Linux-2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

49 files changed, 5136 insertions, 0 deletions

diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
new file mode 100644
index 00000000000..c0e65833ffc
--- /dev/null
+++ b/arch/arm/lib/Makefile
@@ -0,0 +1,29 @@
+#
+# linux/arch/arm/lib/Makefile
+#
+# Copyright (C) 1995-2000 Russell King
+#
+
+lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
+		   csumpartialcopy.o csumpartialcopyuser.o clearbit.o \
+		   copy_page.o delay.o findbit.o memchr.o memcpy.o    \
+		   memset.o memzero.o setbit.o strncpy_from_user.o    \
+		   strnlen_user.o strchr.o strrchr.o testchangebit.o  \
+		   testclearbit.o testsetbit.o uaccess.o getuser.o    \
+		   putuser.o ashldi3.o ashrdi3.o lshrdi3.o muldi3.o   \
+		   ucmpdi2.o udivdi3.o lib1funcs.o div64.o	      \
+		   io-readsb.o io-writesb.o io-readsl.o io-writesl.o
+
+ifeq ($(CONFIG_CPU_32v3),y)
+  lib-y	+= io-readsw-armv3.o io-writesw-armv3.o
+else
+  lib-y	+= io-readsw-armv4.o io-writesw-armv4.o
+endif
+
+lib-$(CONFIG_ARCH_RPC)		+= ecard.o io-acorn.o floppydma.o
+lib-$(CONFIG_ARCH_CLPS7500)	+= io-acorn.o
+lib-$(CONFIG_ARCH_L7200)	+= io-acorn.o
+lib-$(CONFIG_ARCH_SHARK)	+= io-shark.o
+
+$(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
+$(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
diff --git a/arch/arm/lib/ashldi3.c b/arch/arm/lib/ashldi3.c
new file mode 100644
index 00000000000..130f5a83966
--- /dev/null
+++ b/arch/arm/lib/ashldi3.c
@@ -0,0 +1,61 @@
+/* More subroutines needed by GCC output code on some machines.  */
+/* Compile this one with gcc.  */
+/* Copyright (C) 1989, 92-98, 1999 Free Software Foundation, Inc.
+
+This file is part of GNU CC.
+
+GNU CC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 2, or (at your option)
+any later version.
+
+GNU CC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with GNU CC; see the file COPYING.  If not, write to
+the Free Software Foundation, 59 Temple Place - Suite 330,
+Boston, MA 02111-1307, USA.  */
+
+/* As a special exception, if you link this library with other files,
+   some of which are compiled with GCC, to produce an executable,
+   this library does not by itself cause the resulting executable
+   to be covered by the GNU General Public License.
+   This exception does not however invalidate any other reasons why
+   the executable file might be covered by the GNU General Public License.
+ */
+/* support functions required by the kernel. based on code from gcc-2.95.3 */
+/* I Molton	29/07/01 */
+
+#include "gcclib.h"
+
+DItype
+__ashldi3 (DItype u, word_type b)
+{
+  DIunion w;
+  word_type bm;
+  DIunion uu;
+
+  if (b == 0)
+    return u;
+
+  uu.ll = u;
+
+  bm = (sizeof (SItype) * BITS_PER_UNIT) - b;
+  if (bm <= 0)
+    {
+      w.s.low = 0;
+      w.s.high = (USItype)uu.s.low << -bm;
+    }
+  else
+    {
+      USItype carries = (USItype)uu.s.low >> bm;
+      w.s.low = (USItype)uu.s.low << b;
+      w.s.high = ((USItype)uu.s.high << b) | carries;
+    }
+
+  return w.ll;
+}
+
diff --git a/arch/arm/lib/ashrdi3.c b/arch/arm/lib/ashrdi3.c
new file mode 100644
index 00000000000..71625d218f8
--- /dev/null
+++ b/arch/arm/lib/ashrdi3.c
@@ -0,0 +1,61 @@
+/* More subroutines needed by GCC output code on some machines.  */
+/* Compile this one with gcc.  */
+/* Copyright (C) 1989, 92-98, 1999 Free Software Foundation, Inc.
+
+This file is part of GNU CC.
+
+GNU CC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 2, or (at your option)
+any later version.
+
+GNU CC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with GNU CC; see the file COPYING.  If not, write to
+the Free Software Foundation, 59 Temple Place - Suite 330,
+Boston, MA 02111-1307, USA.  */
+
+/* As a special exception, if you link this library with other files,
+   some of which are compiled with GCC, to produce an executable,
+   this library does not by itself cause the resulting executable
+   to be covered by the GNU General Public License.
+   This exception does not however invalidate any other reasons why
+   the executable file might be covered by the GNU General Public License.
+ */
+/* support functions required by the kernel. based on code from gcc-2.95.3 */
+/* I Molton     29/07/01 */
+
+#include "gcclib.h"
+
+DItype
+__ashrdi3 (DItype u, word_type b)
+{
+  DIunion w;
+  word_type bm;
+  DIunion uu;
+
+  if (b == 0)
+    return u;
+
+  uu.ll = u;
+
+  bm = (sizeof (SItype) * BITS_PER_UNIT) - b;
+  if (bm <= 0)
+    {
+      /* w.s.high = 1..1 or 0..0 */
+      w.s.high = uu.s.high >> (sizeof (SItype) * BITS_PER_UNIT - 1);
+      w.s.low = uu.s.high >> -bm;
+    }
+  else
+    {
+      USItype carries = (USItype)uu.s.high << bm;
+      w.s.high = uu.s.high >> b;
+      w.s.low = ((USItype)uu.s.low >> b) | carries;
+    }
+
+  return w.ll;
+}
diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S
new file mode 100644
index 00000000000..68a21c0f3f5
--- /dev/null
+++ b/arch/arm/lib/backtrace.S
@@ -0,0 +1,157 @@
+/*
+ *  linux/arch/arm/lib/backtrace.S
+ *
+ *  Copyright (C) 1995, 1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 27/03/03 Ian Molton Clean up CONFIG_CPU
+ *
+ */
+#include <linux/config.h>
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+		.text
+
+@ fp is 0 or stack frame
+
+#define frame	r4
+#define next	r5
+#define save	r6
+#define mask	r7
+#define offset	r8
+
+ENTRY(__backtrace)
+		mov	r1, #0x10
+		mov	r0, fp
+
+ENTRY(c_backtrace)
+
+#ifndef CONFIG_FRAME_POINTER
+		mov	pc, lr
+#else
+
+		stmfd	sp!, {r4 - r8, lr}	@ Save an extra register so we have a location...
+		tst	r1, #0x10		@ 26 or 32-bit?
+		moveq	mask, #0xfc000003
+		movne	mask, #0
+		tst	mask, r0
+		movne	r0, #0
+		movs	frame, r0
+1:		moveq	r0, #-2
+		LOADREGS(eqfd, sp!, {r4 - r8, pc})
+
+2:		stmfd	sp!, {pc}		@ calculate offset of PC in STMIA instruction
+		ldr	r0, [sp], #4
+		adr	r1, 2b - 4
+		sub	offset, r0, r1
+
+3:		tst	frame, mask		@ Check for address exceptions...
+		bne	1b
+
+1001:		ldr	next, [frame, #-12]	@ get fp
+1002:		ldr	r2, [frame, #-4]	@ get lr
+1003:		ldr	r3, [frame, #0]		@ get pc
+		sub	save, r3, offset	@ Correct PC for prefetching
+		bic	save, save, mask
+1004:		ldr	r1, [save, #0]		@ get instruction at function
+		mov	r1, r1, lsr #10
+		ldr	r3, .Ldsi+4
+		teq	r1, r3
+		subeq	save, save, #4
+		mov	r0, save
+		bic	r1, r2, mask
+		bl	dump_backtrace_entry
+
+		ldr	r0, [frame, #-8]	@ get sp
+		sub	r0, r0, #4
+1005:		ldr	r1, [save, #4]		@ get instruction at function+4
+		mov	r3, r1, lsr #10
+		ldr	r2, .Ldsi+4
+		teq	r3, r2			@ Check for stmia sp!, {args}
+		addeq	save, save, #4		@ next instruction
+		bleq	.Ldumpstm
+
+		sub	r0, frame, #16
+1006:		ldr	r1, [save, #4]		@ Get 'stmia sp!, {rlist, fp, ip, lr, pc}' instruction
+		mov	r3, r1, lsr #10
+		ldr	r2, .Ldsi
+		teq	r3, r2
+		bleq	.Ldumpstm
+
+		/*
+		 * A zero next framepointer means we're done.
+		 */
+		teq	next, #0
+		LOADREGS(eqfd, sp!, {r4 - r8, pc})
+
+		/*
+		 * The next framepointer must be above the
+		 * current framepointer.
+		 */
+		cmp	next, frame
+		mov	frame, next
+		bhi	3b
+		b	1007f
+
+/*
+ * Fixup for LDMDB
+ */
+		.section .fixup,"ax"
+		.align	0
+1007:		ldr	r0, =.Lbad
+		mov	r1, frame
+		bl	printk
+		LOADREGS(fd, sp!, {r4 - r8, pc})
+		.ltorg
+		.previous
+		
+		.section __ex_table,"a"
+		.align	3
+		.long	1001b, 1007b
+		.long	1002b, 1007b
+		.long	1003b, 1007b
+		.long	1004b, 1007b
+		.long	1005b, 1007b
+		.long	1006b, 1007b
+		.previous
+
+#define instr r4
+#define reg   r5
+#define stack r6
+
+.Ldumpstm:	stmfd	sp!, {instr, reg, stack, r7, lr}
+		mov	stack, r0
+		mov	instr, r1
+		mov	reg, #9
+		mov	r7, #0
+1:		mov	r3, #1
+		tst	instr, r3, lsl reg
+		beq	2f
+		add	r7, r7, #1
+		teq	r7, #4
+		moveq	r7, #0
+		moveq	r3, #'\n'
+		movne	r3, #' '
+		ldr	r2, [stack], #-4
+		mov	r1, reg
+		adr	r0, .Lfp
+		bl	printk
+2:		subs	reg, reg, #1
+		bpl	1b
+		teq	r7, #0
+		adrne	r0, .Lcr
+		blne	printk
+		mov	r0, stack
+		LOADREGS(fd, sp!, {instr, reg, stack, r7, pc})
+
+.Lfp:		.asciz	" r%d = %08X%c"
+.Lcr:		.asciz	"\n"
+.Lbad:		.asciz	"Backtrace aborted due to bad frame pointer <%p>\n"
+		.align
+.Ldsi:		.word	0x00e92dd8 >> 2
+		.word	0x00e92d00 >> 2
+
+#endif
diff --git a/arch/arm/lib/changebit.S b/arch/arm/lib/changebit.S
new file mode 100644
index 00000000000..3af45cab70e
--- /dev/null
+++ b/arch/arm/lib/changebit.S
@@ -0,0 +1,28 @@
+/*
+ *  linux/arch/arm/lib/changebit.S
+ *
+ *  Copyright (C) 1995-1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+                .text
+
+/* Purpose  : Function to change a bit
+ * Prototype: int change_bit(int bit, void *addr)
+ */
+ENTRY(_change_bit_be)
+		eor	r0, r0, #0x18		@ big endian byte ordering
+ENTRY(_change_bit_le)
+		and	r2, r0, #7
+		mov	r3, #1
+		mov	r3, r3, lsl r2
+		save_and_disable_irqs ip, r2
+		ldrb	r2, [r1, r0, lsr #3]
+		eor	r2, r2, r3
+		strb	r2, [r1, r0, lsr #3]
+		restore_irqs ip
+		RETINSTR(mov,pc,lr)
diff --git a/arch/arm/lib/clearbit.S b/arch/arm/lib/clearbit.S
new file mode 100644
index 00000000000..069a2ce413f
--- /dev/null
+++ b/arch/arm/lib/clearbit.S
@@ -0,0 +1,31 @@
+/*
+ *  linux/arch/arm/lib/clearbit.S
+ *
+ *  Copyright (C) 1995-1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+                .text
+
+/*
+ * Purpose  : Function to clear a bit
+ * Prototype: int clear_bit(int bit, void *addr)
+ */
+ENTRY(_clear_bit_be)
+		eor	r0, r0, #0x18		@ big endian byte ordering
+ENTRY(_clear_bit_le)
+		and	r2, r0, #7
+		mov	r3, #1
+		mov	r3, r3, lsl r2
+		save_and_disable_irqs ip, r2
+		ldrb	r2, [r1, r0, lsr #3]
+		bic	r2, r2, r3
+		strb	r2, [r1, r0, lsr #3]
+		restore_irqs ip
+		RETINSTR(mov,pc,lr)
+
+
diff --git a/arch/arm/lib/copy_page.S b/arch/arm/lib/copy_page.S
new file mode 100644
index 00000000000..4c38abdbe49
--- /dev/null
+++ b/arch/arm/lib/copy_page.S
@@ -0,0 +1,46 @@
+/*
+ *  linux/arch/arm/lib/copypage.S
+ *
+ *  Copyright (C) 1995-1999 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  ASM optimised string functions
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/constants.h>
+
+#define COPY_COUNT (PAGE_SZ/64 PLD( -1 ))
+
+		.text
+		.align	5
+/*
+ * StrongARM optimised copy_page routine
+ * now 1.78bytes/cycle, was 1.60 bytes/cycle (50MHz bus -> 89MB/s)
+ * Note that we probably achieve closer to the 100MB/s target with
+ * the core clock switching.
