 
 	rc = -ENODEV;
-	if ((ec->podaddr = ecard_address(ec, type, ECARD_SYNC)) == 0)
+	if ((ec->podaddr = __ecard_address(ec, type, ECARD_SYNC)) == 0)
 		goto nodev;
 
 	cid.r_zero = 1;
@@ -1141,10 +1138,10 @@ static int ecard_drv_probe(struct device *dev)
 
 	id = ecard_match_device(drv->id_table, ec);
 
-	ecard_claim(ec);
+	ec->claimed = 1;
 	ret = drv->probe(ec, id);
 	if (ret)
-		ecard_release(ec);
+		ec->claimed = 0;
 	return ret;
 }
 
@@ -1154,7 +1151,7 @@ static int ecard_drv_remove(struct device *dev)
 	struct ecard_driver *drv = ECARD_DRV(dev->driver);
 
 	drv->remove(ec);
-	ecard_release(ec);
+	ec->claimed = 0;
 
 	/*
 	 * Restore the default operations.  We ensure that the
@@ -1182,7 +1179,7 @@ static void ecard_drv_shutdown(struct device *dev)
 	if (dev->driver) {
 		if (drv->shutdown)
 			drv->shutdown(ec);
-		ecard_release(ec);
+		ec->claimed = 0;
 	}
 
 	/*
@@ -1239,7 +1236,6 @@ static int ecard_bus_init(void)
 postcore_initcall(ecard_bus_init);
 
 EXPORT_SYMBOL(ecard_readchunk);
-EXPORT_SYMBOL(__ecard_address);
 EXPORT_SYMBOL(ecard_register_driver);
 EXPORT_SYMBOL(ecard_remove_driver);
 EXPORT_SYMBOL(ecard_bus_type);
diff --git a/arch/arm/kernel/ecard.h b/arch/arm/kernel/ecard.h
index d7c2dacf935..4642d436be2 100644
--- a/arch/arm/kernel/ecard.h
+++ b/arch/arm/kernel/ecard.h
@@ -54,3 +54,16 @@ struct ex_chunk_dir {
 #define c_len(x)	((x)->r_len[0]|((x)->r_len[1]<<8)|((x)->r_len[2]<<16))
 #define c_start(x)	((x)->r_start)
 };
+
+typedef enum ecard_type {		/* Cards address space		*/
+	ECARD_IOC,
+	ECARD_MEMC,
+	ECARD_EASI
+} card_type_t;
+
+typedef enum {				/* Speed for ECARD_IOC space	*/
+	ECARD_SLOW	 = 0,
+	ECARD_MEDIUM	 = 1,
+	ECARD_FAST	 = 2,
+	ECARD_SYNC	 = 3
+} card_speed_t;
diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c
new file mode 100644
index 00000000000..513f332f040
--- /dev/null
+++ b/arch/arm/kernel/elf.c
@@ -0,0 +1,79 @@
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/personality.h>
+#include <linux/binfmts.h>
+#include <linux/elf.h>
+
+int elf_check_arch(const struct elf32_hdr *x)
+{
+	unsigned int eflags;
+
+	/* Make sure it's an ARM executable */
+	if (x->e_machine != EM_ARM)
+		return 0;
+
+	/* Make sure the entry address is reasonable */
+	if (x->e_entry & 1) {
+		if (!(elf_hwcap & HWCAP_THUMB))
+			return 0;
+	} else if (x->e_entry & 3)
+		return 0;
+
+	eflags = x->e_flags;
+	if ((eflags & EF_ARM_EABI_MASK) == EF_ARM_EABI_UNKNOWN) {
+		/* APCS26 is only allowed if the CPU supports it */
+		if ((eflags & EF_ARM_APCS_26) && !(elf_hwcap & HWCAP_26BIT))
+			return 0;
+
+		/* VFP requires the supporting code */
+		if ((eflags & EF_ARM_VFP_FLOAT) && !(elf_hwcap & HWCAP_VFP))
+			return 0;
+	}
+	return 1;
+}
+EXPORT_SYMBOL(elf_check_arch);
+
+void elf_set_personality(const struct elf32_hdr *x)
+{
+	unsigned int eflags = x->e_flags;
+	unsigned int personality = PER_LINUX_32BIT;
+
+	/*
+	 * APCS-26 is only valid for OABI executables
+	 */
+	if ((eflags & EF_ARM_EABI_MASK) == EF_ARM_EABI_UNKNOWN) {
+		if (eflags & EF_ARM_APCS_26)
+			personality = PER_LINUX;
+	}
+
+	set_personality(personality);
+
+	/*
+	 * Since the FPA coprocessor uses CP1 and CP2, and iWMMXt uses CP0
+	 * and CP1, we only enable access to the iWMMXt coprocessor if the
+	 * binary is EABI or softfloat (and thus, guaranteed not to use
+	 * FPA instructions.)
+	 */
+	if (elf_hwcap & HWCAP_IWMMXT &&
+	    eflags & (EF_ARM_EABI_MASK | EF_ARM_SOFT_FLOAT)) {
+		set_thread_flag(TIF_USING_IWMMXT);
+	} else {
+		clear_thread_flag(TIF_USING_IWMMXT);
+	}
+}
+EXPORT_SYMBOL(elf_set_personality);
+
+/*
+ * Set READ_IMPLIES_EXEC if:
+ *  - the binary requires an executable stack
+ *  - we're running on a CPU which doesn't support NX.
+ */
+int arm_elf_read_implies_exec(const struct elf32_hdr *x, int executable_stack)
+{
+	if (executable_stack != EXSTACK_ENABLE_X)
+		return 1;
+	if (cpu_architecture() <= CPU_ARCH_ARMv6)
+		return 1;
+	return 0;
+}
+EXPORT_SYMBOL(arm_elf_read_implies_exec);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 7dca225752c..77b04747553 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -18,7 +18,7 @@
 #include <asm/memory.h>
 #include <asm/glue.h>
 #include <asm/vfpmacros.h>
-#include <asm/arch/entry-macro.S>
+#include <mach/entry-macro.S>
 #include <asm/thread_notify.h>
 
 #include "entry-header.S"
@@ -76,14 +76,17 @@
 __pabt_invalid:
 	inv_entry BAD_PREFETCH
 	b	common_invalid
+ENDPROC(__pabt_invalid)
 
 __dabt_invalid:
 	inv_entry BAD_DATA
 	b	common_invalid
+ENDPROC(__dabt_invalid)
 
 __irq_invalid:
 	inv_entry BAD_IRQ
 	b	common_invalid
+ENDPROC(__irq_invalid)
 
 __und_invalid:
 	inv_entry BAD_UNDEFINSTR
@@ -107,6 +110,7 @@ common_invalid:
 
 	mov	r0, sp
 	b	bad_mode
+ENDPROC(__und_invalid)
 
 /*
  * SVC mode handlers
@@ -192,6 +196,7 @@ __dabt_svc:
 	ldr	r0, [sp, #S_PSR]
 	msr	spsr_cxsf, r0
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+ENDPROC(__dabt_svc)
 
 	.align	5
 __irq_svc:
@@ -223,6 +228,7 @@ __irq_svc:
 	bleq	trace_hardirqs_on
 #endif
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+ENDPROC(__irq_svc)
 
 	.ltorg
 
@@ -272,6 +278,7 @@ __und_svc:
 	ldr	lr, [sp, #S_PSR]		@ Get SVC cpsr
 	msr	spsr_cxsf, lr
 	ldmia	sp, {r0 - pc}^			@ Restore SVC registers
+ENDPROC(__und_svc)
 
 	.align	5
 __pabt_svc:
@@ -313,6 +320,7 @@ __pabt_svc:
 	ldr	r0, [sp, #S_PSR]
 	msr	spsr_cxsf, r0
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+ENDPROC(__pabt_svc)
 
 	.align	5
 .LCcralign:
@@ -412,6 +420,7 @@ __dabt_usr:
 	mov	r2, sp
 	adr	lr, ret_from_exception
 	b	do_DataAbort
+ENDPROC(__dabt_usr)
 
 	.align	5
 __irq_usr:
@@ -441,6 +450,7 @@ __irq_usr:
 
 	mov	why, #0
 	b	ret_to_user
+ENDPROC(__irq_usr)
 
 	.ltorg
 
@@ -474,6 +484,7 @@ __und_usr:
 #else
 	b	__und_usr_unknown
 #endif
+ENDPROC(__und_usr)
 
 	@
 	@ fallthrough to call_fpe
@@ -642,6 +653,7 @@ __und_usr_unknown:
 	mov	r0, sp
 	adr	lr, ret_from_exception
 	b	do_undefinstr
+ENDPROC(__und_usr_unknown)
 
 	.align	5
 __pabt_usr:
@@ -666,6 +678,8 @@ ENTRY(ret_from_exception)
 	get_thread_info tsk
 	mov	why, #0
 	b	ret_to_user
+ENDPROC(__pabt_usr)
+ENDPROC(ret_from_exception)
 
 /*
  * Register switch for ARMv3 and ARMv4 processors
@@ -702,6 +716,7 @@ ENTRY(__switch_to)
 	bl	atomic_notifier_call_chain
 	mov	r0, r5
 	ldmia	r4, {r4 - sl, fp, sp, pc}	@ Load all regs saved previously
+ENDPROC(__switch_to)
 
 	__INIT
 
@@ -1029,6 +1044,7 @@ vector_\name:
 	mov	r0, sp
 	ldr	lr, [pc, lr, lsl #2]
 	movs	pc, lr			@ branch to handler in SVC mode
+ENDPROC(vector_\name)
 	.endm
 
 	.globl	__stubs_start
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 597ed00a08d..3aa14dcc5ba 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -9,7 +9,8 @@
  */
 
 #include <asm/unistd.h>
-#include <asm/arch/entry-macro.S>
+#include <asm/ftrace.h>
+#include <mach/entry-macro.S>
 
 #include "entry-header.S"
 
@@ -76,6 +77,7 @@ no_work_pending:
 	mov	r0, r0
 	add	sp, sp, #S_FRAME_SIZE - S_PC
 	movs	pc, lr				@ return & move spsr_svc into cpsr
+ENDPROC(ret_to_user)
 
 /*
  * This is how we return from a fork.
@@ -91,7 +93,7 @@ ENTRY(ret_from_fork)
 	mov	r0, #1				@ trace exit [IP = 1]
 	bl	syscall_trace
 	b	ret_slow_syscall
-	
+ENDPROC(ret_from_fork)
 