+ */
+ENTRY(copy_page)
+		stmfd	sp!, {r4, lr}			@	2
+	PLD(	pld	[r1, #0]		)
+	PLD(	pld	[r1, #32]		)
+		mov	r2, #COPY_COUNT			@	1
+		ldmia	r1!, {r3, r4, ip, lr}		@	4+1
+1:	PLD(	pld	[r1, #64]		)
+	PLD(	pld	[r1, #96]		)
+2:		stmia	r0!, {r3, r4, ip, lr}		@	4
+		ldmia	r1!, {r3, r4, ip, lr}		@	4+1
+		stmia	r0!, {r3, r4, ip, lr}		@	4
+		ldmia	r1!, {r3, r4, ip, lr}		@	4+1
+		stmia	r0!, {r3, r4, ip, lr}		@	4
+		ldmia	r1!, {r3, r4, ip, lr}		@	4
+		subs	r2, r2, #1			@	1
+		stmia	r0!, {r3, r4, ip, lr}		@	4
+		ldmgtia	r1!, {r3, r4, ip, lr}		@	4
+		bgt	1b				@	1
+	PLD(	ldmeqia r1!, {r3, r4, ip, lr}	)
+	PLD(	beq	2b			)
+		LOADREGS(fd, sp!, {r4, pc})		@	3
diff --git a/arch/arm/lib/csumipv6.S b/arch/arm/lib/csumipv6.S
new file mode 100644
index 00000000000..7065a20ee8a
--- /dev/null
+++ b/arch/arm/lib/csumipv6.S
@@ -0,0 +1,32 @@
+/*
+ *  linux/arch/arm/lib/csumipv6.S
+ *
+ *  Copyright (C) 1995-1998 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.text
+
+ENTRY(__csum_ipv6_magic)
+		str	lr, [sp, #-4]!
+		adds	ip, r2, r3
+		ldmia	r1, {r1 - r3, lr}
+		adcs	ip, ip, r1
+		adcs	ip, ip, r2
+		adcs	ip, ip, r3
+		adcs	ip, ip, lr
+		ldmia	r0, {r0 - r3}
+		adcs	r0, ip, r0
+		adcs	r0, r0, r1
+		adcs	r0, r0, r2
+		ldr	r2, [sp, #4]
+		adcs	r0, r0, r3
+		adcs	r0, r0, r2
+		adcs	r0, r0, #0
+		LOADREGS(fd, sp!, {pc})
+
diff --git a/arch/arm/lib/csumpartial.S b/arch/arm/lib/csumpartial.S
new file mode 100644
index 00000000000..cb5e3708f11
--- /dev/null
+++ b/arch/arm/lib/csumpartial.S
@@ -0,0 +1,137 @@
+/*
+ *  linux/arch/arm/lib/csumpartial.S
+ *
+ *  Copyright (C) 1995-1998 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.text
+
+/*
+ * Function: __u32 csum_partial(const char *src, int len, __u32 sum)
+ * Params  : r0 = buffer, r1 = len, r2 = checksum
+ * Returns : r0 = new checksum
+ */
+
+buf	.req	r0
+len	.req	r1
+sum	.req	r2
+td0	.req	r3
+td1	.req	r4	@ save before use
+td2	.req	r5	@ save before use
+td3	.req	lr
+
+.zero:		mov	r0, sum
+		add	sp, sp, #4
+		ldr	pc, [sp], #4
+
+		/*
+		 * Handle 0 to 7 bytes, with any alignment of source and
+		 * destination pointers.  Note that when we get here, C = 0
+		 */
+.less8:		teq	len, #0			@ check for zero count
+		beq	.zero
+
+		/* we must have at least one byte. */
+		tst	buf, #1			@ odd address?
+		ldrneb	td0, [buf], #1
+		subne	len, len, #1
+		adcnes	sum, sum, td0, put_byte_1
+
+.less4:		tst	len, #6
+		beq	.less8_byte
+
+		/* we are now half-word aligned */
+
+.less8_wordlp:
+#if __LINUX_ARM_ARCH__ >= 4
+		ldrh	td0, [buf], #2
+		sub	len, len, #2
+#else
+		ldrb	td0, [buf], #1
+		ldrb	td3, [buf], #1
+		sub	len, len, #2
+#ifndef __ARMEB__
+		orr	td0, td0, td3, lsl #8
+#else
+		orr	td0, td3, td0, lsl #8
+#endif
+#endif
+		adcs	sum, sum, td0
+		tst	len, #6
+		bne	.less8_wordlp
+
+.less8_byte:	tst	len, #1			@ odd number of bytes
+		ldrneb	td0, [buf], #1		@ include last byte
+		adcnes	sum, sum, td0, put_byte_0	@ update checksum
+
+.done:		adc	r0, sum, #0		@ collect up the last carry
+		ldr	td0, [sp], #4
+		tst	td0, #1			@ check buffer alignment
+		movne	r0, r0, ror #8		@ rotate checksum by 8 bits
+		ldr	pc, [sp], #4		@ return
+
+.not_aligned:	tst	buf, #1			@ odd address
+		ldrneb	td0, [buf], #1		@ make even
+		subne	len, len, #1
+		adcnes	sum, sum, td0, put_byte_1	@ update checksum
+
+		tst	buf, #2			@ 32-bit aligned?
+#if __LINUX_ARM_ARCH__ >= 4
+		ldrneh	td0, [buf], #2		@ make 32-bit aligned
+		subne	len, len, #2
+#else
+		ldrneb	td0, [buf], #1
+		ldrneb	ip, [buf], #1
+		subne	len, len, #2
+#ifndef __ARMEB__
+		orrne	td0, td0, ip, lsl #8
+#else
+		orrne	td0, ip, td0, lsl #8
+#endif
+#endif
+		adcnes	sum, sum, td0		@ update checksum
+		mov	pc, lr
+
+ENTRY(csum_partial)
+		stmfd	sp!, {buf, lr}
+		cmp	len, #8			@ Ensure that we have at least
+		blo	.less8			@ 8 bytes to copy.
+
+		adds	sum, sum, #0		@ C = 0
+		tst	buf, #3			@ Test destination alignment
+		blne	.not_aligned		@ aligh destination, return here
+
+1:		bics	ip, len, #31
+		beq	3f
+
+		stmfd	sp!, {r4 - r5}
+2:		ldmia	buf!, {td0, td1, td2, td3}
+		adcs	sum, sum, td0
+		adcs	sum, sum, td1
+		adcs	sum, sum, td2
+		adcs	sum, sum, td3
+		ldmia	buf!, {td0, td1, td2, td3}
+		adcs	sum, sum, td0
+		adcs	sum, sum, td1
+		adcs	sum, sum, td2
+		adcs	sum, sum, td3
+		sub	ip, ip, #32
+		teq	ip, #0
+		bne	2b
+		ldmfd	sp!, {r4 - r5}
+
+3:		tst	len, #0x1c		@ should not change C
+		beq	.less4
+
+4:		ldr	td0, [buf], #4
+		sub	len, len, #4
+		adcs	sum, sum, td0
+		tst	len, #0x1c
+		bne	4b
+		b	.less4
diff --git a/arch/arm/lib/csumpartialcopy.S b/arch/arm/lib/csumpartialcopy.S
new file mode 100644
index 00000000000..990ee63b246
--- /dev/null
+++ b/arch/arm/lib/csumpartialcopy.S
@@ -0,0 +1,52 @@
+/*
+ *  linux/arch/arm/lib/csumpartialcopy.S
+ *
+ *  Copyright (C) 1995-1998 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.text
+
+/* Function: __u32 csum_partial_copy_nocheck(const char *src, char *dst, int len, __u32 sum)
+ * Params  : r0 = src, r1 = dst, r2 = len, r3 = checksum
+ * Returns : r0 = new checksum
+ */
+
+		.macro	save_regs
+		stmfd	sp!, {r1, r4 - r8, fp, ip, lr, pc}
+		.endm
+
+		.macro	load_regs,flags
+		LOADREGS(\flags,fp,{r1, r4 - r8, fp, sp, pc})
+		.endm
+
+		.macro	load1b, reg1
+		ldrb	\reg1, [r0], #1
+		.endm
+
+		.macro	load2b, reg1, reg2
+		ldrb	\reg1, [r0], #1
+		ldrb	\reg2, [r0], #1
+		.endm
+
+		.macro	load1l, reg1
+		ldr	\reg1, [r0], #4
+		.endm
+
+		.macro	load2l, reg1, reg2
+		ldr	\reg1, [r0], #4
+		ldr	\reg2, [r0], #4
+		.endm
+
+		.macro	load4l, reg1, reg2, reg3, reg4
+		ldmia	r0!, {\reg1, \reg2, \reg3, \reg4}
+		.endm
+
+#define FN_ENTRY	ENTRY(csum_partial_copy_nocheck)
+
+#include "csumpartialcopygeneric.S"
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
new file mode 100644
index 00000000000..d3a2f4667db
--- /dev/null
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -0,0 +1,331 @@
+/*
+ *  linux/arch/arm/lib/csumpartialcopygeneric.S
+ *
+ *  Copyright (C) 1995-2001 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * unsigned int
+ * csum_partial_copy_xxx(const char *src, char *dst, int len, int sum, )
+ *  r0 = src, r1 = dst, r2 = len, r3 = sum
+ *  Returns : r0 = checksum
+ *
+ * Note that 'tst' and 'teq' preserve the carry flag.
+ */
+
+src	.req	r0
+dst	.req	r1
+len	.req	r2
+sum	.req	r3
+
+.zero:		mov	r0, sum
+		load_regs	ea
+
+		/*
+		 * Align an unaligned destination pointer.  We know that
+		 * we have >= 8 bytes here, so we don't need to check
+		 * the length.  Note that the source pointer hasn't been
+		 * aligned yet.
+		 */
+.dst_unaligned:	tst	dst, #1
+		beq	.dst_16bit
+
+		load1b	ip
+		sub	len, len, #1
+		adcs	sum, sum, ip, put_byte_1	@ update checksum
+		strb	ip, [dst], #1
+		tst	dst, #2
+		moveq	pc, lr			@ dst is now 32bit aligned
+
+.dst_16bit:	load2b	r8, ip
+		sub	len, len, #2
+		adcs	sum, sum, r8, put_byte_0
+		strb	r8, [dst], #1
+		adcs	sum, sum, ip, put_byte_1
+		strb	ip, [dst], #1
+		mov	pc, lr			@ dst is now 32bit aligned
+
+		/*
+		 * Handle 0 to 7 bytes, with any alignment of source and
+		 * destination pointers.  Note that when we get here, C = 0
+		 */
+.less8:		teq	len, #0			@ check for zero count
+		beq	.zero
+
+		/* we must have at least one byte. */
+		tst	dst, #1			@ dst 16-bit aligned
+		beq	.less8_aligned
+
+		/* Align dst */
+		load1b	ip
+		sub	len, len, #1
+		adcs	sum, sum, ip, put_byte_1	@ update checksum
+		strb	ip, [dst], #1
+		tst	len, #6
+		beq	.less8_byteonly
+
+1:		load2b	r8, ip
+		sub	len, len, #2
+		adcs	sum, sum, r8, put_byte_0
+		strb	r8, [dst], #1
+		adcs	sum, sum, ip, put_byte_1
+		strb	ip, [dst], #1
+.less8_aligned:	tst	len, #6
+		bne	1b
+.less8_byteonly:
+		tst	len, #1
+		beq	.done
+		load1b	r8
+		adcs	sum, sum, r8, put_byte_0	@ update checksum
+		strb	r8, [dst], #1
+		b	.done
+
+FN_ENTRY
+		mov	ip, sp
+		save_regs
+		sub	fp, ip, #4
+
+		cmp	len, #8			@ Ensure that we have at least
+		blo	.less8			@ 8 bytes to copy.