 	.equ NR_syscalls,0
 #define CALL(x) .equ NR_syscalls,NR_syscalls+1
@@ -99,6 +101,56 @@ ENTRY(ret_from_fork)
 #undef CALL
 #define CALL(x) .long x
 
+#ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+ENTRY(mcount)
+	stmdb sp!, {r0-r3, lr}
+	mov r0, lr
+	sub r0, r0, #MCOUNT_INSN_SIZE
+
+	.globl mcount_call
+mcount_call:
+	bl ftrace_stub
+	ldmia sp!, {r0-r3, pc}
+
+ENTRY(ftrace_caller)
+	stmdb sp!, {r0-r3, lr}
+	ldr r1, [fp, #-4]
+	mov r0, lr
+	sub r0, r0, #MCOUNT_INSN_SIZE
+
+	.globl ftrace_call
+ftrace_call:
+	bl ftrace_stub
+	ldmia sp!, {r0-r3, pc}
+
+#else
+
+ENTRY(mcount)
+	stmdb sp!, {r0-r3, lr}
+	ldr r0, =ftrace_trace_function
+	ldr r2, [r0]
+	adr r0, ftrace_stub
+	cmp r0, r2
+	bne trace
+	ldmia sp!, {r0-r3, pc}
+
+trace:
+	ldr r1, [fp, #-4]
+	mov r0, lr
+	sub r0, r0, #MCOUNT_INSN_SIZE
+	mov lr, pc
+	mov pc, r2
+	ldmia sp!, {r0-r3, pc}
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+	.globl ftrace_stub
+ftrace_stub:
+	mov pc, lr
+
+#endif /* CONFIG_FTRACE */
+
 /*=============================================================================
  * SWI handler
  *-----------------------------------------------------------------------------
@@ -218,6 +270,7 @@ ENTRY(vector_swi)
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
 	bcs	arm_syscall	
 	b	sys_ni_syscall			@ not private func
+ENDPROC(vector_swi)
 
 	/*
 	 * This is the really slow path.  We're going to be doing
@@ -275,7 +328,6 @@ ENTRY(sys_call_table)
  */
 @ r0 = syscall number
 @ r8 = syscall table
-		.type	sys_syscall, #function
 sys_syscall:
 		bic	scno, r0, #__NR_OABI_SYSCALL_BASE
 		cmp	scno, #__NR_syscall - __NR_SYSCALL_BASE
@@ -287,53 +339,65 @@ sys_syscall:
 		movlo	r3, r4
 		ldrlo	pc, [tbl, scno, lsl #2]
 		b	sys_ni_syscall
+ENDPROC(sys_syscall)
 
 sys_fork_wrapper:
 		add	r0, sp, #S_OFF
 		b	sys_fork
+ENDPROC(sys_fork_wrapper)
 
 sys_vfork_wrapper:
 		add	r0, sp, #S_OFF
 		b	sys_vfork
+ENDPROC(sys_vfork_wrapper)
 
 sys_execve_wrapper:
 		add	r3, sp, #S_OFF
 		b	sys_execve
+ENDPROC(sys_execve_wrapper)
 
 sys_clone_wrapper:
 		add	ip, sp, #S_OFF
 		str	ip, [sp, #4]
 		b	sys_clone
+ENDPROC(sys_clone_wrapper)
 
 sys_sigsuspend_wrapper:
 		add	r3, sp, #S_OFF
 		b	sys_sigsuspend
+ENDPROC(sys_sigsuspend_wrapper)
 
 sys_rt_sigsuspend_wrapper:
 		add	r2, sp, #S_OFF
 		b	sys_rt_sigsuspend
+ENDPROC(sys_rt_sigsuspend_wrapper)
 
 sys_sigreturn_wrapper:
 		add	r0, sp, #S_OFF
 		b	sys_sigreturn
+ENDPROC(sys_sigreturn_wrapper)
 
 sys_rt_sigreturn_wrapper:
 		add	r0, sp, #S_OFF
 		b	sys_rt_sigreturn
+ENDPROC(sys_rt_sigreturn_wrapper)
 
 sys_sigaltstack_wrapper:
 		ldr	r2, [sp, #S_OFF + S_SP]
 		b	do_sigaltstack
+ENDPROC(sys_sigaltstack_wrapper)
 
 sys_statfs64_wrapper:
 		teq	r1, #88
 		moveq	r1, #84
 		b	sys_statfs64
+ENDPROC(sys_statfs64_wrapper)
 
 sys_fstatfs64_wrapper:
 		teq	r1, #88
 		moveq	r1, #84
 		b	sys_fstatfs64
+ENDPROC(sys_fstatfs64_wrapper)
 
 /*
  * Note: off_4k (r5) is always units of 4K.  If we can't do the requested
@@ -351,11 +415,14 @@ sys_mmap2:
 		str	r5, [sp, #4]
 		b	do_mmap2
 #endif
+ENDPROC(sys_mmap2)
 
 ENTRY(pabort_ifar)
 		mrc	p15, 0, r0, cr6, cr0, 2
 ENTRY(pabort_noifar)
 		mov	pc, lr
+ENDPROC(pabort_ifar)
+ENDPROC(pabort_noifar)
 
 #ifdef CONFIG_OABI_COMPAT
 
@@ -366,26 +433,31 @@ ENTRY(pabort_noifar)
 sys_oabi_pread64:
 		stmia	sp, {r3, r4}
 		b	sys_pread64
+ENDPROC(sys_oabi_pread64)
 
 sys_oabi_pwrite64:
 		stmia	sp, {r3, r4}
 		b	sys_pwrite64
+ENDPROC(sys_oabi_pwrite64)
 
 sys_oabi_truncate64:
 		mov	r3, r2
 		mov	r2, r1
 		b	sys_truncate64
+ENDPROC(sys_oabi_truncate64)
 
 sys_oabi_ftruncate64:
 		mov	r3, r2
 		mov	r2, r1
 		b	sys_ftruncate64
+ENDPROC(sys_oabi_ftruncate64)
 
 sys_oabi_readahead:
 		str	r3, [sp]
 		mov	r3, r2
 		mov	r2, r1
 		b	sys_readahead
+ENDPROC(sys_oabi_readahead)
 
 /*
  * Let's declare a second syscall table for old ABI binaries
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index e8e90346f11..36f81d96797 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -45,7 +45,6 @@
 #include <asm/fiq.h>
 #include <asm/irq.h>
 #include <asm/system.h>
-#include <asm/uaccess.h>
 
 static unsigned long no_fiq_insn;
 
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
new file mode 100644
index 00000000000..76d50e6091b
--- /dev/null
+++ b/arch/arm/kernel/ftrace.c
@@ -0,0 +1,116 @@
+/*
+ * Dynamic function tracing support.
+ *
+ * Copyright (C) 2008 Abhishek Sagar <sagar.abhishek@gmail.com>
+ *
+ * For licencing details, see COPYING.
+ *
+ * Defines low-level handling of mcount calls when the kernel
+ * is compiled with the -pg flag. When using dynamic ftrace, the
+ * mcount call-sites get patched lazily with NOP till they are
+ * enabled. All code mutation routines here take effect atomically.
+ */
+
+#include <linux/ftrace.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+
+#define PC_OFFSET      8
+#define BL_OPCODE      0xeb000000
+#define BL_OFFSET_MASK 0x00ffffff
+
+static unsigned long bl_insn;
+static const unsigned long NOP = 0xe1a00000; /* mov r0, r0 */
+
+unsigned char *ftrace_nop_replace(void)
+{
+	return (char *)&NOP;
+}
+
+/* construct a branch (BL) instruction to addr */
+unsigned char *ftrace_call_replace(unsigned long pc, unsigned long addr)
+{
+	long offset;
+
+	offset = (long)addr - (long)(pc + PC_OFFSET);
+	if (unlikely(offset < -33554432 || offset > 33554428)) {
+		/* Can't generate branches that far (from ARM ARM). Ftrace
+		 * doesn't generate branches outside of kernel text.
+		 */
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+	offset = (offset >> 2) & BL_OFFSET_MASK;
+	bl_insn = BL_OPCODE | offset;
+	return (unsigned char *)&bl_insn;
+}
+
+int ftrace_modify_code(unsigned long pc, unsigned char *old_code,
+		       unsigned char *new_code)
+{
+	unsigned long err = 0, replaced = 0, old, new;
+
+	old = *(unsigned long *)old_code;
+	new = *(unsigned long *)new_code;
+
+	__asm__ __volatile__ (
+		"1:  ldr    %1, [%2]  \n"
+		"    cmp    %1, %4    \n"
+		"2:  streq  %3, [%2]  \n"
+		"    cmpne  %1, %3    \n"
+		"    movne  %0, #2    \n"
+		"3:\n"
+
+		".section .fixup, \"ax\"\n"
+		"4:  mov  %0, #1  \n"
+		"    b    3b      \n"
+		".previous\n"
+
+		".section __ex_table, \"a\"\n"
+		"    .long 1b, 4b \n"
+		"    .long 2b, 4b \n"
+		".previous\n"
+
+		: "=r"(err), "=r"(replaced)
+		: "r"(pc), "r"(new), "r"(old), "0"(err), "1"(replaced)
+		: "memory");
+
+	if (!err && (replaced == old))
+		flush_icache_range(pc, pc + MCOUNT_INSN_SIZE);
+
+	return err;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	int ret;
+	unsigned long pc, old;
+	unsigned char *new;
+
+	pc = (unsigned long)&ftrace_call;
+	memcpy(&old, &ftrace_call, MCOUNT_INSN_SIZE);
+	new = ftrace_call_replace(pc, (unsigned long)func);
+	ret = ftrace_modify_code(pc, (unsigned char *)&old, new);
+	return ret;
+}
+
+int ftrace_mcount_set(unsigned long *data)
+{
+	unsigned long pc, old;
+	unsigned long *addr = data;
+	unsigned char *new;
+
+	pc = (unsigned long)&mcount_call;
+	memcpy(&old, &mcount_call, MCOUNT_INSN_SIZE);
+	new = ftrace_call_replace(pc, *addr);
+	*addr = ftrace_modify_code(pc, (unsigned char *)&old, new);
+	return 0;
+}
+
+/* run from kstop_machine */
+int __init ftrace_dyn_arch_init(void *data)
+{
+	ftrace_mcount_set(data);
+	return 0;
+}
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 7e9c00a8a41..bde52df1c66 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -36,7 +36,6 @@ __switch_data:
  *  r2  = atags pointer
  *  r9  = processor ID
  */
-	.type	__mmap_switched, %function
 __mmap_switched:
 	adr	r3, __switch_data + 4
 
@@ -59,6 +58,7 @@ __mmap_switched:
 	bic	r4, r0, #CR_A			@ Clear 'A' bit
 	stmia	r7, {r0, r4}			@ Save control register values
 	b	start_kernel
+ENDPROC(__mmap_switched)
 
 /*
  * Exception handling.  Something went wrong and we can't proceed.  We
@@ -69,8 +69,6 @@ __mmap_switched:
  * and hope for the best (useful if bootloader fails to pass a proper
  * machine ID for example).
  */
-
-	.type	__error_p, %function
 __error_p:
 #ifdef CONFIG_DEBUG_LL
 	adr	r0, str_p1
@@ -84,8 +82,8 @@ str_p1:	.asciz	"\nError: unrecognized/unsupported processor variant (0x"
 str_p2:	.asciz	").\n"
 	.align
 #endif
+ENDPROC(__error_p)
 
-	.type	__error_a, %function
 __error_a:
 #ifdef CONFIG_DEBUG_LL
 	mov	r4, r1				@ preserve machine ID
@@ -115,13 +113,14 @@ __error_a:
 	adr	r0, str_a3
 	bl	printascii
 	b	__error
+ENDPROC(__error_a)
+
 str_a1:	.asciz	"\nError: unrecognized/unsupported machine ID (r1 = 0x"
 str_a2:	.asciz	").\n\nAvailable machine support:\n\nID (hex)\tNAME\n"
 str_a3:	.asciz	"\nPlease check your kernel config and/or bootloader.\n"
 	.align
 #endif
 
-	.type	__error, %function
 __error:
 #ifdef CONFIG_ARCH_RPC
 /*
@@ -138,6 +137,7 @@ __error:
 #endif
 1:	mov	r0, r0
 	b	1b
+ENDPROC(__error)
 
 
 /*
@@ -153,7 +153,6 @@ __error:
  *	r5 = proc_info pointer in physical address space
  *	r9 = cpuid (preserved)
  */
-	.type	__lookup_processor_type, %function
 __lookup_processor_type:
 	adr	r3, 3f
 	ldmda	r3, {r5 - r7}
@@ -169,6 +168,7 @@ __lookup_processor_type:
 	blo	1b
 	mov	r5, #0				@ unknown processor
 2:	mov	pc, lr
+ENDPROC(__lookup_processor_type)
 
 /*
  * This provides a C-API version of the above function.
@@ -179,9 +179,10 @@ ENTRY(lookup_processor_type)
 	bl	__lookup_processor_type
 	mov	r0, r5
 	ldmfd	sp!, {r4 - r7, r9, pc}
+ENDPROC(lookup_processor_type)
 
 /*
- * Look in include/asm-arm/procinfo.h and arch/arm/kernel/arch.[ch] for
+ * Look in <asm/procinfo.h> and arch/arm/kernel/arch.[ch] for
  * more information about the __proc_info and __arch_info structures.
  */
 	.long	__proc_info_begin
@@ -201,7 +202,6 @@ ENTRY(lookup_processor_type)
  *  r3, r4, r6 corrupted
  *  r5 = mach_info pointer in physical address space
  */
-	.type	__lookup_machine_type, %function
 __lookup_machine_type:
 	adr	r3, 3b
 	ldmia	r3, {r4, r5, r6}
@@ -216,6 +216,7 @@ __lookup_machine_type:
 	blo	1b
 	mov	r5, #0				@ unknown machine
 2:	mov	pc, lr
+ENDPROC(__lookup_machine_type)
 
 /*
  * This provides a C-API version of the above function.
@@ -226,6 +227,7 @@ ENTRY(lookup_machine_type)
 	bl	__lookup_machine_type
 	mov	r0, r5
 	ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(lookup_machine_type)
 
 /* Determine validity of the r2 atags pointer.  The heuristic requires
  * that the pointer be aligned, in the first 16k of physical RAM and
@@ -239,8 +241,6 @@ ENTRY(lookup_machine_type)
  *  r2 either valid atags pointer, or zero
  *  r5, r6 corrupted
  */
-
-	.type	__vet_atags, %function
 __vet_atags:
 	tst	r2, #0x3			@ aligned?
 	bne	1f
@@ -257,3 +257,4 @@ __vet_atags:
 
 1:	mov	r2, #0
 	mov	pc, lr
+ENDPROC(__vet_atags)
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 5d78ffb8a9a..cc87e1765ed 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 
 #include <asm/assembler.h>
-#include <asm/mach-types.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
@@ -34,7 +33,6 @@
  *
  */
 	.section ".text.head", "ax"
-	.type	stext, %function
 ENTRY(stext)
 	msr	cpsr_c, #PSR_F_BIT | PSR_I_BIT | SVC_MODE @ ensure svc mode
 						@ and irqs disabled
@@ -54,11 +52,11 @@ ENTRY(stext)
 						@ the initialization is done
 	adr	lr, __after_proc_init		@ return (PIC) address
 	add	pc, r10, #PROCINFO_INITFUNC
+ENDPROC(stext)
 
 /*
  * Set the Control Register and Read the process ID.
  */
-	.type	__after_proc_init, %function
 __after_proc_init:
 #ifdef CONFIG_CPU_CP15
 	mrc	p15, 0, r0, c1, c0, 0		@ read control reg
@@ -86,6 +84,7 @@ __after_proc_init:
 
 	mov	pc, r13				@ clear the BSS and jump
 						@ to start_kernel
+ENDPROC(__after_proc_init)
 	.ltorg
 
 #include "head-common.S"
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index bff4c6e90dd..21e17dc94cb 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -75,7 +75,6 @@
  * circumstances, zImage) is for.
  */
 	.section ".text.head", "ax"
-	.type	stext, %function
 ENTRY(stext)
 	msr	cpsr_c, #PSR_F_BIT | PSR_I_BIT | SVC_MODE @ ensure svc mode
 						@ and irqs disabled
@@ -100,9 +99,9 @@ ENTRY(stext)
 						@ mmu has been enabled
 	adr	lr, __enable_mmu		@ return (PIC) address
 	add	pc, r10, #PROCINFO_INITFUNC
+ENDPROC(stext)
 
 #if defined(CONFIG_SMP)
-	.type   secondary_startup, #function
 ENTRY(secondary_startup)
 	/*
 	 * Common entry point for secondary CPUs.
@@ -128,6 +127,7 @@ ENTRY(secondary_startup)
 	adr	lr, __enable_mmu		@ return address
 	add	pc, r10, #PROCINFO_INITFUNC	@ initialise processor
 						@ (return control reg)
+ENDPROC(secondary_startup)
 
 	/*
 	 * r6  = &secondary_data
@@ -136,6 +136,7 @@ ENTRY(__secondary_switched)
 	ldr	sp, [r7, #4]			@ get secondary_data.stack
 	mov	fp, #0
 	b	secondary_start_kernel
+ENDPROC(__secondary_switched)
 
 	.type	__secondary_data, %object
 __secondary_data:
@@ -151,7 +152,6 @@ __secondary_data:
  * this is just loading the page table pointer and domain access
  * registers.
  */
-	.type	__enable_mmu, %function
 __enable_mmu:
 #ifdef CONFIG_ALIGNMENT_TRAP
 	orr	r0, r0, #CR_A
@@ -174,6 +174,7 @@ __enable_mmu:
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
 	b	__turn_mmu_on
+ENDPROC(__enable_mmu)
 
 /*
  * Enable the MMU.  This completely changes the structure of the visible
@@ -187,7 +188,6 @@ __enable_mmu:
  * other registers depend on the function called upon completion
  */
 	.align	5
-	.type	__turn_mmu_on, %function
 __turn_mmu_on:
 	mov	r0, r0
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
@@ -195,7 +195,7 @@ __turn_mmu_on:
 	mov	r3, r3
 	mov	r3, r3
 	mov	pc, r13
-
+ENDPROC(__turn_mmu_on)
 
 
 /*
@@ -211,7 +211,6 @@ __turn_mmu_on:
  *  r0, r3, r6, r7 corrupted
  *  r4 = physical page table address
  */
-	.type	__create_page_tables, %function
 __create_page_tables:
 	pgtbl	r4				@ page table address
 
@@ -325,6 +324,7 @@ __create_page_tables:
 #endif
 #endif
 	mov	pc, lr
+ENDPROC(__create_page_tables)
 	.ltorg
 
 #include "head-common.S"
diff --git a/arch/arm/kernel/init_task.c b/arch/arm/kernel/init_task.c
index 8b8c9d38a76..0bbf8062539 100644
--- a/arch/arm/kernel/init_task.c
+++ b/arch/arm/kernel/init_task.c
@@ -8,8 +8,8 @@
 #include <linux/init.h>
 #include <linux/init_task.h>
 #include <linux/mqueue.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
 static struct fs_struct init_fs = INIT_FS;
diff --git a/arch/arm/kernel/io.c b/arch/arm/kernel/io.c
index 1f6822dfae7..f4470307edb 100644
--- a/arch/arm/kernel/io.c
+++ b/arch/arm/kernel/io.c
@@ -1,7 +1,6 @@
 #include <linux/module.h>
 #include <linux/types.h>
-
-#include <asm/io.h>
+#include <linux/io.h>
 
 /*
  * Copy data from IO memory space to "real" memory space.
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 11dcd52e51b..2f3eb795fa6 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -38,6 +38,7 @@
 #include <linux/proc_fs.h>
 
 #include <asm/system.h>
+#include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 
 /*
@@ -111,18 +112,17 @@ static struct irq_desc bad_irq_desc = {
 asmlinkage void __exception asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct irq_desc *desc = irq_desc + irq;
+
+	irq_enter();
 
 	/*
 	 * Some hardware gives randomly wrong interrupts.  Rather
 	 * than crashing, do something sensible.
 	 */
 	if (irq >= NR_IRQS)
-		desc = &bad_irq_desc;
-
-	irq_enter();
-
-	desc_handle_irq(irq, desc);
+		handle_bad_irq(irq, &bad_irq_desc);
+	else
+		generic_handle_irq(irq);
 