+
+		adds	sum, sum, #0		@ C = 0
+		tst	dst, #3			@ Test destination alignment
+		blne	.dst_unaligned		@ align destination, return here
+
+		/*
+		 * Ok, the dst pointer is now 32bit aligned, and we know
+		 * that we must have more than 4 bytes to copy.  Note
+		 * that C contains the carry from the dst alignment above.
+		 */
+
+		tst	src, #3			@ Test source alignment
+		bne	.src_not_aligned
+
+		/* Routine for src & dst aligned */
+
+		bics	ip, len, #15
+		beq	2f
+
+1:		load4l	r4, r5, r6, r7
+		stmia	dst!, {r4, r5, r6, r7}
+		adcs	sum, sum, r4
+		adcs	sum, sum, r5
+		adcs	sum, sum, r6
+		adcs	sum, sum, r7
+		sub	ip, ip, #16
+		teq	ip, #0
+		bne	1b
+
+2:		ands	ip, len, #12
+		beq	4f
+		tst	ip, #8
+		beq	3f
+		load2l	r4, r5
+		stmia	dst!, {r4, r5}
+		adcs	sum, sum, r4
+		adcs	sum, sum, r5
+		tst	ip, #4
+		beq	4f
+
+3:		load1l	r4
+		str	r4, [dst], #4
+		adcs	sum, sum, r4
+
+4:		ands	len, len, #3
+		beq	.done
+		load1l	r4
+		tst	len, #2
+		mov	r5, r4, get_byte_0
+		beq	.exit
+		adcs	sum, sum, r4, push #16
+		strb	r5, [dst], #1
+		mov	r5, r4, get_byte_1
+		strb	r5, [dst], #1
+		mov	r5, r4, get_byte_2
+.exit:		tst	len, #1
+		strneb	r5, [dst], #1
+		andne	r5, r5, #255
+		adcnes	sum, sum, r5, put_byte_0
+
+		/*
+		 * If the dst pointer was not 16-bit aligned, we
+		 * need to rotate the checksum here to get around
+		 * the inefficient byte manipulations in the
+		 * architecture independent code.
+		 */
+.done:		adc	r0, sum, #0
+		ldr	sum, [sp, #0]		@ dst
+		tst	sum, #1
+		movne	r0, r0, ror #8
+		load_regs	ea
+
+.src_not_aligned:
+		adc	sum, sum, #0		@ include C from dst alignment
+		and	ip, src, #3
+		bic	src, src, #3
+		load1l	r5
+		cmp	ip, #2
+		beq	.src2_aligned
+		bhi	.src3_aligned
+		mov	r4, r5, pull #8		@ C = 0
+		bics	ip, len, #15
+		beq	2f
+1:		load4l	r5, r6, r7, r8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		mov	r7, r7, pull #8
+		orr	r7, r7, r8, push #24
+		stmia	dst!, {r4, r5, r6, r7}
+		adcs	sum, sum, r4
+		adcs	sum, sum, r5
+		adcs	sum, sum, r6
+		adcs	sum, sum, r7
+		mov	r4, r8, pull #8
+		sub	ip, ip, #16
+		teq	ip, #0
+		bne	1b
+2:		ands	ip, len, #12
+		beq	4f
+		tst	ip, #8
+		beq	3f
+		load2l	r5, r6
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		stmia	dst!, {r4, r5}
+		adcs	sum, sum, r4
+		adcs	sum, sum, r5
+		mov	r4, r6, pull #8
+		tst	ip, #4
+		beq	4f
+3:		load1l	r5
+		orr	r4, r4, r5, push #24
+		str	r4, [dst], #4
+		adcs	sum, sum, r4
+		mov	r4, r5, pull #8
+4:		ands	len, len, #3
+		beq	.done
+		mov	r5, r4, get_byte_0
+		tst	len, #2
+		beq	.exit
+		adcs	sum, sum, r4, push #16
+		strb	r5, [dst], #1
+		mov	r5, r4, get_byte_1
+		strb	r5, [dst], #1
+		mov	r5, r4, get_byte_2
+		b	.exit
+
+.src2_aligned:	mov	r4, r5, pull #16
+		adds	sum, sum, #0
+		bics	ip, len, #15
+		beq	2f
+1:		load4l	r5, r6, r7, r8
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		mov	r7, r7, pull #16
+		orr	r7, r7, r8, push #16
+		stmia	dst!, {r4, r5, r6, r7}
+		adcs	sum, sum, r4
+		adcs	sum, sum, r5
+		adcs	sum, sum, r6
+		adcs	sum, sum, r7
+		mov	r4, r8, pull #16
+		sub	ip, ip, #16
+		teq	ip, #0
+		bne	1b
+2:		ands	ip, len, #12
+		beq	4f
+		tst	ip, #8
+		beq	3f
+		load2l	r5, r6
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		stmia	dst!, {r4, r5}
+		adcs	sum, sum, r4
+		adcs	sum, sum, r5
+		mov	r4, r6, pull #16
+		tst	ip, #4
+		beq	4f
+3:		load1l	r5
+		orr	r4, r4, r5, push #16
+		str	r4, [dst], #4
+		adcs	sum, sum, r4
+		mov	r4, r5, pull #16
+4:		ands	len, len, #3
+		beq	.done
+		mov	r5, r4, get_byte_0
+		tst	len, #2
+		beq	.exit
+		adcs	sum, sum, r4
+		strb	r5, [dst], #1
+		mov	r5, r4, get_byte_1
+		strb	r5, [dst], #1
+		tst	len, #1
+		beq	.done
+		load1b	r5
+		b	.exit
+
+.src3_aligned:	mov	r4, r5, pull #24
+		adds	sum, sum, #0
+		bics	ip, len, #15
+		beq	2f
+1:		load4l	r5, r6, r7, r8
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		mov	r7, r7, pull #24
+		orr	r7, r7, r8, push #8
+		stmia	dst!, {r4, r5, r6, r7}
+		adcs	sum, sum, r4
+		adcs	sum, sum, r5
+		adcs	sum, sum, r6
+		adcs	sum, sum, r7
+		mov	r4, r8, pull #24
+		sub	ip, ip, #16
+		teq	ip, #0
+		bne	1b
+2:		ands	ip, len, #12
+		beq	4f
+		tst	ip, #8
+		beq	3f
+		load2l	r5, r6
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		stmia	dst!, {r4, r5}
+		adcs	sum, sum, r4
+		adcs	sum, sum, r5
+		mov	r4, r6, pull #24
+		tst	ip, #4
+		beq	4f
+3:		load1l	r5
+		orr	r4, r4, r5, push #8
+		str	r4, [dst], #4
+		adcs	sum, sum, r4
+		mov	r4, r5, pull #24
+4:		ands	len, len, #3
+		beq	.done
+		mov	r5, r4, get_byte_0
+		tst	len, #2
+		beq	.exit
+		strb	r5, [dst], #1
+		adcs	sum, sum, r4
+		load1l	r4
+		mov	r5, r4, get_byte_0
+		strb	r5, [dst], #1
+		adcs	sum, sum, r4, push #24
+		mov	r5, r4, get_byte_1
+		b	.exit
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
new file mode 100644
index 00000000000..46a2dc962e9
--- /dev/null
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -0,0 +1,104 @@
+/*
+ *  linux/arch/arm/lib/csumpartialcopyuser.S
+ *
+ *  Copyright (C) 1995-1998 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 27/03/03 Ian Molton Clean up CONFIG_CPU
+ *
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+#include <asm/constants.h>
+
+		.text
+
+		.macro	save_regs
+		stmfd	sp!, {r1 - r2, r4 - r8, fp, ip, lr, pc}
+		.endm
+
+		.macro	load_regs,flags
+		ldm\flags	fp, {r1, r2, r4-r8, fp, sp, pc}
+		.endm
+
+		.macro	load1b,	reg1
+9999:		ldrbt	\reg1, [r0], $1
+		.section __ex_table, "a"
+		.align	3
+		.long	9999b, 6001f
+		.previous
+		.endm
+
+		.macro	load2b, reg1, reg2
+9999:		ldrbt	\reg1, [r0], $1
+9998:		ldrbt	\reg2, [r0], $1
+		.section __ex_table, "a"
+		.long	9999b, 6001f
+		.long	9998b, 6001f
+		.previous
+		.endm
+
+		.macro	load1l, reg1
+9999:		ldrt	\reg1, [r0], $4
+		.section __ex_table, "a"
+		.align	3
+		.long	9999b, 6001f
+		.previous
+		.endm
+
+		.macro	load2l, reg1, reg2
+9999:		ldrt	\reg1, [r0], $4
+9998:		ldrt	\reg2, [r0], $4
+		.section __ex_table, "a"
+		.long	9999b, 6001f
+		.long	9998b, 6001f
+		.previous
+		.endm
+
+		.macro	load4l, reg1, reg2, reg3, reg4
+9999:		ldrt	\reg1, [r0], $4
+9998:		ldrt	\reg2, [r0], $4
+9997:		ldrt	\reg3, [r0], $4
+9996:		ldrt	\reg4, [r0], $4
+		.section __ex_table, "a"
+		.long	9999b, 6001f
+		.long	9998b, 6001f
+		.long	9997b, 6001f
+		.long	9996b, 6001f
+		.previous
+		.endm
+
+/*
+ * unsigned int
+ * csum_partial_copy_from_user(const char *src, char *dst, int len, int sum, int *err_ptr)
+ *  r0 = src, r1 = dst, r2 = len, r3 = sum, [sp] = *err_ptr
+ *  Returns : r0 = checksum, [[sp, #0], #0] = 0 or -EFAULT
+ */
+
+#define FN_ENTRY	ENTRY(csum_partial_copy_from_user)
+
+#include "csumpartialcopygeneric.S"
+
+/*
+ * FIXME: minor buglet here
+ * We don't return the checksum for the data present in the buffer.  To do
+ * so properly, we would have to add in whatever registers were loaded before
+ * the fault, which, with the current asm above is not predictable.
+ */
+		.section .fixup,"ax"
+		.align	4
+6001:		mov	r4, #-EFAULT
+		ldr	r5, [fp, #4]		@ *err_ptr
+		str	r4, [r5]
+		ldmia	sp, {r1, r2}		@ retrieve dst, len
+		add	r2, r2, r1
+		mov	r0, #0			@ zero the buffer
+6002:		teq	r2, r1
+		strneb	r0, [r1], #1
+		bne	6002b
+		load_regs	ea
+		.previous
diff --git a/arch/arm/lib/delay.S b/arch/arm/lib/delay.S
new file mode 100644
index 00000000000..3c7f7e675dd
--- /dev/null
+++ b/arch/arm/lib/delay.S
@@ -0,0 +1,58 @@
+/*
+ *  linux/arch/arm/lib/delay.S
+ *
+ *  Copyright (C) 1995, 1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+		.text
+
+LC0:		.word	loops_per_jiffy
+
+/*
+ * 0 <= r0 <= 2000
+ */
+ENTRY(__udelay)
+		mov	r2,     #0x6800
+		orr	r2, r2, #0x00db
+		mul	r0, r2, r0
+ENTRY(__const_udelay)				@ 0 <= r0 <= 0x01ffffff
+		ldr	r2, LC0
+		ldr	r2, [r2]		@ max = 0x0fffffff
+		mov	r0, r0, lsr #11		@ max = 0x00003fff
+		mov	r2, r2, lsr #11		@ max = 0x0003ffff
+		mul	r0, r2, r0		@ max = 2^32-1
+		movs	r0, r0, lsr #6
+		RETINSTR(moveq,pc,lr)
+
+/*
+ * loops = (r0 * 0x10c6 * 100 * loops_per_jiffy) / 2^32
+ *
+ * Oh, if only we had a cycle counter...
+ */
+
+@ Delay routine
+ENTRY(__delay)
+		subs	r0, r0, #1
+#if 0
+		RETINSTR(movls,pc,lr)
+		subs	r0, r0, #1
+		RETINSTR(movls,pc,lr)
+		subs	r0, r0, #1
+		RETINSTR(movls,pc,lr)
+		subs	r0, r0, #1
+		RETINSTR(movls,pc,lr)
+		subs	r0, r0, #1
+		RETINSTR(movls,pc,lr)
+		subs	r0, r0, #1
+		RETINSTR(movls,pc,lr)
+		subs	r0, r0, #1
+		RETINSTR(movls,pc,lr)
+		subs	r0, r0, #1
+#endif
+		bhi	__delay
+		RETINSTR(mov,pc,lr)
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
new file mode 100644
index 00000000000..ec9a1cd6176
--- /dev/null
+++ b/arch/arm/lib/div64.S
@@ -0,0 +1,200 @@
+/*
+ *  linux/arch/arm/lib/div64.S
+ *
+ *  Optimized computation of 64-bit dividend / 32-bit divisor
+ *
+ *  Author:	Nicolas Pitre
+ *  Created:	Oct 5, 2003
+ *  Copyright:	Monta Vista Software, Inc.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#ifdef __ARMEB__
+#define xh r0
+#define xl r1
+#define yh r2
+#define yl r3
+#else
+#define xl r0
+#define xh r1
+#define yl r2
+#define yh r3
+#endif
+
+/*
+ * __do_div64: perform a division with 64-bit dividend and 32-bit divisor.