 	/* AT91 specific workaround */
 	irq_finish(irq);
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
new file mode 100644
index 00000000000..ba8ccfede96
--- /dev/null
+++ b/arch/arm/kernel/kgdb.c
@@ -0,0 +1,199 @@
+/*
+ * arch/arm/kernel/kgdb.c
+ *
+ * ARM KGDB support
+ *
+ * Copyright (c) 2002-2004 MontaVista Software, Inc
+ * Copyright (c) 2008 Wind River Systems, Inc.
+ *
+ * Authors:  George Davis <davis_g@mvista.com>
+ *           Deepak Saxena <dsaxena@plexity.net>
+ */
+#include <linux/kgdb.h>
+#include <asm/traps.h>
+
+/* Make a local copy of the registers passed into the handler (bletch) */
+void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs)
+{
+	int regno;
+
+	/* Initialize all to zero. */
+	for (regno = 0; regno < GDB_MAX_REGS; regno++)
+		gdb_regs[regno] = 0;
+
+	gdb_regs[_R0]		= kernel_regs->ARM_r0;
+	gdb_regs[_R1]		= kernel_regs->ARM_r1;
+	gdb_regs[_R2]		= kernel_regs->ARM_r2;
+	gdb_regs[_R3]		= kernel_regs->ARM_r3;
+	gdb_regs[_R4]		= kernel_regs->ARM_r4;
+	gdb_regs[_R5]		= kernel_regs->ARM_r5;
+	gdb_regs[_R6]		= kernel_regs->ARM_r6;
+	gdb_regs[_R7]		= kernel_regs->ARM_r7;
+	gdb_regs[_R8]		= kernel_regs->ARM_r8;
+	gdb_regs[_R9]		= kernel_regs->ARM_r9;
+	gdb_regs[_R10]		= kernel_regs->ARM_r10;
+	gdb_regs[_FP]		= kernel_regs->ARM_fp;
+	gdb_regs[_IP]		= kernel_regs->ARM_ip;
+	gdb_regs[_SPT]		= kernel_regs->ARM_sp;
+	gdb_regs[_LR]		= kernel_regs->ARM_lr;
+	gdb_regs[_PC]		= kernel_regs->ARM_pc;
+	gdb_regs[_CPSR]		= kernel_regs->ARM_cpsr;
+}
+
+/* Copy local gdb registers back to kgdb regs, for later copy to kernel */
+void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs)
+{
+	kernel_regs->ARM_r0	= gdb_regs[_R0];
+	kernel_regs->ARM_r1	= gdb_regs[_R1];
+	kernel_regs->ARM_r2	= gdb_regs[_R2];
+	kernel_regs->ARM_r3	= gdb_regs[_R3];
+	kernel_regs->ARM_r4	= gdb_regs[_R4];
+	kernel_regs->ARM_r5	= gdb_regs[_R5];
+	kernel_regs->ARM_r6	= gdb_regs[_R6];
+	kernel_regs->ARM_r7	= gdb_regs[_R7];
+	kernel_regs->ARM_r8	= gdb_regs[_R8];
+	kernel_regs->ARM_r9	= gdb_regs[_R9];
+	kernel_regs->ARM_r10	= gdb_regs[_R10];
+	kernel_regs->ARM_fp	= gdb_regs[_FP];
+	kernel_regs->ARM_ip	= gdb_regs[_IP];
+	kernel_regs->ARM_sp	= gdb_regs[_SPT];
+	kernel_regs->ARM_lr	= gdb_regs[_LR];
+	kernel_regs->ARM_pc	= gdb_regs[_PC];
+	kernel_regs->ARM_cpsr	= gdb_regs[_CPSR];
+}
+
+void
+sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
+{
+	struct pt_regs *thread_regs;
+	int regno;
+
+	/* Just making sure... */
+	if (task == NULL)
+		return;
+
+	/* Initialize to zero */
+	for (regno = 0; regno < GDB_MAX_REGS; regno++)
+		gdb_regs[regno] = 0;
+
+	/* Otherwise, we have only some registers from switch_to() */
+	thread_regs		= task_pt_regs(task);
+	gdb_regs[_R0]		= thread_regs->ARM_r0;
+	gdb_regs[_R1]		= thread_regs->ARM_r1;
+	gdb_regs[_R2]		= thread_regs->ARM_r2;
+	gdb_regs[_R3]		= thread_regs->ARM_r3;
+	gdb_regs[_R4]		= thread_regs->ARM_r4;
+	gdb_regs[_R5]		= thread_regs->ARM_r5;
+	gdb_regs[_R6]		= thread_regs->ARM_r6;
+	gdb_regs[_R7]		= thread_regs->ARM_r7;
+	gdb_regs[_R8]		= thread_regs->ARM_r8;
+	gdb_regs[_R9]		= thread_regs->ARM_r9;
+	gdb_regs[_R10]		= thread_regs->ARM_r10;
+	gdb_regs[_FP]		= thread_regs->ARM_fp;
+	gdb_regs[_IP]		= thread_regs->ARM_ip;
+	gdb_regs[_SPT]		= thread_regs->ARM_sp;
+	gdb_regs[_LR]		= thread_regs->ARM_lr;
+	gdb_regs[_PC]		= thread_regs->ARM_pc;
+	gdb_regs[_CPSR]		= thread_regs->ARM_cpsr;
+}
+
+static int compiled_break;
+
+int kgdb_arch_handle_exception(int exception_vector, int signo,
+			       int err_code, char *remcom_in_buffer,
+			       char *remcom_out_buffer,
+			       struct pt_regs *linux_regs)
+{
+	unsigned long addr;
+	char *ptr;
+
+	switch (remcom_in_buffer[0]) {
+	case 'D':
+	case 'k':
+	case 'c':
+		/*
+		 * Try to read optional parameter, pc unchanged if no parm.
+		 * If this was a compiled breakpoint, we need to move
+		 * to the next instruction or we will just breakpoint
+		 * over and over again.
+		 */
+		ptr = &remcom_in_buffer[1];
+		if (kgdb_hex2long(&ptr, &addr))
+			linux_regs->ARM_pc = addr;
+		else if (compiled_break == 1)
+			linux_regs->ARM_pc += 4;
+
+		compiled_break = 0;
+
+		return 0;
+	}
+
+	return -1;
+}
+
+static int kgdb_brk_fn(struct pt_regs *regs, unsigned int instr)
+{
+	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+
+	return 0;
+}
+
+static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr)
+{
+	compiled_break = 1;
+	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+
+	return 0;
+}
+
+static struct undef_hook kgdb_brkpt_hook = {
+	.instr_mask		= 0xffffffff,
+	.instr_val		= KGDB_BREAKINST,
+	.fn			= kgdb_brk_fn
+};
+
+static struct undef_hook kgdb_compiled_brkpt_hook = {
+	.instr_mask		= 0xffffffff,
+	.instr_val		= KGDB_COMPILED_BREAK,
+	.fn			= kgdb_compiled_brk_fn
+};
+
+/**
+ *	kgdb_arch_init - Perform any architecture specific initalization.
+ *
+ *	This function will handle the initalization of any architecture
+ *	specific callbacks.
+ */
+int kgdb_arch_init(void)
+{
+	register_undef_hook(&kgdb_brkpt_hook);
+	register_undef_hook(&kgdb_compiled_brkpt_hook);
+
+	return 0;
+}
+
+/**
+ *	kgdb_arch_exit - Perform any architecture specific uninitalization.
+ *
+ *	This function will handle the uninitalization of any architecture
+ *	specific callbacks, for dynamic registration and unregistration.
+ */
+void kgdb_arch_exit(void)
+{
+	unregister_undef_hook(&kgdb_brkpt_hook);
+	unregister_undef_hook(&kgdb_compiled_brkpt_hook);
+}
+
+/*
+ * Register our undef instruction hooks with ARM undef core.
+ * We regsiter a hook specifically looking for the KGB break inst
+ * and we handle the normal undef case within the do_undefinstr
+ * handler.
+ */
+struct kgdb_arch arch_kgdb_ops = {
+#ifndef __ARMEB__
+	.gdb_bpt_instr		= {0xfe, 0xde, 0xff, 0xe7}
+#else /* ! __ARMEB__ */
+	.gdb_bpt_instr		= {0xe7, 0xff, 0xde, 0xfe}
+#endif
+};
diff --git a/arch/arm/kernel/kprobes-decode.c b/arch/arm/kernel/kprobes-decode.c
index b4565bb133c..da1f94906a4 100644
--- a/arch/arm/kernel/kprobes-decode.c
+++ b/arch/arm/kernel/kprobes-decode.c
@@ -488,7 +488,7 @@ static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs)
 
 	if (!ubit)
 		addr -= reg_count;
-	addr += (!pbit ^ !ubit);
+	addr += (!pbit == !ubit);
 
 	reg_bit_vector = insn & 0xffff;
 	while (reg_bit_vector) {
@@ -503,7 +503,7 @@ static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs)
 	if (wbit) {
 		if (!ubit)
 			addr -= reg_count;
-		addr -= (!pbit ^ !ubit);
+		addr -= (!pbit == !ubit);
 		regs->uregs[rn] = (long)addr;
 	}
 }
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 5593dd20721..3f9abe0e9af 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -200,9 +200,12 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 	}
 }
 
-int kprobe_trap_handler(struct pt_regs *regs, unsigned int instr)
+static int __kprobes kprobe_trap_handler(struct pt_regs *regs, unsigned int instr)
 {
+	unsigned long flags;
+	local_irq_save(flags);
 	kprobe_handler(regs);
+	local_irq_restore(flags);
 	return 0;
 }
 
@@ -274,7 +277,7 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
  * for kretprobe handlers which should normally be interested in r0 only
  * anyway.
  */
-static void __attribute__((naked)) __kprobes kretprobe_trampoline(void)
+void __naked __kprobes kretprobe_trampoline(void)
 {
 	__asm__ __volatile__ (
 		"stmdb	sp!, {r0 - r11}		\n\t"
@@ -296,8 +299,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
 
 	INIT_HLIST_HEAD(&empty_rp);
-	spin_lock_irqsave(&kretprobe_lock, flags);
-	head = kretprobe_inst_table_head(current);
+	kretprobe_hash_lock(current, &head, &flags);
 
 	/*
 	 * It is possible to have multiple instances associated with a given
@@ -337,7 +339,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	}
 