+ *
+ * Note: Calling convention is totally non standard for optimal code.
+ *       This is meant to be used by do_div() from include/asm/div64.h only.
+ *
+ * Input parameters:
+ * 	xh-xl	= dividend (clobbered)
+ * 	r4	= divisor (preserved)
+ *
+ * Output values:
+ * 	yh-yl	= result
+ * 	xh	= remainder
+ *
+ * Clobbered regs: xl, ip
+ */
+
+ENTRY(__do_div64)
+
+	@ Test for easy paths first.
+	subs	ip, r4, #1
+	bls	9f			@ divisor is 0 or 1
+	tst	ip, r4
+	beq	8f			@ divisor is power of 2
+
+	@ See if we need to handle upper 32-bit result.
+	cmp	xh, r4
+	mov	yh, #0
+	blo	3f
+
+	@ Align divisor with upper part of dividend.
+	@ The aligned divisor is stored in yl preserving the original.
+	@ The bit position is stored in ip.
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	yl, r4
+	clz	ip, xh
+	sub	yl, yl, ip
+	mov	ip, #1
+	mov	ip, ip, lsl yl
+	mov	yl, r4, lsl yl
+
+#else
+
+	mov	yl, r4
+	mov	ip, #1
+1:	cmp	yl, #0x80000000
+	cmpcc	yl, xh
+	movcc	yl, yl, lsl #1
+	movcc	ip, ip, lsl #1
+	bcc	1b
+
+#endif
+
+	@ The division loop for needed upper bit positions.
+ 	@ Break out early if dividend reaches 0.
+2:	cmp	xh, yl
+	orrcs	yh, yh, ip
+	subcss	xh, xh, yl
+	movnes	ip, ip, lsr #1
+	mov	yl, yl, lsr #1
+	bne	2b
+
+	@ See if we need to handle lower 32-bit result.
+3:	cmp	xh, #0
+	mov	yl, #0
+	cmpeq	xl, r4
+	movlo	xh, xl
+	movlo	pc, lr
+
+	@ The division loop for lower bit positions.
+	@ Here we shift remainer bits leftwards rather than moving the
+	@ divisor for comparisons, considering the carry-out bit as well.
+	mov	ip, #0x80000000
+4:	movs	xl, xl, lsl #1
+	adcs	xh, xh, xh
+	beq	6f
+	cmpcc	xh, r4
+5:	orrcs	yl, yl, ip
+	subcs	xh, xh, r4
+	movs	ip, ip, lsr #1
+	bne	4b
+	mov	pc, lr
+
+	@ The top part of remainder became zero.  If carry is set
+	@ (the 33th bit) this is a false positive so resume the loop.
+	@ Otherwise, if lower part is also null then we are done.
+6:	bcs	5b
+	cmp	xl, #0
+	moveq	pc, lr
+
+	@ We still have remainer bits in the low part.  Bring them up.
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	xh, xl			@ we know xh is zero here so...
+	add	xh, xh, #1
+	mov	xl, xl, lsl xh
+	mov	ip, ip, lsr xh
+
+#else
+
+7:	movs	xl, xl, lsl #1
+	mov	ip, ip, lsr #1
+	bcc	7b
+
+#endif
+
+	@ Current remainder is now 1.  It is worthless to compare with
+	@ divisor at this point since divisor can not be smaller than 3 here.
+	@ If possible, branch for another shift in the division loop.
+	@ If no bit position left then we are done.
+	movs	ip, ip, lsr #1
+	mov	xh, #1
+	bne	4b
+	mov	pc, lr
+
+8:	@ Division by a power of 2: determine what that divisor order is
+	@ then simply shift values around
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	ip, r4
+	rsb	ip, ip, #31
+
+#else
+
+	mov	yl, r4
+	cmp	r4, #(1 << 16)
+	mov	ip, #0
+	movhs	yl, yl, lsr #16
+	movhs	ip, #16
+
+	cmp	yl, #(1 << 8)
+	movhs	yl, yl, lsr #8
+	addhs	ip, ip, #8
+
+	cmp	yl, #(1 << 4)
+	movhs	yl, yl, lsr #4
+	addhs	ip, ip, #4
+
+	cmp	yl, #(1 << 2)
+	addhi	ip, ip, #3
+	addls	ip, ip, yl, lsr #1
+
+#endif
+
+	mov	yh, xh, lsr ip
+	mov	yl, xl, lsr ip
+	rsb	ip, ip, #32
+	orr	yl, yl, xh, lsl ip
+	mov	xh, xl, lsl ip
+	mov	xh, xh, lsr ip
+	mov	pc, lr
+
+	@ eq -> division by 1: obvious enough...
+9:	moveq	yl, xl
+	moveq	yh, xh
+	moveq	xh, #0
+	moveq	pc, lr
+
+	@ Division by 0:
+	str	lr, [sp, #-4]!
+	bl	__div0
+
+	@ as wrong as it could be...
+	mov	yl, #0
+	mov	yh, #0
+	mov	xh, #0
+	ldr	pc, [sp], #4
+
diff --git a/arch/arm/lib/ecard.S b/arch/arm/lib/ecard.S
new file mode 100644
index 00000000000..fb7b602a6f7
--- /dev/null
+++ b/arch/arm/lib/ecard.S
@@ -0,0 +1,45 @@
+/*
+ *  linux/arch/arm/lib/ecard.S
+ *
+ *  Copyright (C) 1995, 1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 27/03/03 Ian Molton Clean up CONFIG_CPU
+ *
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/hardware.h>
+
+#define CPSR2SPSR(rt) \
+		mrs	rt, cpsr; \
+		msr	spsr_cxsf, rt
+
+@ Purpose: call an expansion card loader to read bytes.
+@ Proto  : char read_loader(int offset, char *card_base, char *loader);
+@ Returns: byte read
+
+ENTRY(ecard_loader_read)
+		stmfd	sp!, {r4 - r12, lr}
+		mov	r11, r1
+		mov	r1, r0
+		CPSR2SPSR(r0)
+		mov	lr, pc
+		mov	pc, r2
+		LOADREGS(fd, sp!, {r4 - r12, pc})
+
+@ Purpose: call an expansion card loader to reset the card
+@ Proto  : void read_loader(int card_base, char *loader);
+@ Returns: byte read
+
+ENTRY(ecard_loader_reset)
+		stmfd	sp!, {r4 - r12, lr}
+		mov	r11, r0
+		CPSR2SPSR(r0)
+		mov	lr, pc
+		add	pc, r1, #8
+		LOADREGS(fd, sp!, {r4 - r12, pc})
+
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
new file mode 100644
index 00000000000..f055d56ea68
--- /dev/null
+++ b/arch/arm/lib/findbit.S
@@ -0,0 +1,168 @@
+/*
+ *  linux/arch/arm/lib/findbit.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 16th March 2001 - John Ripley <jripley@sonicblue.com>
+ *   Fixed so that "size" is an exclusive not an inclusive quantity.
+ *   All users of these functions expect exclusive sizes, and may
+ *   also call with zero size.
+ * Reworked by rmk.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+                .text
+
+/*
+ * Purpose  : Find a 'zero' bit
+ * Prototype: int find_first_zero_bit(void *addr, unsigned int maxbit);
+ */
+ENTRY(_find_first_zero_bit_le)
+		teq	r1, #0	
+		beq	3f
+		mov	r2, #0
+1:		ldrb	r3, [r0, r2, lsr #3]
+		eors	r3, r3, #0xff		@ invert bits
+		bne	.found			@ any now set - found zero bit
+		add	r2, r2, #8		@ next bit pointer
+2:		cmp	r2, r1			@ any more?
+		blo	1b
+3:		mov	r0, r1			@ no free bits
+		RETINSTR(mov,pc,lr)
+
+/*
+ * Purpose  : Find next 'zero' bit
+ * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
+ */
+ENTRY(_find_next_zero_bit_le)
+		teq	r1, #0
+		beq	3b
+		ands	ip, r2, #7
+		beq	1b			@ If new byte, goto old routine
+		ldrb	r3, [r0, r2, lsr #3]
+		eor	r3, r3, #0xff		@ now looking for a 1 bit
+		movs	r3, r3, lsr ip		@ shift off unused bits
+		bne	.found
+		orr	r2, r2, #7		@ if zero, then no bits here
+		add	r2, r2, #1		@ align bit pointer
+		b	2b			@ loop for next bit
+
+/*
+ * Purpose  : Find a 'one' bit
+ * Prototype: int find_first_bit(const unsigned long *addr, unsigned int maxbit);
+ */
+ENTRY(_find_first_bit_le)
+		teq	r1, #0	
+		beq	3f
+		mov	r2, #0
+1:		ldrb	r3, [r0, r2, lsr #3]
+		movs	r3, r3
+		bne	.found			@ any now set - found zero bit
+		add	r2, r2, #8		@ next bit pointer
+2:		cmp	r2, r1			@ any more?
+		blo	1b
+3:		mov	r0, r1			@ no free bits
+		RETINSTR(mov,pc,lr)
+
+/*
+ * Purpose  : Find next 'one' bit
+ * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
+ */
+ENTRY(_find_next_bit_le)
+		teq	r1, #0
+		beq	3b
+		ands	ip, r2, #7
+		beq	1b			@ If new byte, goto old routine
+		ldrb	r3, [r0, r2, lsr #3]
+		movs	r3, r3, lsr ip		@ shift off unused bits
+		bne	.found
+		orr	r2, r2, #7		@ if zero, then no bits here
+		add	r2, r2, #1		@ align bit pointer
+		b	2b			@ loop for next bit
+
+#ifdef __ARMEB__
+
+ENTRY(_find_first_zero_bit_be)
+		teq	r1, #0
+		beq	3f
+		mov	r2, #0
+1:		eor	r3, r2, #0x18		@ big endian byte ordering
+		ldrb	r3, [r0, r3, lsr #3]
+		eors	r3, r3, #0xff		@ invert bits
+		bne	.found			@ any now set - found zero bit
+		add	r2, r2, #8		@ next bit pointer
+2:		cmp	r2, r1			@ any more?
+		blo	1b
+3:		mov	r0, r1			@ no free bits
+		RETINSTR(mov,pc,lr)
+
+ENTRY(_find_next_zero_bit_be)
+		teq	r1, #0
+		beq	3b
+		ands	ip, r2, #7
+		beq	1b			@ If new byte, goto old routine
+		eor	r3, r2, #0x18		@ big endian byte ordering
+		ldrb	r3, [r0, r3, lsr #3]
+		eor	r3, r3, #0xff		@ now looking for a 1 bit
+		movs	r3, r3, lsr ip		@ shift off unused bits
+		bne	.found
+		orr	r2, r2, #7		@ if zero, then no bits here
+		add	r2, r2, #1		@ align bit pointer
+		b	2b			@ loop for next bit
+
+ENTRY(_find_first_bit_be)
+		teq	r1, #0
+		beq	3f
+		mov	r2, #0
+1:		eor	r3, r2, #0x18		@ big endian byte ordering
+		ldrb	r3, [r0, r3, lsr #3]
+		movs	r3, r3
+		bne	.found			@ any now set - found zero bit
+		add	r2, r2, #8		@ next bit pointer
+2:		cmp	r2, r1			@ any more?
+		blo	1b
+3:		mov	r0, r1			@ no free bits
+		RETINSTR(mov,pc,lr)
+
+ENTRY(_find_next_bit_be)
+		teq	r1, #0
+		beq	3b
+		ands	ip, r2, #7
+		beq	1b			@ If new byte, goto old routine
+		eor	r3, r2, #0x18		@ big endian byte ordering
+		ldrb	r3, [r0, r3, lsr #3]
+		movs	r3, r3, lsr ip		@ shift off unused bits
+		bne	.found
+		orr	r2, r2, #7		@ if zero, then no bits here
+		add	r2, r2, #1		@ align bit pointer
+		b	2b			@ loop for next bit
+
+#endif
+
+/*
+ * One or more bits in the LSB of r3 are assumed to be set.