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-	spin_unlock_irqrestore(&kretprobe_lock, flags);
+	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
@@ -347,7 +349,6 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	return (void *)orig_ret_address;
 }
 
-/* Called with kretprobe_lock held. */
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index db8f54a3451..440dc62cdc3 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -6,10 +6,10 @@
 #include <linux/kexec.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>
+#include <linux/io.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
-#include <asm/io.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-types.h>
 
@@ -71,7 +71,7 @@ void machine_kexec(struct kimage *image)
 
 
 	flush_icache_range((unsigned long) reboot_code_buffer,
-			   (unsigned long) reboot_code_buffer + KEXEC_CONTROL_CODE_SIZE);
+			   (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
 	printk(KERN_INFO "Bye!\n");
 
 	cpu_proc_fin();
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 79b7e5cf541..9203ba7d58e 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/moduleloader.h>
 #include <linux/kernel.h>
+#include <linux/mm.h>
 #include <linux/elf.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
@@ -46,7 +47,7 @@ void *module_alloc(unsigned long size)
 	if (!area)
 		return NULL;
 
-	return __vmalloc_area(area, GFP_KERNEL, PAGE_KERNEL);
+	return __vmalloc_area(area, GFP_KERNEL, PAGE_KERNEL_EXEC);
 }
 #else /* CONFIG_MMU */
 void *module_alloc(unsigned long size)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 46bf2ede612..d3ea6fa8952 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -28,12 +28,12 @@
 #include <linux/pm.h>
 #include <linux/tick.h>
 #include <linux/utsname.h>
+#include <linux/uaccess.h>
 
 #include <asm/leds.h>
 #include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/thread_notify.h>
-#include <asm/uaccess.h>
 #include <asm/mach/time.h>
 
 static const char *processor_modes[] = {
@@ -51,7 +51,7 @@ extern void setup_mm_for_reboot(char mode);
 
 static volatile int hlt_counter;
 
-#include <asm/arch/system.h>
+#include <mach/system.h>
 
 void disable_hlt(void)
 {
@@ -133,10 +133,8 @@ static void default_idle(void)
 		cpu_relax();
 	else {
 		local_irq_disable();
-		if (!need_resched()) {
-			timer_dyn_reprogram();
+		if (!need_resched())
 			arch_idle();
-		}
 		local_irq_enable();
 	}
 }
@@ -164,7 +162,7 @@ void cpu_idle(void)
 		if (!idle)
 			idle = default_idle;
 		leds_event(led_idle_start);
-		tick_nohz_stop_sched_tick();
+		tick_nohz_stop_sched_tick(1);
 		while (!need_resched())
 			idle();
 		leds_event(led_idle_end);
@@ -269,35 +267,6 @@ void show_regs(struct pt_regs * regs)
 	__backtrace();
 }
 
-void show_fpregs(struct user_fp *regs)
-{
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		unsigned long *p;
-		char type;
-
-		p = (unsigned long *)(regs->fpregs + i);
-
-		switch (regs->ftype[i]) {
-			case 1: type = 'f'; break;
-			case 2: type = 'd'; break;
-			case 3: type = 'e'; break;
-			default: type = '?'; break;
-		}
-		if (regs->init_flag)
-			type = '?';
-
-		printk("  f%d(%c): %08lx %08lx %08lx%c",
-			i, type, p[0], p[1], p[2], i & 1 ? '\n' : ' ');
-	}
-			
-
-	printk("FPSR: %08lx FPCR: %08lx\n",
-		(unsigned long)regs->fpsr,
-		(unsigned long)regs->fpcr);
-}
-
 /*
  * Free current thread data structures etc..
  */
@@ -416,7 +385,7 @@ unsigned long get_wchan(struct task_struct *p)
 	do {
 		if (fp < stack_start || fp > stack_end)
 			return 0;
-		lr = pc_pointer (((unsigned long *)fp)[-1]);
+		lr = ((unsigned long *)fp)[-1];
 		if (!in_sched_functions(lr))
 			return lr;
 		fp = *(unsigned long *) (fp - 12);
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 4b05dc5c102..df653ea5925 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -18,8 +18,8 @@
 #include <linux/security.h>
 #include <linux/init.h>
 #include <linux/signal.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/system.h>
 #include <asm/traps.h>
@@ -126,7 +126,7 @@ ptrace_getrn(struct task_struct *child, unsigned long insn)
 
 	val = get_user_reg(child, reg);
 	if (reg == 15)
-		val = pc_pointer(val + 8);
+		val += 8;
 
 	return val;
 }
@@ -278,8 +278,7 @@ get_branch_address(struct task_struct *child, unsigned long pc, unsigned long in
 				else
 					base -= aluop2;
 			}
-			if (read_u32(child, base, &alt) == 0)
-				alt = pc_pointer(alt);
+			read_u32(child, base, &alt);
 		}
 		break;
 
@@ -305,8 +304,7 @@ get_branch_address(struct task_struct *child, unsigned long pc, unsigned long in
 
 			base = ptrace_getrn(child, insn);
 
-			if (read_u32(child, base + nr_regs, &alt) == 0)
-				alt = pc_pointer(alt);
+			read_u32(child, base + nr_regs, &alt);
 			break;
 		}
 		break;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index b7b0720bc1b..1f1eecca7f5 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -26,16 +26,19 @@
 #include <linux/fs.h>
 
 #include <asm/cpu.h>
+#include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/procinfo.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
 #include <asm/cacheflush.h>
+#include <asm/cachetype.h>
 #include <asm/tlbflush.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
+#include <asm/traps.h>
 
 #include "compat.h"
 #include "atags.h"
@@ -58,13 +61,14 @@ __setup("fpe=", fpe_setup);
 
 extern void paging_init(struct meminfo *, struct machine_desc *desc);
 extern void reboot_setup(char *str);
-extern int root_mountflags;
-extern void _stext, _text, _etext, __data_start, _edata, _end;
+extern void _text, _etext, __data_start, _edata, _end;
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
 unsigned int __machine_arch_type;
 EXPORT_SYMBOL(__machine_arch_type);
+unsigned int cacheid;
+EXPORT_SYMBOL(cacheid);
 
 unsigned int __atags_pointer __initdata;
 
@@ -108,9 +112,6 @@ static struct stack stacks[NR_CPUS];
 char elf_platform[ELF_PLATFORM_SIZE];
 EXPORT_SYMBOL(elf_platform);
 
-unsigned long phys_initrd_start __initdata = 0;
-unsigned long phys_initrd_size __initdata = 0;
-
 static struct meminfo meminfo __initdata = { 0, };
 static const char *cpu_name;
 static const char *machine_name;
@@ -175,63 +176,6 @@ static struct resource io_res[] = {
 #define lp1 io_res[1]
 #define lp2 io_res[2]
 
-static const char *cache_types[16] = {
-	"write-through",
-	"write-back",
-	"write-back",
-	"undefined 3",
-	"undefined 4",
-	"undefined 5",
-	"write-back",
-	"write-back",
-	"undefined 8",
-	"undefined 9",
-	"undefined 10",
-	"undefined 11",
-	"undefined 12",
-	"undefined 13",
-	"write-back",
-	"undefined 15",
-};
-
-static const char *cache_clean[16] = {
-	"not required",
-	"read-block",
-	"cp15 c7 ops",
-	"undefined 3",
-	"undefined 4",
-	"undefined 5",
-	"cp15 c7 ops",
-	"cp15 c7 ops",
-	"undefined 8",
-	"undefined 9",
-	"undefined 10",
-	"undefined 11",
-	"undefined 12",
-	"undefined 13",
-	"cp15 c7 ops",
-	"undefined 15",
-};
-
-static const char *cache_lockdown[16] = {
-	"not supported",
-	"not supported",
-	"not supported",
-	"undefined 3",
-	"undefined 4",
-	"undefined 5",
-	"format A",
-	"format B",
-	"undefined 8",
-	"undefined 9",
-	"undefined 10",
-	"undefined 11",
-	"undefined 12",
-	"undefined 13",
-	"format C",
-	"undefined 15",
-};
-
 static const char *proc_arch[] = {
 	"undefined/unknown",
 	"3",
@@ -252,61 +196,19 @@ static const char *proc_arch[] = {
 	"?(17)",
 };
 
-#define CACHE_TYPE(x)	(((x) >> 25) & 15)
-#define CACHE_S(x)	((x) & (1 << 24))
-#define CACHE_DSIZE(x)	(((x) >> 12) & 4095)	/* only if S=1 */
-#define CACHE_ISIZE(x)	((x) & 4095)
-
-#define CACHE_SIZE(y)	(((y) >> 6) & 7)
-#define CACHE_ASSOC(y)	(((y) >> 3) & 7)
-#define CACHE_M(y)	((y) & (1 << 2))
-#define CACHE_LINE(y)	((y) & 3)
-
-static inline void dump_cache(const char *prefix, int cpu, unsigned int cache)
-{
-	unsigned int mult = 2 + (CACHE_M(cache) ? 1 : 0);
-
-	printk("CPU%u: %s: %d bytes, associativity %d, %d byte lines, %d sets\n",
-		cpu, prefix,
-		mult << (8 + CACHE_SIZE(cache)),
-		(mult << CACHE_ASSOC(cache)) >> 1,
-		8 << CACHE_LINE(cache),
-		1 << (6 + CACHE_SIZE(cache) - CACHE_ASSOC(cache) -
-			CACHE_LINE(cache)));
-}
-
-static void __init dump_cpu_info(int cpu)
-{
-	unsigned int info = read_cpuid(CPUID_CACHETYPE);
-
-	if (info != processor_id) {
-		printk("CPU%u: D %s %s cache\n", cpu, cache_is_vivt() ? "VIVT" : "VIPT",
-		       cache_types[CACHE_TYPE(info)]);
-		if (CACHE_S(info)) {
-			dump_cache("I cache", cpu, CACHE_ISIZE(info));
-			dump_cache("D cache", cpu, CACHE_DSIZE(info));
-		} else {
-			dump_cache("cache", cpu, CACHE_ISIZE(info));
-		}
-	}
-
-	if (arch_is_coherent())
-		printk("Cache coherency enabled\n");
-}
-
 int cpu_architecture(void)
 {
 	int cpu_arch;
 
-	if ((processor_id & 0x0008f000) == 0) {
+	if ((read_cpuid_id() & 0x0008f000) == 0) {
 		cpu_arch = CPU_ARCH_UNKNOWN;
-	} else if ((processor_id & 0x0008f000) == 0x00007000) {
-		cpu_arch = (processor_id & (1 << 23)) ? CPU_ARCH_ARMv4T : CPU_ARCH_ARMv3;
-	} else if ((processor_id & 0x00080000) == 0x00000000) {
-		cpu_arch = (processor_id >> 16) & 7;
+	} else if ((read_cpuid_id() & 0x0008f000) == 0x00007000) {
+		cpu_arch = (read_cpuid_id() & (1 << 23)) ? CPU_ARCH_ARMv4T : CPU_ARCH_ARMv3;
+	} else if ((read_cpuid_id() & 0x00080000) == 0x00000000) {
+		cpu_arch = (read_cpuid_id() >> 16) & 7;
 		if (cpu_arch)
 			cpu_arch += CPU_ARCH_ARMv3;
-	} else if ((processor_id & 0x000f0000) == 0x000f0000) {
+	} else if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) {
 		unsigned int mmfr0;
 
 		/* Revised CPUID format. Read the Memory Model Feature
@@ -327,6 +229,34 @@ int cpu_architecture(void)
 	return cpu_arch;
 }
 
+static void __init cacheid_init(void)
+{
+	unsigned int cachetype = read_cpuid_cachetype();
+	unsigned int arch = cpu_architecture();
+
+	if (arch >= CPU_ARCH_ARMv7) {
+		cacheid = CACHEID_VIPT_NONALIASING;
+		if ((cachetype & (3 << 14)) == 1 << 14)
+			cacheid |= CACHEID_ASID_TAGGED;
+	} else if (arch >= CPU_ARCH_ARMv6) {
+		if (cachetype & (1 << 23))
+			cacheid = CACHEID_VIPT_ALIASING;
+		else
+			cacheid = CACHEID_VIPT_NONALIASING;
+	} else {
+		cacheid = CACHEID_VIVT;
+	}
+
+	printk("CPU: %s data cache, %s instruction cache\n",
+		cache_is_vivt() ? "VIVT" :
+		cache_is_vipt_aliasing() ? "VIPT aliasing" :
+		cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown",
+		cache_is_vivt() ? "VIVT" :
+		icache_is_vivt_asid_tagged() ? "VIVT ASID tagged" :
+		cache_is_vipt_aliasing() ? "VIPT aliasing" :
+		cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown");
+}
+
 /*
  * These functions re-use the assembly code in head.S, which
  * already provide the required functionality.
@@ -343,10 +273,10 @@ static void __init setup_processor(void)
 	 * types.  The linker builds this table for us from the
 	 * entries in arch/arm/mm/proc-*.S
 	 */
-	list = lookup_processor_type(processor_id);
+	list = lookup_processor_type(read_cpuid_id());
 	if (!list) {
 		printk("CPU configuration botched (ID %08x), unable "
-		       "to continue.\n", processor_id);
+		       "to continue.\n", read_cpuid_id());
 		while (1);
 	}
 
@@ -366,7 +296,7 @@ static void __init setup_processor(void)
 #endif
 
 	printk("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
-	       cpu_name, processor_id, (int)processor_id & 15,
+	       cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
 	       proc_arch[cpu_architecture()], cr_alignment);
 
 	sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS);
@@ -376,14 +306,14 @@ static void __init setup_processor(void)
 	elf_hwcap &= ~HWCAP_THUMB;
 #endif
 
+	cacheid_init();
 	cpu_proc_init();
 }
 
 /*
  * cpu_init - initialise one CPU.
  *
- * cpu_init dumps the cache information, initialises SMP specific
- * information, and sets up the per-CPU stacks.
+ * cpu_init sets up the per-CPU stacks.
  */
 void cpu_init(void)
 {
@@ -395,9 +325,6 @@ void cpu_init(void)
 		BUG();
 	}
 
-	if (system_state == SYSTEM_BOOTING)
-		dump_cpu_info(cpu);
-
 	/*
 	 * setup stacks for re-entrant exception handlers
 	 */
@@ -440,20 +367,6 @@ static struct machine_desc * __init setup_machine(unsigned int nr)
 	return list;
 }
 
-static void __init early_initrd(char **p)
-{
-	unsigned long start, size;
-
-	start = memparse(*p, p);
-	if (**p == ',') {
-		size = memparse((*p) + 1, p);
-
-		phys_initrd_start = start;
-		phys_initrd_size = size;
-	}
-}
-__early_param("initrd=", early_initrd);
-
 static void __init arm_add_memory(unsigned long start, unsigned long size)
 {
 	struct membank *bank;
@@ -513,12 +426,12 @@ static void __init parse_cmdline(char **cmdline_p, char *from)
 			struct early_params *p;
 
 			for (p = &__early_begin; p < &__early_end; p++) {
-				int len = strlen(p->arg);
+				int arglen = strlen(p->arg);
 
-				if (memcmp(from, p->arg, len) == 0) {
+				if (memcmp(from, p->arg, arglen) == 0) {
 					if (to != command_line)
 						to -= 1;
-					from += len;
+					from += arglen;
 					p->fn(&from);
 
 					while (*from != ' ' && *from != '\0')
@@ -565,18 +478,13 @@ request_standard_resources(struct meminfo *mi, struct machine_desc *mdesc)
 	kernel_data.end     = virt_to_phys(&_end - 1);
 
 	for (i = 0; i < mi->nr_banks; i++) {
-		unsigned long virt_start, virt_end;
-
 		if (mi->bank[i].size == 0)
 			continue;
 
-		virt_start = __phys_to_virt(mi->bank[i].start);
-		virt_end   = virt_start + mi->bank[i].size - 1;
-
 		res = alloc_bootmem_low(sizeof(*res));
 		res->name  = "System RAM";
-		res->start = __virt_to_phys(virt_start);
-		res->end   = __virt_to_phys(virt_end);
+		res->start = mi->bank[i].start;
+		res->end   = mi->bank[i].start + mi->bank[i].size - 1;
 		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);
@@ -680,26 +588,6 @@ static int __init parse_tag_ramdisk(const struct tag *tag)
 
 __tagtable(ATAG_RAMDISK, parse_tag_ramdisk);
 
-static int __init parse_tag_initrd(const struct tag *tag)
-{
-	printk(KERN_WARNING "ATAG_INITRD is deprecated; "
-		"please update your bootloader.\n");
-	phys_initrd_start = __virt_to_phys(tag->u.initrd.start);
-	phys_initrd_size = tag->u.initrd.size;
-	return 0;
-}
-
-__tagtable(ATAG_INITRD, parse_tag_initrd);
-
-static int __init parse_tag_initrd2(const struct tag *tag)
-{
-	phys_initrd_start = tag->u.initrd.start;
-	phys_initrd_size = tag->u.initrd.size;
-	return 0;
-}
-
-__tagtable(ATAG_INITRD2, parse_tag_initrd2);
-
 static int __init parse_tag_serialnr(const struct tag *tag)
 {
 	system_serial_low = tag->u.serialnr.low;
@@ -853,6 +741,7 @@ void __init setup_arch(char **cmdline_p)
 	conswitchp = &dummy_con;
 #endif
 #endif
+	early_trap_init();
 }
 
 
@@ -886,28 +775,12 @@ static const char *hwcap_str[] = {
 	NULL
 };
 
-static void
-c_show_cache(struct seq_file *m, const char *type, unsigned int cache)
-{
-	unsigned int mult = 2 + (CACHE_M(cache) ? 1 : 0);
-
-	seq_printf(m, "%s size\t\t: %d\n"
-		      "%s assoc\t\t: %d\n"
-		      "%s line length\t: %d\n"
-		      "%s sets\t\t: %d\n",
-		type, mult << (8 + CACHE_SIZE(cache)),
-		type, (mult << CACHE_ASSOC(cache)) >> 1,
-		type, 8 << CACHE_LINE(cache),
-		type, 1 << (6 + CACHE_SIZE(cache) - CACHE_ASSOC(cache) -
-			    CACHE_LINE(cache)));
-}
-
 static int c_show(struct seq_file *m, void *v)
 {
 	int i;
 
 	seq_printf(m, "Processor\t: %s rev %d (%s)\n",
-		   cpu_name, (int)processor_id & 15, elf_platform);
+		   cpu_name, read_cpuid_id() & 15, elf_platform);
 
 #if defined(CONFIG_SMP)
 	for_each_online_cpu(i) {
@@ -934,47 +807,26 @@ static int c_show(struct seq_file *m, void *v)
 		if (elf_hwcap & (1 << i))
 			seq_printf(m, "%s ", hwcap_str[i]);
 
-	seq_printf(m, "\nCPU implementer\t: 0x%02x\n", processor_id >> 24);
+	seq_printf(m, "\nCPU implementer\t: 0x%02x\n", read_cpuid_id() >> 24);
 	seq_printf(m, "CPU architecture: %s\n", proc_arch[cpu_architecture()]);
 
-	if ((processor_id & 0x0008f000) == 0x00000000) {
+	if ((read_cpuid_id() & 0x0008f000) == 0x00000000) {
 		/* pre-ARM7 */
-		seq_printf(m, "CPU part\t: %07x\n", processor_id >> 4);
+		seq_printf(m, "CPU part\t: %07x\n", read_cpuid_id() >> 4);
 	} else {
-		if ((processor_id & 0x0008f000) == 0x00007000) {
+		if ((read_cpuid_id() & 0x0008f000) == 0x00007000) {
 			/* ARM7 */
 			seq_printf(m, "CPU variant\t: 0x%02x\n",
-				   (processor_id >> 16) & 127);
+				   (read_cpuid_id() >> 16) & 127);
 		} else {
 			/* post-ARM7 */
 			seq_printf(m, "CPU variant\t: 0x%x\n",
-				   (processor_id >> 20) & 15);
+				   (read_cpuid_id() >> 20) & 15);
 		}
 		seq_printf(m, "CPU part\t: 0x%03x\n",
-			   (processor_id >> 4) & 0xfff);
-	}
-	seq_printf(m, "CPU revision\t: %d\n", processor_id & 15);
-
-	{
-		unsigned int cache_info = read_cpuid(CPUID_CACHETYPE);
-		if (cache_info != processor_id) {
-			seq_printf(m, "Cache type\t: %s\n"
-				      "Cache clean\t: %s\n"
-				      "Cache lockdown\t: %s\n"
-				      "Cache format\t: %s\n",
-				   cache_types[CACHE_TYPE(cache_info)],
-				   cache_clean[CACHE_TYPE(cache_info)],
-				   cache_lockdown[CACHE_TYPE(cache_info)],
-				   CACHE_S(cache_info) ? "Harvard" : "Unified");
-
-			if (CACHE_S(cache_info)) {
-				c_show_cache(m, "I", CACHE_ISIZE(cache_info));
-				c_show_cache(m, "D", CACHE_DSIZE(cache_info));
-			} else {
-				c_show_cache(m, "Cache", CACHE_ISIZE(cache_info));
-			}
-		}
+			   (read_cpuid_id() >> 4) & 0xfff);
 	}
+	seq_printf(m, "CPU revision\t: %d\n", read_cpuid_id() & 15);
 
 	seq_puts(m, "\n");
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index ef2f86a5e78..80b8b5c7e07 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -11,11 +11,11 @@
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/freezer.h>
+#include <linux/uaccess.h>
 