+ */
+.found:
+#if __LINUX_ARM_ARCH__ >= 5
+		rsb	r1, r3, #0
+		and	r3, r3, r1
+		clz	r3, r3
+		rsb	r3, r3, #31
+		add	r0, r2, r3
+#else
+		tst	r3, #0x0f
+		addeq	r2, r2, #4
+		movne	r3, r3, lsl #4
+		tst	r3, #0x30
+		addeq	r2, r2, #2
+		movne	r3, r3, lsl #2
+		tst	r3, #0x40
+		addeq	r2, r2, #1
+		mov	r0, r2
+#endif
+		RETINSTR(mov,pc,lr)
+
diff --git a/arch/arm/lib/floppydma.S b/arch/arm/lib/floppydma.S
new file mode 100644
index 00000000000..617150b1bae
--- /dev/null
+++ b/arch/arm/lib/floppydma.S
@@ -0,0 +1,32 @@
+/*
+ *  linux/arch/arm/lib/floppydma.S
+ *
+ *  Copyright (C) 1995, 1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+		.text
+
+		.global	floppy_fiqin_end
+ENTRY(floppy_fiqin_start)
+		subs	r9, r9, #1
+		ldrgtb	r12, [r11, #-4]
+		ldrleb	r12, [r11], #0
+		strb	r12, [r10], #1
+		subs	pc, lr, #4
+floppy_fiqin_end:
+
+		.global	floppy_fiqout_end
+ENTRY(floppy_fiqout_start)
+		subs	r9, r9, #1
+		ldrgeb	r12, [r10], #1
+		movlt	r12, #0
+		strleb	r12, [r11], #0
+		subles	pc, lr, #4
+		strb	r12, [r11, #-4]
+		subs	pc, lr, #4
+floppy_fiqout_end:
diff --git a/arch/arm/lib/gcclib.h b/arch/arm/lib/gcclib.h
new file mode 100644
index 00000000000..65314a3d9e2
--- /dev/null
+++ b/arch/arm/lib/gcclib.h
@@ -0,0 +1,25 @@
+/* gcclib.h -- definitions for various functions 'borrowed' from gcc-2.95.3 */
+/* I Molton     29/07/01 */
+
+#define BITS_PER_UNIT  8
+#define SI_TYPE_SIZE (sizeof (SItype) * BITS_PER_UNIT)
+
+typedef unsigned int UQItype    __attribute__ ((mode (QI)));
+typedef          int SItype     __attribute__ ((mode (SI)));
+typedef unsigned int USItype    __attribute__ ((mode (SI)));
+typedef          int DItype     __attribute__ ((mode (DI)));
+typedef          int word_type 	__attribute__ ((mode (__word__)));
+typedef unsigned int UDItype    __attribute__ ((mode (DI)));
+
+#ifdef __ARMEB__
+  struct DIstruct {SItype high, low;};
+#else
+  struct DIstruct {SItype low, high;};
+#endif
+
+typedef union
+{
+  struct DIstruct s;
+  DItype ll;
+} DIunion;
+
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
new file mode 100644
index 00000000000..64aa6f4fe5e
--- /dev/null
+++ b/arch/arm/lib/getuser.S
@@ -0,0 +1,78 @@
+/*
+ *  linux/arch/arm/lib/getuser.S
+ *
+ *  Copyright (C) 2001 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  Idea from x86 version, (C) Copyright 1998 Linus Torvalds
+ *
+ * These functions have a non-standard call interface to make them more
+ * efficient, especially as they return an error value in addition to
+ * the "real" return value.
+ *
+ * __get_user_X
+ *
+ * Inputs:	r0 contains the address
+ * Outputs:	r0 is the error code
+ *		r2, r3 contains the zero-extended value
+ *		lr corrupted
+ *
+ * No other registers must be altered.  (see include/asm-arm/uaccess.h
+ * for specific ASM register usage).
+ *
+ * Note that ADDR_LIMIT is either 0 or 0xc0000000.
+ * Note also that it is intended that __get_user_bad is not global.
+ */
+#include <asm/constants.h>
+#include <asm/thread_info.h>
+#include <asm/errno.h>
+
+	.global	__get_user_1
+__get_user_1:
+1:	ldrbt	r2, [r0]
+	mov	r0, #0
+	mov	pc, lr
+
+	.global	__get_user_2
+__get_user_2:
+2:	ldrbt	r2, [r0], #1
+3:	ldrbt	r3, [r0]
+#ifndef __ARMEB__
+	orr	r2, r2, r3, lsl #8
+#else
+	orr	r2, r3, r2, lsl #8
+#endif
+	mov	r0, #0
+	mov	pc, lr
+
+	.global	__get_user_4
+__get_user_4:
+4:	ldrt	r2, [r0]
+	mov	r0, #0
+	mov	pc, lr
+
+	.global	__get_user_8
+__get_user_8:
+5:	ldrt	r2, [r0], #4
+6:	ldrt	r3, [r0]
+	mov	r0, #0
+	mov	pc, lr
+
+__get_user_bad_8:
+	mov	r3, #0
+__get_user_bad:
+	mov	r2, #0
+	mov	r0, #-EFAULT
+	mov	pc, lr
+
+.section __ex_table, "a"
+	.long	1b, __get_user_bad
+	.long	2b, __get_user_bad
+	.long	3b, __get_user_bad
+	.long	4b, __get_user_bad
+	.long	5b, __get_user_bad_8
+	.long	6b, __get_user_bad_8
+.previous
diff --git a/arch/arm/lib/io-acorn.S b/arch/arm/lib/io-acorn.S
new file mode 100644
index 00000000000..3aacd01d40e
--- /dev/null
+++ b/arch/arm/lib/io-acorn.S
@@ -0,0 +1,32 @@
+/*
+ *  linux/arch/arm/lib/io-acorn.S
+ *
+ *  Copyright (C) 1995, 1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 27/03/03 Ian Molton Clean up CONFIG_CPU
+ *
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/hardware.h>
+
+		.text
+		.align
+
+.iosl_warning:
+		.ascii	"<4>insl/outsl not implemented, called from %08lX\0"
+		.align
+
+/*
+ * These make no sense on Acorn machines.
+ * Print a warning message.
+ */
+ENTRY(insl)
+ENTRY(outsl)
+		adr	r0, .iosl_warning
+		mov	r1, lr
+		b	printk
diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib/io-readsb.S
new file mode 100644
index 00000000000..081ef749298
--- /dev/null
+++ b/arch/arm/lib/io-readsb.S
@@ -0,0 +1,122 @@
+/*
+ *  linux/arch/arm/lib/io-readsb.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+.insb_align:	rsb	ip, ip, #4
+		cmp	ip, r2
+		movgt	ip, r2
+		cmp	ip, #2
+		ldrb	r3, [r0]
+		strb	r3, [r1], #1
+		ldrgeb	r3, [r0]
+		strgeb	r3, [r1], #1
+		ldrgtb	r3, [r0]
+		strgtb	r3, [r1], #1
+		subs	r2, r2, ip
+		bne	.insb_aligned
+
+ENTRY(__raw_readsb)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		ands	ip, r1, #3
+		bne	.insb_align
+
+.insb_aligned:	stmfd	sp!, {r4 - r6, lr}
+
+		subs	r2, r2, #16
+		bmi	.insb_no_16
+
+.insb_16_lp:	ldrb	r3, [r0]
+		ldrb	r4, [r0]
+		ldrb	r5, [r0]
+		mov	r3, r3,     put_byte_0
+		ldrb	r6, [r0]
+		orr	r3, r3, r4, put_byte_1
+		ldrb	r4, [r0]
+		orr	r3, r3, r5, put_byte_2
+		ldrb	r5, [r0]
+		orr	r3, r3, r6, put_byte_3
+		ldrb	r6, [r0]
+		mov	r4, r4,     put_byte_0
+		ldrb	ip, [r0]
+		orr	r4, r4, r5, put_byte_1
+		ldrb	r5, [r0]
+		orr	r4, r4, r6, put_byte_2
+		ldrb	r6, [r0]
+		orr	r4, r4, ip, put_byte_3
+		ldrb	ip, [r0]
+		mov	r5, r5,     put_byte_0
+		ldrb	lr, [r0]
+		orr	r5, r5, r6, put_byte_1
+		ldrb	r6, [r0]
+		orr	r5, r5, ip, put_byte_2
+		ldrb	ip, [r0]
+		orr	r5, r5, lr, put_byte_3
+		ldrb	lr, [r0]
+		mov	r6, r6,     put_byte_0
+		orr	r6, r6, ip, put_byte_1
+		ldrb	ip, [r0]
+		orr	r6, r6, lr, put_byte_2
+		orr	r6, r6, ip, put_byte_3
+		stmia	r1!, {r3 - r6}
+
+		subs	r2, r2, #16
+		bpl	.insb_16_lp
+
+		tst	r2, #15
+		LOADREGS(eqfd, sp!, {r4 - r6, pc})
+
+.insb_no_16:	tst	r2, #8
+		beq	.insb_no_8
+
+		ldrb	r3, [r0]
+		ldrb	r4, [r0]
+		ldrb	r5, [r0]
+		mov	r3, r3,     put_byte_0
+		ldrb	r6, [r0]
+		orr	r3, r3, r4, put_byte_1
+		ldrb	r4, [r0]
+		orr	r3, r3, r5, put_byte_2
+		ldrb	r5, [r0]
+		orr	r3, r3, r6, put_byte_3
+		ldrb	r6, [r0]
+		mov	r4, r4,     put_byte_0
+		ldrb	ip, [r0]
+		orr	r4, r4, r5, put_byte_1
+		orr	r4, r4, r6, put_byte_2
+		orr	r4, r4, ip, put_byte_3
+		stmia	r1!, {r3, r4}
+
+.insb_no_8:	tst	r2, #4
+		beq	.insb_no_4
+
+		ldrb	r3, [r0]
+		ldrb	r4, [r0]
+		ldrb	r5, [r0]
+		ldrb	r6, [r0]
+		mov	r3, r3,     put_byte_0
+		orr	r3, r3, r4, put_byte_1
+		orr	r3, r3, r5, put_byte_2
+		orr	r3, r3, r6, put_byte_3
+		str	r3, [r1], #4
+
+.insb_no_4:	ands	r2, r2, #3
+		LOADREGS(eqfd, sp!, {r4 - r6, pc})
+
+		cmp	r2, #2
+		ldrb	r3, [r0]
+		strb	r3, [r1], #1
+		ldrgeb	r3, [r0]
+		strgeb	r3, [r1], #1
+		ldrgtb	r3, [r0]
+		strgtb	r3, [r1]
+
+		LOADREGS(fd, sp!, {r4 - r6, pc})
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
new file mode 100644