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
 #include <asm/unistd.h>
 
 #include "ptrace.h"
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index eefae1de334..e42a749a56d 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -68,20 +68,10 @@ enum ipi_msg_type {
 	IPI_TIMER,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
+	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
 };
 
-struct smp_call_struct {
-	void (*func)(void *info);
-	void *info;
-	int wait;
-	cpumask_t pending;
-	cpumask_t unfinished;
-};
-
-static struct smp_call_struct * volatile smp_call_function_data;
-static DEFINE_SPINLOCK(smp_call_function_lock);
-
 int __cpuinit __cpu_up(unsigned int cpu)
 {
 	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
@@ -110,7 +100,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	 * a 1:1 mapping for the physical address of the kernel.
 	 */
 	pgd = pgd_alloc(&init_mm);
-	pmd = pmd_offset(pgd, PHYS_OFFSET);
+	pmd = pmd_offset(pgd + pgd_index(PHYS_OFFSET), PHYS_OFFSET);
 	*pmd = __pmd((PHYS_OFFSET & PGDIR_MASK) |
 		     PMD_TYPE_SECT | PMD_SECT_AP_WRITE);
 
@@ -149,7 +139,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	secondary_data.stack = NULL;
 	secondary_data.pgdir = 0;
 
-	*pmd_offset(pgd, PHYS_OFFSET) = __pmd(0);
+	*pmd = __pmd(0);
 	pgd_free(&init_mm, pgd);
 
 	if (ret) {
@@ -287,6 +277,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	/*
 	 * Enable local interrupts.
 	 */
+	notify_cpu_starting(cpu);
 	local_irq_enable();
 	local_fiq_enable();
 
@@ -366,114 +357,15 @@ static void send_ipi_message(cpumask_t callmap, enum ipi_msg_type msg)
 	local_irq_restore(flags);
 }
 
-/*
- * You must not call this function with disabled interrupts, from a
- * hardware interrupt handler, nor from a bottom half handler.
- */
-static int smp_call_function_on_cpu(void (*func)(void *info), void *info,
-				    int retry, int wait, cpumask_t callmap)
-{
-	struct smp_call_struct data;
-	unsigned long timeout;
-	int ret = 0;
-
-	data.func = func;
-	data.info = info;
-	data.wait = wait;
-
-	cpu_clear(smp_processor_id(), callmap);
-	if (cpus_empty(callmap))
-		goto out;
-
-	data.pending = callmap;
-	if (wait)
-		data.unfinished = callmap;
-
-	/*
-	 * try to get the mutex on smp_call_function_data
-	 */
-	spin_lock(&smp_call_function_lock);
-	smp_call_function_data = &data;
-
-	send_ipi_message(callmap, IPI_CALL_FUNC);
-
-	timeout = jiffies + HZ;
-	while (!cpus_empty(data.pending) && time_before(jiffies, timeout))
-		barrier();
-
-	/*
-	 * did we time out?
-	 */
-	if (!cpus_empty(data.pending)) {
-		/*
-		 * this may be causing our panic - report it
-		 */
-		printk(KERN_CRIT
-		       "CPU%u: smp_call_function timeout for %p(%p)\n"
-		       "      callmap %lx pending %lx, %swait\n",
-		       smp_processor_id(), func, info, *cpus_addr(callmap),
-		       *cpus_addr(data.pending), wait ? "" : "no ");
-
-		/*
-		 * TRACE
-		 */
-		timeout = jiffies + (5 * HZ);
-		while (!cpus_empty(data.pending) && time_before(jiffies, timeout))
-			barrier();
-
-		if (cpus_empty(data.pending))
-			printk(KERN_CRIT "     RESOLVED\n");
-		else
-			printk(KERN_CRIT "     STILL STUCK\n");
-	}
-
-	/*
-	 * whatever happened, we're done with the data, so release it
-	 */
-	smp_call_function_data = NULL;
-	spin_unlock(&smp_call_function_lock);
-
-	if (!cpus_empty(data.pending)) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
-
-	if (wait)
-		while (!cpus_empty(data.unfinished))
-			barrier();
- out:
-
-	return 0;
-}
-
-int smp_call_function(void (*func)(void *info), void *info, int retry,
-                      int wait)
+void arch_send_call_function_ipi(cpumask_t mask)
 {
-	return smp_call_function_on_cpu(func, info, retry, wait,
-					cpu_online_map);
+	send_ipi_message(mask, IPI_CALL_FUNC);
 }
-EXPORT_SYMBOL_GPL(smp_call_function);
 
-int smp_call_function_single(int cpu, void (*func)(void *info), void *info,
-			     int retry, int wait)
+void arch_send_call_function_single_ipi(int cpu)
 {
-	/* prevent preemption and reschedule on another processor */
-	int current_cpu = get_cpu();
-	int ret = 0;
-
-	if (cpu == current_cpu) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-	} else
-		ret = smp_call_function_on_cpu(func, info, retry, wait,
-					       cpumask_of_cpu(cpu));
-
-	put_cpu();
-
-	return ret;
+	send_ipi_message(cpumask_of_cpu(cpu), IPI_CALL_FUNC_SINGLE);
 }
-EXPORT_SYMBOL_GPL(smp_call_function_single);
 
 void show_ipi_list(struct seq_file *p)
 {
@@ -521,27 +413,6 @@ asmlinkage void __exception do_local_timer(struct pt_regs *regs)
 }
 #endif
 
-/*
- * ipi_call_function - handle IPI from smp_call_function()
- *
- * Note that we copy data out of the cross-call structure and then
- * let the caller know that we're here and have done with their data
- */
-static void ipi_call_function(unsigned int cpu)
-{
-	struct smp_call_struct *data = smp_call_function_data;
-	void (*func)(void *info) = data->func;
-	void *info = data->info;
-	int wait = data->wait;
-
-	cpu_clear(cpu, data->pending);
-
-	func(info);
-
-	if (wait)
-		cpu_clear(cpu, data->unfinished);
-}
-
 static DEFINE_SPINLOCK(stop_lock);
 
 /*
@@ -611,7 +482,11 @@ asmlinkage void __exception do_IPI(struct pt_regs *regs)
 				break;
 
 			case IPI_CALL_FUNC:
-				ipi_call_function(cpu);
+				generic_smp_call_function_interrupt();
+				break;
+
+			case IPI_CALL_FUNC_SINGLE:
+				generic_smp_call_function_single_interrupt();
 				break;
 
 			case IPI_CPU_STOP:
@@ -662,14 +537,13 @@ int setup_profiling_timer(unsigned int multiplier)
 }
 
 static int
-on_each_cpu_mask(void (*func)(void *), void *info, int retry, int wait,
-		 cpumask_t mask)
+on_each_cpu_mask(void (*func)(void *), void *info, int wait, cpumask_t mask)
 {
 	int ret = 0;
 
 	preempt_disable();
 
-	ret = smp_call_function_on_cpu(func, info, retry, wait, mask);
+	ret = smp_call_function_mask(mask, func, info, wait);
 	if (cpu_isset(smp_processor_id(), mask))
 		func(info);
 
@@ -731,14 +605,14 @@ static inline void ipi_flush_tlb_kernel_range(void *arg)
 
 void flush_tlb_all(void)
 {
-	on_each_cpu(ipi_flush_tlb_all, NULL, 1, 1);
+	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
 	cpumask_t mask = mm->cpu_vm_mask;
 
-	on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, 1, mask);
+	on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mask);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
@@ -749,7 +623,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	ta.ta_vma = vma;
 	ta.ta_start = uaddr;
 
-	on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, 1, mask);
+	on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mask);
 }
 
 void flush_tlb_kernel_page(unsigned long kaddr)
@@ -758,7 +632,7 @@ void flush_tlb_kernel_page(unsigned long kaddr)
 
 	ta.ta_start = kaddr;
 
-	on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1, 1);
+	on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma,
@@ -771,7 +645,7 @@ void flush_tlb_range(struct vm_area_struct *vma,
 	ta.ta_start = start;
 	ta.ta_end = end;
 
-	on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, 1, mask);
+	on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mask);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
@@ -781,5 +655,5 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 	ta.ta_start = start;
 	ta.ta_end = end;
 
-	on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1, 1);
+	on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
 }
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index ae31deb2d06..fc650f64df4 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -36,6 +36,7 @@ EXPORT_SYMBOL(walk_stackframe);
 #ifdef CONFIG_STACKTRACE
 struct stack_trace_data {
 	struct stack_trace *trace;
+	unsigned int no_sched_functions;
 	unsigned int skip;
 };
 
@@ -43,27 +44,53 @@ static int save_trace(struct stackframe *frame, void *d)
 {
 	struct stack_trace_data *data = d;
 	struct stack_trace *trace = data->trace;
+	unsigned long addr = frame->lr;
 
+	if (data->no_sched_functions && in_sched_functions(addr))
+		return 0;
 	if (data->skip) {
 		data->skip--;
 		return 0;
 	}
 