index 00000000000..75a9121cb23
--- /dev/null
+++ b/arch/arm/lib/io-readsl.S
@@ -0,0 +1,78 @@
+/*
+ *  linux/arch/arm/lib/io-readsl.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ENTRY(__raw_readsl)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		ands	ip, r1, #3
+		bne	3f
+
+		subs	r2, r2, #4
+		bmi	2f
+		stmfd	sp!, {r4, lr}
+1:		ldr	r3, [r0, #0]
+		ldr	r4, [r0, #0]
+		ldr	ip, [r0, #0]
+		ldr	lr, [r0, #0]
+		subs	r2, r2, #4
+		stmia	r1!, {r3, r4, ip, lr}
+		bpl	1b
+		ldmfd	sp!, {r4, lr}
+2:		movs	r2, r2, lsl #31
+		ldrcs	r3, [r0, #0]
+		ldrcs	ip, [r0, #0]
+		stmcsia	r1!, {r3, ip}
+		ldrne	r3, [r0, #0]
+		strne	r3, [r1, #0]
+		mov	pc, lr
+
+3:		ldr	r3, [r0]
+		cmp	ip, #2
+		mov	ip, r3, get_byte_0
+		strb	ip, [r1], #1
+		bgt	6f
+		mov	ip, r3, get_byte_1
+		strb	ip, [r1], #1
+		beq	5f
+		mov	ip, r3, get_byte_2
+		strb	ip, [r1], #1
+
+4:		subs	r2, r2, #1
+		mov	ip, r3, pull #24
+		ldrne	r3, [r0]
+		orrne	ip, ip, r3, push #8
+		strne	ip, [r1], #4
+		bne	4b
+		b	8f
+
+5:		subs	r2, r2, #1
+		mov	ip, r3, pull #16
+		ldrne	r3, [r0]
+		orrne	ip, ip, r3, push #16
+		strne	ip, [r1], #4
+		bne	5b
+		b	7f
+
+6:		subs	r2, r2, #1
+		mov	ip, r3, pull #8
+		ldrne	r3, [r0]
+		orrne	ip, ip, r3, push #24
+		strne	ip, [r1], #4
+		bne	6b
+
+		mov	r3, ip, get_byte_2
+		strb	r3, [r1, #2]
+7:		mov	r3, ip, get_byte_1
+		strb	r3, [r1, #1]
+8:		mov	r3, ip, get_byte_0
+		strb	r3, [r1, #0]
+		mov	pc, lr
diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S
new file mode 100644
index 00000000000..476cf7f8a63
--- /dev/null
+++ b/arch/arm/lib/io-readsw-armv3.S
@@ -0,0 +1,107 @@
+/*
+ *  linux/arch/arm/lib/io-readsw-armv3.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/hardware.h>
+
+.insw_bad_alignment:
+		adr	r0, .insw_bad_align_msg
+		mov	r2, lr
+		b	panic
+.insw_bad_align_msg:
+		.asciz	"insw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+		.align
+
+.insw_align:	tst	r1, #1
+		bne	.insw_bad_alignment
+
+		ldr	r3, [r0]
+		strb	r3, [r1], #1
+		mov	r3, r3, lsr #8
+		strb	r3, [r1], #1
+
+		subs	r2, r2, #1
+		RETINSTR(moveq, pc, lr)
+
+ENTRY(__raw_readsw)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.insw_align
+
+.insw_aligned:	mov	ip, #0xff
+		orr	ip, ip, ip, lsl #8
+		stmfd	sp!, {r4, r5, r6, lr}
+
+		subs	r2, r2, #8
+		bmi	.no_insw_8
+
+.insw_8_lp:	ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		ldr	r4, [r0]
+		and	r4, r4, ip
+		ldr	r5, [r0]
+		orr	r4, r4, r5, lsl #16
+
+		ldr	r5, [r0]
+		and	r5, r5, ip
+		ldr	r6, [r0]
+		orr	r5, r5, r6, lsl #16
+
+		ldr	r6, [r0]
+		and	r6, r6, ip
+		ldr	lr, [r0]
+		orr	r6, r6, lr, lsl #16
+
+		stmia	r1!, {r3 - r6}
+
+		subs	r2, r2, #8
+		bpl	.insw_8_lp
+
+		tst	r2, #7
+		LOADREGS(eqfd, sp!, {r4, r5, r6, pc})
+
+.no_insw_8:	tst	r2, #4
+		beq	.no_insw_4
+
+		ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		ldr	r4, [r0]
+		and	r4, r4, ip
+		ldr	r5, [r0]
+		orr	r4, r4, r5, lsl #16
+
+		stmia	r1!, {r3, r4}
+
+.no_insw_4:	tst	r2, #2
+		beq	.no_insw_2
+
+		ldr	r3, [r0]
+		and	r3, r3, ip
+		ldr	r4, [r0]
+		orr	r3, r3, r4, lsl #16
+
+		str	r3, [r1], #4
+
+.no_insw_2:	tst	r2, #1
+		ldrne	r3, [r0]
+		strneb	r3, [r1], #1
+		movne	r3, r3, lsr #8
+		strneb	r3, [r1]
+
+		LOADREGS(fd, sp!, {r4, r5, r6, pc})
+
+
diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib/io-readsw-armv4.S
new file mode 100644
index 00000000000..c92b66ecbe8
--- /dev/null
+++ b/arch/arm/lib/io-readsw-armv4.S
@@ -0,0 +1,130 @@
+/*
+ *  linux/arch/arm/lib/io-readsw-armv4.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.macro	pack, rd, hw1, hw2
+#ifndef __ARMEB__
+		orr	\rd, \hw1, \hw2, lsl #16
+#else
+		orr	\rd, \hw2, \hw1, lsl #16
+#endif
+		.endm
+
+.insw_align:	movs	ip, r1, lsl #31
+		bne	.insw_noalign
+		ldrh	ip, [r0]
+		sub	r2, r2, #1
+		strh	ip, [r1], #2
+
+ENTRY(__raw_readsw)
+		teq	r2, #0
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.insw_align
+
+		stmfd	sp!, {r4, r5, lr}
+
+		subs	r2, r2, #8
+		bmi	.no_insw_8
+
+.insw_8_lp:	ldrh	r3, [r0]
+		ldrh	r4, [r0]
+		pack	r3, r3, r4
+
+		ldrh	r4, [r0]
+		ldrh	r5, [r0]
+		pack	r4, r4, r5
+
+		ldrh	r5, [r0]
+		ldrh	ip, [r0]
+		pack	r5, r5, ip
+
+		ldrh	ip, [r0]
+		ldrh	lr, [r0]
+		pack	ip, ip, lr
+
+		subs	r2, r2, #8
+		stmia	r1!, {r3 - r5, ip}
+		bpl	.insw_8_lp
+
+.no_insw_8:	tst	r2, #4
+		beq	.no_insw_4
+
+		ldrh	r3, [r0]
+		ldrh	r4, [r0]
+		pack	r3, r3, r4
+
+		ldrh	r4, [r0]
+		ldrh	ip, [r0]
+		pack	r4, r4, ip
+
+		stmia	r1!, {r3, r4}
+
+.no_insw_4:	movs	r2, r2, lsl #31
+		bcc	.no_insw_2
+
+		ldrh	r3, [r0]
+		ldrh	ip, [r0]
+		pack	r3, r3, ip
+		str	r3, [r1], #4
+
+.no_insw_2:	ldrneh	r3, [r0]
+		strneh	r3, [r1]
+
+		ldmfd	sp!, {r4, r5, pc}
+
+#ifdef __ARMEB__
+#define _BE_ONLY_(code...)	code
+#define _LE_ONLY_(code...)
+#define push_hbyte0		lsr #8
+#define pull_hbyte1		lsl #24
+#else
+#define _BE_ONLY_(code...)
+#define _LE_ONLY_(code...) code
+#define push_hbyte0		lsl #24
+#define pull_hbyte1		lsr #8
+#endif
+
+.insw_noalign:	stmfd	sp!, {r4, lr}
+		ldrccb	ip, [r1, #-1]!
+		bcc	1f
+
+		ldrh	ip, [r0]
+		sub	r2, r2, #1
+   _BE_ONLY_(	mov	ip, ip, ror #8		)
+		strb	ip, [r1], #1
+   _LE_ONLY_(	mov	ip, ip, lsr #8		)
+   _BE_ONLY_(	mov	ip, ip, lsr #24		)
+
+1:		subs	r2, r2, #2
+		bmi	3f
+   _BE_ONLY_(	mov	ip, ip, lsl #24		)
+
+2:		ldrh	r3, [r0]
+		ldrh	r4, [r0]
+		subs	r2, r2, #2
+		orr	ip, ip, r3, lsl #8
+		orr	ip, ip, r4, push_hbyte0
+		str	ip, [r1], #4
+		mov	ip, r4, pull_hbyte1
+		bpl	2b
+
+   _BE_ONLY_(	mov	ip, ip, lsr #24		)
+
+3:		tst	r2, #1
+		strb	ip, [r1], #1
+		ldrneh	ip, [r0]
+   _BE_ONLY_(	movne	ip, ip, ror #8		)
+		strneb	ip, [r1], #1
+   _LE_ONLY_(	movne	ip, ip, lsr #8		)
+   _BE_ONLY_(	movne	ip, ip, lsr #24		)
+		strneb	ip, [r1]
+		ldmfd	sp!, {r4, pc}
diff --git a/arch/arm/lib/io-shark.c b/arch/arm/lib/io-shark.c
new file mode 100644
index 00000000000..108d4573e97
--- /dev/null
+++ b/arch/arm/lib/io-shark.c
@@ -0,0 +1,83 @@
+/*
+ *  linux/arch/arm/lib/io-shark.c
+ *
+ *  by Alexander Schulz
+ *
+ * derived from:
+ * linux/arch/arm/lib/io-ebsa.S
+ * Copyright (C) 1995, 1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+
+#include <asm/io.h>
+
+void print_warning(void)
+{
+	printk(KERN_WARNING "ins?/outs? not implemented on this architecture\n");
+}
+
+void insl(unsigned int port, void *to, int len)
+{
+	print_warning();
+}
+
+void insb(unsigned int port, void *to, int len)
+{
+	print_warning();
+}
+
+void outsl(unsigned int port, const void *from, int len)
+{
+	print_warning();
+}
+
+void outsb(unsigned int port, const void *from, int len)
+{
+	print_warning();
+}
+
+/* these should be in assembler again */
+
+/*
+ * Purpose: read a block of data from a hardware register to memory.
+ * Proto  : insw(int from_port, void *to, int len_in_words);
+ * Proto  : inswb(int from_port, void *to, int len_in_bytes);
+ * Notes  : increment to
+ */
+
+void insw(unsigned int port, void *to, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		((unsigned short *) to)[i] = inw(port);
+}
+
+void inswb(unsigned int port, void *to, int len)
+{
+	insw(port, to, len >> 2);
+}
+
+/*
+ * Purpose: write a block of data from memory to a hardware register.
+ * Proto  : outsw(int to_reg, void *from, int len_in_words);
+ * Proto  : outswb(int to_reg, void *from, int len_in_bytes);
+ * Notes  : increments from
+ */
+
+void outsw(unsigned int port, const void *from, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		outw(((unsigned short *) from)[i], port);
+}
+
+void outswb(unsigned int port, const void *from, int len)
+{
+	outsw(port, from, len >> 2);
+}
diff --git a/arch/arm/lib/io-writesb.S b/arch/arm/lib/io-writesb.S
new file mode 100644
index 00000000000..70b2561bdb0
--- /dev/null
+++ b/arch/arm/lib/io-writesb.S
@@ -0,0 +1,92 @@
+/*
+ *  linux/arch/arm/lib/io-writesb.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.macro	outword, rd
+#ifndef __ARMEB__
+		strb	\rd, [r0]
+		mov	\rd, \rd, lsr #8
+		strb	\rd, [r0]
+		mov	\rd, \rd, lsr #8
+		strb	\rd, [r0]
+		mov	\rd, \rd, lsr #8
+		strb	\rd, [r0]
+#else
+		mov	lr, \rd, lsr #24
+		strb	lr, [r0]
+		mov	lr, \rd, lsr #16
+		strb	lr, [r0]
+		mov	lr, \rd, lsr #8
+		strb	lr, [r0]
+		strb	\rd, [r0]
+#endif
+		.endm
+
+.outsb_align:	rsb	ip, ip, #4
+		cmp	ip, r2
+		movgt	ip, r2
+		cmp	ip, #2
+		ldrb	r3, [r1], #1
+		strb	r3, [r0]
+		ldrgeb	r3, [r1], #1
+		strgeb	r3, [r0]
+		ldrgtb	r3, [r1], #1
+		strgtb	r3, [r0]
+		subs	r2, r2, ip
+		bne	.outsb_aligned
+
+ENTRY(__raw_writesb)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		ands	ip, r1, #3
+		bne	.outsb_align
+
+.outsb_aligned:	stmfd	sp!, {r4, r5, lr}
+
+		subs	r2, r2, #16
+		bmi	.outsb_no_16
+
+.outsb_16_lp:	ldmia	r1!, {r3, r4, r5, ip}
+		outword	r3
+		outword	r4
+		outword	r5
+		outword	ip
+		subs	r2, r2, #16
+		bpl	.outsb_16_lp
+
+		tst	r2, #15
+		LOADREGS(eqfd, sp!, {r4, r5, pc})
+
+.outsb_no_16:	tst	r2, #8
+		beq	.outsb_no_8
+
+		ldmia	r1!, {r3, r4}
+		outword	r3
+		outword	r4
+
+.outsb_no_8:	tst	r2, #4
+		beq	.outsb_no_4
+
+		ldr	r3, [r1], #4
+		outword	r3
+
+.outsb_no_4:	ands	r2, r2, #3
+		LOADREGS(eqfd, sp!, {r4, r5, pc})
+
+		cmp	r2, #2
+		ldrb	r3, [r1], #1
+		strb	r3, [r0]
+		ldrgeb	r3, [r1], #1
+		strgeb	r3, [r0]
+		ldrgtb	r3, [r1]
+		strgtb	r3, [r0]
+
+		LOADREGS(fd, sp!, {r4, r5, pc})
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
new file mode 100644
index 00000000000..f8f14dd227c
--- /dev/null
+++ b/arch/arm/lib/io-writesl.S
@@ -0,0 +1,66 @@
+/*
+ *  linux/arch/arm/lib/io-writesl.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ENTRY(__raw_writesl)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		ands	ip, r1, #3
+		bne	3f
+
+		subs	r2, r2, #4
+		bmi	2f
+		stmfd	sp!, {r4, lr}
+1:		ldmia	r1!, {r3, r4, ip, lr}
+		subs	r2, r2, #4
+		str	r3, [r0, #0]
+		str	r4, [r0, #0]
+		str	ip, [r0, #0]
+		str	lr, [r0, #0]
+		bpl	1b
+		ldmfd	sp!, {r4, lr}
+2:		movs	r2, r2, lsl #31
+		ldmcsia	r1!, {r3, ip}
+		strcs	r3, [r0, #0]
+		ldrne	r3, [r1, #0]
+		strcs	ip, [r0, #0]
+		strne	r3, [r0, #0]
+		mov	pc, lr
+
+3:		bic	r1, r1, #3
+		ldr	r3, [r1], #4
+		cmp	ip, #2
+		blt	5f
+		bgt	6f
+
+4:		mov	ip, r3, pull #16
+		ldr	r3, [r1], #4
+		subs	r2, r2, #1
+		orr	ip, ip, r3, push #16
+		str	ip, [r0]
+		bne	4b
+		mov	pc, lr
+
+5:		mov	ip, r3, pull #8
+		ldr	r3, [r1], #4
+		subs	r2, r2, #1
+		orr	ip, ip, r3, push #24
+		str	ip, [r0]
+		bne	5b
+		mov	pc, lr
+
+6:		mov	ip, r3, pull #24
+		ldr	r3, [r1], #4
+		subs	r2, r2, #1
+		orr	ip, ip, r3, push #8
+		str	ip, [r0]
+		bne	6b
+		mov	pc, lr
diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S
new file mode 100644
index 00000000000..950e7e310f1
--- /dev/null
+++ b/arch/arm/lib/io-writesw-armv3.S
@@ -0,0 +1,127 @@
+/*
+ *  linux/arch/arm/lib/io-writesw-armv3.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/hardware.h>
+
+.outsw_bad_alignment:
+		adr	r0, .outsw_bad_align_msg
+		mov	r2, lr
+		b	panic
+.outsw_bad_align_msg:
+		.asciz	"outsw: bad buffer alignment (0x%p, lr=0x%08lX)\n"
+		.align
+
+.outsw_align:	tst	r1, #1
+		bne	.outsw_bad_alignment
+
+		add	r1, r1, #2
+
+		ldr	r3, [r1, #-4]
+		mov	r3, r3, lsr #16
+		orr	r3, r3, r3, lsl #16
+		str	r3, [r0]
+		subs	r2, r2, #1
+		RETINSTR(moveq, pc, lr)
+
+ENTRY(__raw_writesw)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.outsw_align
+
+.outsw_aligned:	stmfd	sp!, {r4, r5, r6, lr}
+
+		subs	r2, r2, #8
+		bmi	.no_outsw_8
+
+.outsw_8_lp:	ldmia	r1!, {r3, r4, r5, r6}
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r5, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r5, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r6, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r6, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		subs	r2, r2, #8
+		bpl	.outsw_8_lp
+
+		tst	r2, #7
+		LOADREGS(eqfd, sp!, {r4, r5, r6, pc})
+
+.no_outsw_8:	tst	r2, #4
+		beq	.no_outsw_4
+
+		ldmia	r1!, {r3, r4}
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r4, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+.no_outsw_4:	tst	r2, #2
+		beq	.no_outsw_2
+
+		ldr	r3, [r1], #4
+
+		mov	ip, r3, lsl #16
+		orr	ip, ip, ip, lsr #16
+		str	ip, [r0]
+
+		mov	ip, r3, lsr #16
+		orr	ip, ip, ip, lsl #16
+		str	ip, [r0]
+
+.no_outsw_2:	tst	r2, #1
+
+		ldrne	r3, [r1]
+
+		movne	ip, r3, lsl #16
+		orrne	ip, ip, ip, lsr #16
+		strne	ip, [r0]
+
+		LOADREGS(fd, sp!, {r4, r5, r6, pc})
diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S
new file mode 100644
index 00000000000..6d1d7c27806
--- /dev/null
+++ b/arch/arm/lib/io-writesw-armv4.S
@@ -0,0 +1,95 @@
+/*
+ *  linux/arch/arm/lib/io-writesw-armv4.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.macro	outword, rd
+#ifndef __ARMEB__
+		strh	\rd, [r0]
+		mov	\rd, \rd, lsr #16
+		strh	\rd, [r0]
+#else
+		mov	lr, \rd, lsr #16
+		strh	lr, [r0]
+		strh	\rd, [r0]
+#endif
+		.endm
+
+.outsw_align:	movs	ip, r1, lsl #31
+		bne	.outsw_noalign
+
+		ldrh	r3, [r1], #2
+		sub	r2, r2, #1
+		strh	r3, [r0]
+
+ENTRY(__raw_writesw)
+		teq	r2, #0
+		moveq	pc, lr
+		ands	r3, r1, #3
+		bne	.outsw_align
+
+		stmfd	sp!, {r4, r5, lr}
+
+		subs	r2, r2, #8
+		bmi	.no_outsw_8
+
+.outsw_8_lp:	ldmia	r1!, {r3, r4, r5, ip}
+		subs	r2, r2, #8
+		outword	r3
+		outword	r4
+		outword	r5
+		outword	ip
+		bpl	.outsw_8_lp
+
+.no_outsw_8:	tst	r2, #4
+		beq	.no_outsw_4
+
+		ldmia	r1!, {r3, ip}
+		outword	r3
+		outword	ip
+
+.no_outsw_4:	movs	r2, r2, lsl #31
+		bcc	.no_outsw_2
+
+		ldr	r3, [r1], #4
+		outword	r3
+
+.no_outsw_2:	ldrneh	r3, [r1]
+		strneh	r3, [r0]
+
+		ldmfd	sp!, {r4, r5, pc}
+
+#ifdef __ARMEB__
+#define pull_hbyte0	lsl #8
+#define push_hbyte1	lsr #24
+#else
+#define pull_hbyte0	lsr #24
+#define push_hbyte1	lsl #8
+#endif
+
+.outsw_noalign:	ldr	r3, [r1, -r3]!
+		subcs	r2, r2, #1
+		bcs	2f
+		subs	r2, r2, #2
+		bmi	3f
+
+1:		mov	ip, r3, lsr #8
+		strh	ip, [r0]
+2:		mov	ip, r3, pull_hbyte0
+		ldr	r3, [r1, #4]!
+		subs	r2, r2, #2
+		orr	ip, ip, r3, push_hbyte1
+		strh	ip, [r0]
+		bpl	2b
+
+3:		tst	r2, #1
+2:		movne	ip, r3, lsr #8
+		strneh	ip, [r0]
+		mov	pc, lr
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
new file mode 100644
index 00000000000..59026029d01
--- /dev/null
+++ b/arch/arm/lib/lib1funcs.S
@@ -0,0 +1,314 @@
+/*
+ * linux/arch/arm/lib/lib1funcs.S: Optimized ARM division routines
+ *
+ * Author: Nicolas Pitre <nico@cam.org>
+ *   - contributed to gcc-3.4 on Sep 30, 2003
+ *   - adapted for the Linux kernel on Oct 2, 2003
+ */
+
+/* Copyright 1995, 1996, 1998, 1999, 2000, 2003 Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 59 Temple Place - Suite 330,
+Boston, MA 02111-1307, USA.  */
+
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+
+.macro ARM_DIV_BODY dividend, divisor, result, curbit
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	\curbit, \divisor
+	clz	\result, \dividend
+	sub	\result, \curbit, \result
+	mov	\curbit, #1
+	mov	\divisor, \divisor, lsl \result
+	mov	\curbit, \curbit, lsl \result
+	mov	\result, #0
+	
+#else
+
+	@ Initially shift the divisor left 3 bits if possible,
+	@ set curbit accordingly.  This allows for curbit to be located
+	@ at the left end of each 4 bit nibbles in the division loop
+	@ to save one loop in most cases.
+	tst	\divisor, #0xe0000000
+	moveq	\divisor, \divisor, lsl #3
+	moveq	\curbit, #8
+	movne	\curbit, #1
+
+	@ Unless the divisor is very big, shift it up in multiples of
+	@ four bits, since this is the amount of unwinding in the main
+	@ division loop.  Continue shifting until the divisor is 
+	@ larger than the dividend.
+1:	cmp	\divisor, #0x10000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #4
+	movlo	\curbit, \curbit, lsl #4
+	blo	1b
+
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+1:	cmp	\divisor, #0x80000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #1
+	movlo	\curbit, \curbit, lsl #1
+	blo	1b
+
+	mov	\result, #0
+
+#endif
+
+	@ Division loop
+1:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	orrhs	\result,   \result,   \curbit
+	cmp	\dividend, \divisor,  lsr #1
+	subhs	\dividend, \dividend, \divisor, lsr #1
+	orrhs	\result,   \result,   \curbit,  lsr #1
+	cmp	\dividend, \divisor,  lsr #2
+	subhs	\dividend, \dividend, \divisor, lsr #2
+	orrhs	\result,   \result,   \curbit,  lsr #2
+	cmp	\dividend, \divisor,  lsr #3
+	subhs	\dividend, \dividend, \divisor, lsr #3
+	orrhs	\result,   \result,   \curbit,  lsr #3
+	cmp	\dividend, #0			@ Early termination?
+	movnes	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
+	movne	\divisor,  \divisor, lsr #4
+	bne	1b
+
+.endm
+
+
+.macro ARM_DIV2_ORDER divisor, order
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	\order, \divisor
+	rsb	\order, \order, #31
+
+#else
+
+	cmp	\divisor, #(1 << 16)
+	movhs	\divisor, \divisor, lsr #16
+	movhs	\order, #16
+	movlo	\order, #0
+
+	cmp	\divisor, #(1 << 8)
+	movhs	\divisor, \divisor, lsr #8
+	addhs	\order, \order, #8
+
+	cmp	\divisor, #(1 << 4)
+	movhs	\divisor, \divisor, lsr #4
+	addhs	\order, \order, #4
+
+	cmp	\divisor, #(1 << 2)
+	addhi	\order, \order, #3
+	addls	\order, \order, \divisor, lsr #1
+
+#endif
+
+.endm
+
+
+.macro ARM_MOD_BODY dividend, divisor, order, spare
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	\order, \divisor
+	clz	\spare, \dividend
+	sub	\order, \order, \spare
+	mov	\divisor, \divisor, lsl \order
+
+#else
+
+	mov	\order, #0
+
+	@ Unless the divisor is very big, shift it up in multiples of
+	@ four bits, since this is the amount of unwinding in the main
+	@ division loop.  Continue shifting until the divisor is 
+	@ larger than the dividend.
+1:	cmp	\divisor, #0x10000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #4
+	addlo	\order, \order, #4
+	blo	1b
+
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+1:	cmp	\divisor, #0x80000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #1
+	addlo	\order, \order, #1
+	blo	1b
+
+#endif
+
+	@ Perform all needed substractions to keep only the reminder.
+	@ Do comparisons in batch of 4 first.
+	subs	\order, \order, #3		@ yes, 3 is intended here
+	blt	2f
+
+1:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	cmp	\dividend, \divisor,  lsr #1
+	subhs	\dividend, \dividend, \divisor, lsr #1
+	cmp	\dividend, \divisor,  lsr #2
+	subhs	\dividend, \dividend, \divisor, lsr #2
+	cmp	\dividend, \divisor,  lsr #3
+	subhs	\dividend, \dividend, \divisor, lsr #3
+	cmp	\dividend, #1
+	mov	\divisor, \divisor, lsr #4
+	subges	\order, \order, #4
+	bge	1b
+
+	tst	\order, #3
+	teqne	\dividend, #0
+	beq	5f
+
+	@ Either 1, 2 or 3 comparison/substractions are left.
+2:	cmn	\order, #2
+	blt	4f
+	beq	3f
+	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	mov	\divisor,  \divisor,  lsr #1
+3:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	mov	\divisor,  \divisor,  lsr #1
+4:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+5:
+.endm
+
+
+ENTRY(__udivsi3)
+
+	subs	r2, r1, #1
+	moveq	pc, lr
+	bcc	Ldiv0
+	cmp	r0, r1
+	bls	11f
+	tst	r1, r2
+	beq	12f
+
+	ARM_DIV_BODY r0, r1, r2, r3
+
+	mov	r0, r2
+	mov	pc, lr
+
+11:	moveq	r0, #1
+	movne	r0, #0
+	mov	pc, lr
+
+12:	ARM_DIV2_ORDER r1, r2
+
+	mov	r0, r0, lsr r2
+	mov	pc, lr
+
+
+ENTRY(__umodsi3)
+
+	subs	r2, r1, #1			@ compare divisor with 1
+	bcc	Ldiv0
+	cmpne	r0, r1				@ compare dividend with divisor
+	moveq   r0, #0
+	tsthi	r1, r2				@ see if divisor is power of 2
+	andeq	r0, r0, r2
+	movls	pc, lr
+
+	ARM_MOD_BODY r0, r1, r2, r3
+
+	mov	pc, lr
+
+
+ENTRY(__divsi3)
+
+	cmp	r1, #0
+	eor	ip, r0, r1			@ save the sign of the result.