-	trace->entries[trace->nr_entries++] = frame->lr;
+	trace->entries[trace->nr_entries++] = addr;
 
 	return trace->nr_entries >= trace->max_entries;
 }
 
-void save_stack_trace(struct stack_trace *trace)
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	struct stack_trace_data data;
 	unsigned long fp, base;
 
 	data.trace = trace;
 	data.skip = trace->skip;
-	base = (unsigned long)task_stack_page(current);
-	asm("mov %0, fp" : "=r" (fp));
+	base = (unsigned long)task_stack_page(tsk);
+
+	if (tsk != current) {
+#ifdef CONFIG_SMP
+		/*
+		 * What guarantees do we have here that 'tsk'
+		 * is not running on another CPU?
+		 */
+		BUG();
+#else
+		data.no_sched_functions = 1;
+		fp = thread_saved_fp(tsk);
+#endif
+	} else {
+		data.no_sched_functions = 0;
+		asm("mov %0, fp" : "=r" (fp));
+	}
 
 	walk_stackframe(fp, base, base + THREAD_SIZE, save_trace, &data);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	save_stack_trace_tsk(current, trace);
 }
+EXPORT_SYMBOL_GPL(save_stack_trace);
 #endif
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index 0128687ba0f..b3ec641b5cf 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -27,8 +27,7 @@
 #include <linux/file.h>
 #include <linux/utsname.h>
 #include <linux/ipc.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern unsigned long do_mremap(unsigned long addr, unsigned long old_len,
 			       unsigned long new_len, unsigned long flags,
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 96ab5f52949..42623db7f87 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -82,7 +82,7 @@
 #include <linux/socket.h>
 #include <linux/net.h>
 #include <linux/ipc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 struct oldabi_stat64 {
 	unsigned long long st_dev;
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index b5867eca1d0..c68b44aa88d 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -59,7 +59,7 @@ unsigned long profile_pc(struct pt_regs *regs)
 
 	if (in_lock_functions(pc)) {
 		fp = regs->ARM_fp;
-		pc = pc_pointer(((unsigned long *)fp)[-1]);
+		pc = ((unsigned long *)fp)[-1];
 	}
 
 	return pc;
@@ -130,7 +130,9 @@ static const struct leds_evt_name evt_names[] = {
 	{ "red",   led_red_on,   led_red_off   },
 };
 
-static ssize_t leds_store(struct sys_device *dev, const char *buf, size_t size)
+static ssize_t leds_store(struct sys_device *dev,
+			struct sysdev_attribute *attr,
+			const char *buf, size_t size)
 {
 	int ret = -EINVAL, len = strcspn(buf, " ");
 
@@ -365,108 +367,6 @@ static struct sysdev_class timer_sysclass = {
 	.resume		= timer_resume,
 };
 
-#ifdef CONFIG_NO_IDLE_HZ
-static int timer_dyn_tick_enable(void)
-{
-	struct dyn_tick_timer *dyn_tick = system_timer->dyn_tick;
-	unsigned long flags;
-	int ret = -ENODEV;
-
-	if (dyn_tick) {
-		spin_lock_irqsave(&dyn_tick->lock, flags);
-		ret = 0;
-		if (!(dyn_tick->state & DYN_TICK_ENABLED)) {
-			ret = dyn_tick->enable();
-
-			if (ret == 0)
-				dyn_tick->state |= DYN_TICK_ENABLED;
-		}
-		spin_unlock_irqrestore(&dyn_tick->lock, flags);
-	}
-
-	return ret;
-}
-
-static int timer_dyn_tick_disable(void)
-{
-	struct dyn_tick_timer *dyn_tick = system_timer->dyn_tick;
-	unsigned long flags;
-	int ret = -ENODEV;
-
-	if (dyn_tick) {
-		spin_lock_irqsave(&dyn_tick->lock, flags);
-		ret = 0;
-		if (dyn_tick->state & DYN_TICK_ENABLED) {
-			ret = dyn_tick->disable();
-
-			if (ret == 0)
-				dyn_tick->state &= ~DYN_TICK_ENABLED;
-		}
-		spin_unlock_irqrestore(&dyn_tick->lock, flags);
-	}
-
-	return ret;
-}
-
-/*
- * Reprogram the system timer for at least the calculated time interval.
- * This function should be called from the idle thread with IRQs disabled,
- * immediately before sleeping.
- */
-void timer_dyn_reprogram(void)
-{
-	struct dyn_tick_timer *dyn_tick = system_timer->dyn_tick;
-	unsigned long next, seq, flags;
-
-	if (!dyn_tick)
-		return;
-
-	spin_lock_irqsave(&dyn_tick->lock, flags);
-	if (dyn_tick->state & DYN_TICK_ENABLED) {
-		next = next_timer_interrupt();
-		do {
-			seq = read_seqbegin(&xtime_lock);
-			dyn_tick->reprogram(next - jiffies);
-		} while (read_seqretry(&xtime_lock, seq));
-	}
-	spin_unlock_irqrestore(&dyn_tick->lock, flags);
-}
-
-static ssize_t timer_show_dyn_tick(struct sys_device *dev, char *buf)
-{
-	return sprintf(buf, "%i\n",
-		       (system_timer->dyn_tick->state & DYN_TICK_ENABLED) >> 1);
-}
-
-static ssize_t timer_set_dyn_tick(struct sys_device *dev, const char *buf,
-				  size_t count)
-{
-	unsigned int enable = simple_strtoul(buf, NULL, 2);
-
-	if (enable)
-		timer_dyn_tick_enable();
-	else
-		timer_dyn_tick_disable();
-
-	return count;
-}
-static SYSDEV_ATTR(dyn_tick, 0644, timer_show_dyn_tick, timer_set_dyn_tick);
-
-/*
- * dyntick=enable|disable
- */
-static char dyntick_str[4] __initdata = "";
-
-static int __init dyntick_setup(char *str)
-{
-	if (str)
-		strlcpy(dyntick_str, str, sizeof(dyntick_str));
-	return 1;
-}
-
-__setup("dyntick=", dyntick_setup);
-#endif
-
 static int __init timer_init_sysfs(void)
 {
 	int ret = sysdev_class_register(&timer_sysclass);
@@ -475,19 +375,6 @@ static int __init timer_init_sysfs(void)
 		ret = sysdev_register(&system_timer->dev);
 	}
 
-#ifdef CONFIG_NO_IDLE_HZ
-	if (ret == 0 && system_timer->dyn_tick) {
-		ret = sysdev_create_file(&system_timer->dev, &attr_dyn_tick);
-
-		/*
-		 * Turn on dynamic tick after calibrate delay
-		 * for correct bogomips
-		 */
-		if (ret == 0 && dyntick_str[0] == 'e')
-			ret = timer_dyn_tick_enable();
-	}
-#endif
-
 	return ret;
 }
 
@@ -500,10 +387,5 @@ void __init time_init(void)
 		system_timer->offset = dummy_gettimeoffset;
 #endif
 	system_timer->init();
-
-#ifdef CONFIG_NO_IDLE_HZ
-	if (system_timer->dyn_tick)
-		spin_lock_init(&system_timer->dyn_tick->lock);
-#endif
 }
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 5595fdd75e8..57e6874d0b8 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -19,15 +19,13 @@
 #include <linux/kallsyms.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/kprobes.h>
+#include <linux/uaccess.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/system.h>
-#include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>
-#include <asm/io.h>
 
 #include "ptrace.h"
 #include "signal.h"
@@ -69,7 +67,8 @@ void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long
  */
 static int verify_stack(unsigned long sp)
 {
-	if (sp < PAGE_OFFSET || (sp > (unsigned long)high_memory && high_memory != 0))
+	if (sp < PAGE_OFFSET ||
+	    (sp > (unsigned long)high_memory && high_memory != NULL))
 		return -EFAULT;
 
 	return 0;
@@ -288,14 +287,28 @@ void unregister_undef_hook(struct undef_hook *hook)
 	spin_unlock_irqrestore(&undef_lock, flags);
 }
 
+static int call_undef_hook(struct pt_regs *regs, unsigned int instr)
+{
+	struct undef_hook *hook;
+	unsigned long flags;
+	int (*fn)(struct pt_regs *regs, unsigned int instr) = NULL;
+
+	spin_lock_irqsave(&undef_lock, flags);
+	list_for_each_entry(hook, &undef_hook, node)
+		if ((instr & hook->instr_mask) == hook->instr_val &&
+		    (regs->ARM_cpsr & hook->cpsr_mask) == hook->cpsr_val)
+			fn = hook->fn;
+	spin_unlock_irqrestore(&undef_lock, flags);
+
+	return fn ? fn(regs, instr) : 1;
+}
+
 asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 {
 	unsigned int correction = thumb_mode(regs) ? 2 : 4;
 	unsigned int instr;
-	struct undef_hook *hook;
 	siginfo_t info;
 	void __user *pc;
-	unsigned long flags;
 
 	/*
 	 * According to the ARM ARM, PC is 2 or 4 bytes ahead,
@@ -314,28 +327,8 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 		get_user(instr, (u32 __user *)pc);
 	}
 
-#ifdef CONFIG_KPROBES
-	/*
-	 * It is possible to have recursive kprobes, so we can't call
-	 * the kprobe trap handler with the undef_lock held.
-	 */
-	if (instr == KPROBE_BREAKPOINT_INSTRUCTION && !user_mode(regs)) {
-		kprobe_trap_handler(regs, instr);
+	if (call_undef_hook(regs, instr) == 0)
 		return;
-	}
-#endif
-
-	spin_lock_irqsave(&undef_lock, flags);
-	list_for_each_entry(hook, &undef_hook, node) {
-		if ((instr & hook->instr_mask) == hook->instr_val &&
-		    (regs->ARM_cpsr & hook->cpsr_mask) == hook->cpsr_val) {
-			if (hook->fn(regs, instr) == 0) {
-				spin_unlock_irqrestore(&undef_lock, flags);
-				return;
-			}
-		}
-	}
-	spin_unlock_irqrestore(&undef_lock, flags);
 
 #ifdef CONFIG_DEBUG_USER
 	if (user_debug & UDBG_UNDEFINED) {
@@ -708,6 +701,11 @@ EXPORT_SYMBOL(abort);
 
 void __init trap_init(void)
 {
+	return;
+}
+
+void __init early_trap_init(void)
+{
 	unsigned long vectors = CONFIG_VECTORS_BASE;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
diff --git a/arch/arm/kernel/xscale-cp0.c b/arch/arm/kernel/xscale-cp0.c
index 180000bfdc8..17127db906f 100644
--- a/arch/arm/kernel/xscale-cp0.c
+++ b/arch/arm/kernel/xscale-cp0.c
@@ -14,8 +14,8 @@
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <asm/thread_notify.h>
-#include <asm/io.h>
 
 static inline void dsp_save_state(u32 *state)
 {