+	beq	Ldiv0
+	rsbmi	r1, r1, #0			@ loops below use unsigned.
+	subs	r2, r1, #1			@ division by 1 or -1 ?
+	beq	10f
+	movs	r3, r0
+	rsbmi	r3, r0, #0			@ positive dividend value
+	cmp	r3, r1
+	bls	11f
+	tst	r1, r2				@ divisor is power of 2 ?
+	beq	12f
+
+	ARM_DIV_BODY r3, r1, r0, r2
+
+	cmp	ip, #0
+	rsbmi	r0, r0, #0
+	mov	pc, lr
+
+10:	teq	ip, r0				@ same sign ?
+	rsbmi	r0, r0, #0
+	mov	pc, lr
+
+11:	movlo	r0, #0
+	moveq	r0, ip, asr #31
+	orreq	r0, r0, #1
+	mov	pc, lr
+
+12:	ARM_DIV2_ORDER r1, r2
+
+	cmp	ip, #0
+	mov	r0, r3, lsr r2
+	rsbmi	r0, r0, #0
+	mov	pc, lr
+
+
+ENTRY(__modsi3)
+
+	cmp	r1, #0
+	beq	Ldiv0
+	rsbmi	r1, r1, #0			@ loops below use unsigned.
+	movs	ip, r0				@ preserve sign of dividend
+	rsbmi	r0, r0, #0			@ if negative make positive
+	subs	r2, r1, #1			@ compare divisor with 1
+	cmpne	r0, r1				@ compare dividend with divisor
+	moveq	r0, #0
+	tsthi	r1, r2				@ see if divisor is power of 2
+	andeq	r0, r0, r2
+	bls	10f
+
+	ARM_MOD_BODY r0, r1, r2, r3
+
+10:	cmp	ip, #0
+	rsbmi	r0, r0, #0
+	mov	pc, lr
+
+
+Ldiv0:
+
+	str	lr, [sp, #-4]!
+	bl	__div0
+	mov	r0, #0			@ About as wrong as it could be.
+	ldr	pc, [sp], #4
+
+
diff --git a/arch/arm/lib/longlong.h b/arch/arm/lib/longlong.h
new file mode 100644
index 00000000000..179eea4edc3
--- /dev/null
+++ b/arch/arm/lib/longlong.h
@@ -0,0 +1,183 @@
+/* longlong.h -- based on code from gcc-2.95.3
+
+   definitions for mixed size 32/64 bit arithmetic.
+   Copyright (C) 1991, 92, 94, 95, 96, 1997, 1998 Free Software Foundation, Inc.
+
+   This definition file is free software; you can redistribute it
+   and/or modify it under the terms of the GNU General Public
+   License as published by the Free Software Foundation; either
+   version 2, or (at your option) any later version.
+
+   This definition file is distributed in the hope that it will be
+   useful, but WITHOUT ANY WARRANTY; without even the implied
+   warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+   See the GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; if not, write to the Free Software
+   Foundation, Inc., 59 Temple Place - Suite 330,
+   Boston, MA 02111-1307, USA.  */
+
+/* Borrowed from GCC 2.95.3, I Molton 29/07/01 */
+
+#ifndef SI_TYPE_SIZE
+#define SI_TYPE_SIZE 32
+#endif
+
+#define __BITS4 (SI_TYPE_SIZE / 4)
+#define __ll_B (1L << (SI_TYPE_SIZE / 2))
+#define __ll_lowpart(t) ((USItype) (t) % __ll_B)
+#define __ll_highpart(t) ((USItype) (t) / __ll_B)
+
+/* Define auxiliary asm macros.
+
+   1) umul_ppmm(high_prod, low_prod, multipler, multiplicand)
+   multiplies two USItype integers MULTIPLER and MULTIPLICAND,
+   and generates a two-part USItype product in HIGH_PROD and
+   LOW_PROD.
+
+   2) __umulsidi3(a,b) multiplies two USItype integers A and B,
+   and returns a UDItype product.  This is just a variant of umul_ppmm.
+
+   3) udiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
+   denominator) divides a two-word unsigned integer, composed by the
+   integers HIGH_NUMERATOR and LOW_NUMERATOR, by DENOMINATOR and
+   places the quotient in QUOTIENT and the remainder in REMAINDER.
+   HIGH_NUMERATOR must be less than DENOMINATOR for correct operation.
+   If, in addition, the most significant bit of DENOMINATOR must be 1,
+   then the pre-processor symbol UDIV_NEEDS_NORMALIZATION is defined to 1.
+
+   4) sdiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
+   denominator).  Like udiv_qrnnd but the numbers are signed.  The
+   quotient is rounded towards 0.
+
+   5) count_leading_zeros(count, x) counts the number of zero-bits from
+   the msb to the first non-zero bit.  This is the number of steps X
+   needs to be shifted left to set the msb.  Undefined for X == 0.
+
+   6) add_ssaaaa(high_sum, low_sum, high_addend_1, low_addend_1,
+   high_addend_2, low_addend_2) adds two two-word unsigned integers,
+   composed by HIGH_ADDEND_1 and LOW_ADDEND_1, and HIGH_ADDEND_2 and
+   LOW_ADDEND_2 respectively.  The result is placed in HIGH_SUM and
+   LOW_SUM.  Overflow (i.e. carry out) is not stored anywhere, and is
+   lost.
+
+   7) sub_ddmmss(high_difference, low_difference, high_minuend,
+   low_minuend, high_subtrahend, low_subtrahend) subtracts two
+   two-word unsigned integers, composed by HIGH_MINUEND_1 and
+   LOW_MINUEND_1, and HIGH_SUBTRAHEND_2 and LOW_SUBTRAHEND_2
+   respectively.  The result is placed in HIGH_DIFFERENCE and
+   LOW_DIFFERENCE.  Overflow (i.e. carry out) is not stored anywhere,
+   and is lost.
+
+   If any of these macros are left undefined for a particular CPU,
+   C macros are used.  */
+
+#if defined (__arm__)
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+  __asm__ ("adds	%1, %4, %5					\n\
+	adc	%0, %2, %3"						\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "%r" ((USItype) (ah)),					\
+	     "rI" ((USItype) (bh)),					\
+	     "%r" ((USItype) (al)),					\
+	     "rI" ((USItype) (bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+  __asm__ ("subs	%1, %4, %5					\n\
+	sbc	%0, %2, %3"						\
+	   : "=r" ((USItype) (sh)),					\
+	     "=&r" ((USItype) (sl))					\
+	   : "r" ((USItype) (ah)),					\
+	     "rI" ((USItype) (bh)),					\
+	     "r" ((USItype) (al)),					\
+	     "rI" ((USItype) (bl)))
+#define umul_ppmm(xh, xl, a, b) \
+{register USItype __t0, __t1, __t2;					\
+  __asm__ ("%@ Inlined umul_ppmm					\n\
+	mov	%2, %5, lsr #16						\n\
+	mov	%0, %6, lsr #16						\n\
+	bic	%3, %5, %2, lsl #16					\n\
+	bic	%4, %6, %0, lsl #16					\n\
+	mul	%1, %3, %4						\n\
+	mul	%4, %2, %4						\n\
+	mul	%3, %0, %3						\n\
+	mul	%0, %2, %0						\n\
+	adds	%3, %4, %3						\n\
+	addcs	%0, %0, #65536						\n\
+	adds	%1, %1, %3, lsl #16					\n\
+	adc	%0, %0, %3, lsr #16"					\
+	   : "=&r" ((USItype) (xh)),					\
+	     "=r" ((USItype) (xl)),					\
+	     "=&r" (__t0), "=&r" (__t1), "=r" (__t2)			\
+	   : "r" ((USItype) (a)),					\
+	     "r" ((USItype) (b)));}
+#define UMUL_TIME 20
+#define UDIV_TIME 100
+#endif /* __arm__ */
+
+#define __umulsidi3(u, v) \
+  ({DIunion __w;							\
+    umul_ppmm (__w.s.high, __w.s.low, u, v);				\
+    __w.ll; })
+
+#define __udiv_qrnnd_c(q, r, n1, n0, d) \
+  do {									\
+    USItype __d1, __d0, __q1, __q0;					\
+    USItype __r1, __r0, __m;						\
+    __d1 = __ll_highpart (d);						\
+    __d0 = __ll_lowpart (d);						\
+									\
+    __r1 = (n1) % __d1;							\
+    __q1 = (n1) / __d1;							\
+    __m = (USItype) __q1 * __d0;					\
+    __r1 = __r1 * __ll_B | __ll_highpart (n0);				\
+    if (__r1 < __m)							\
+      {									\
+	__q1--, __r1 += (d);						\
+	if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\
+	  if (__r1 < __m)						\
+	    __q1--, __r1 += (d);					\
+      }									\
+    __r1 -= __m;							\
+									\
+    __r0 = __r1 % __d1;							\
+    __q0 = __r1 / __d1;							\
+    __m = (USItype) __q0 * __d0;					\
+    __r0 = __r0 * __ll_B | __ll_lowpart (n0);				\
+    if (__r0 < __m)							\
+      {									\
+	__q0--, __r0 += (d);						\
+	if (__r0 >= (d))						\
+	  if (__r0 < __m)						\
+	    __q0--, __r0 += (d);					\
+      }									\
+    __r0 -= __m;							\
+									\
+    (q) = (USItype) __q1 * __ll_B | __q0;				\
+    (r) = __r0;								\
+  } while (0)
+
+#define UDIV_NEEDS_NORMALIZATION 1
+#define udiv_qrnnd __udiv_qrnnd_c
+
+#define count_leading_zeros(count, x) \
+  do {									\
+    USItype __xr = (x);							\
+    USItype __a;							\
+									\
+    if (SI_TYPE_SIZE <= 32)						\
+      {									\
+	__a = __xr < ((USItype)1<<2*__BITS4)				\
+	  ? (__xr < ((USItype)1<<__BITS4) ? 0 : __BITS4)		\
+	  : (__xr < ((USItype)1<<3*__BITS4) ?  2*__BITS4 : 3*__BITS4);	\
+      }									\
+    else								\
+      {									\
+	for (__a = SI_TYPE_SIZE - 8; __a > 0; __a -= 8)			\
+	  if (((__xr >> __a) & 0xff) != 0)				\
+	    break;							\
+      }									\
+									\
+    (count) = SI_TYPE_SIZE - (__clz_tab[__xr >> __a] + __a);		\
+  } while (0)
diff --git a/arch/arm/lib/lshrdi3.c b/arch/arm/lib/lshrdi3.c
new file mode 100644
index 00000000000..b666f1bad45
--- /dev/null
+++ b/arch/arm/lib/lshrdi3.c
@@ -0,0 +1,61 @@
+/* More subroutines needed by GCC output code on some machines.  */
+/* Compile this one with gcc.  */
+/* Copyright (C) 1989, 92-98, 1999 Free Software Foundation, Inc.
+
+This file is part of GNU CC.
+
+GNU CC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 2, or (at your option)
+any later version.
+
+GNU CC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with GNU CC; see the file COPYING.  If not, write to
+the Free Software Foundation, 59 Temple Place - Suite 330,
+Boston, MA 02111-1307, USA.  */
+
+/* As a special exception, if you link this library with other files,
+   some of which are compiled with GCC, to produce an executable,
+   this library does not by itself cause the resulting executable
+   to be covered by the GNU General Public License.
+   This exception does not however invalidate any other reasons why
+   the executable file might be covered by the GNU General Public License.
+ */
+/* support functions required by the kernel. based on code from gcc-2.95.3 */
+/* I Molton     29/07/01 */
+
+#include "gcclib.h"
+
+DItype
+__lshrdi3 (DItype u, word_type b)
+{
+  DIunion w;
+  word_type bm;
+  DIunion uu;
+
+  if (b == 0)
+    return u;
+
+  uu.ll = u;
+
+  bm = (sizeof (SItype) * BITS_PER_UNIT) - b;
+  if (bm <= 0)
+    {
+      w.s.high = 0;
+      w.s.low = (USItype)uu.s.high >> -bm;
+    }
+  else
+    {
+      USItype carries = (USItype)uu.s.high << bm;
+      w.s.high = (USItype)uu.s.high >> b;
+      w.s.low = ((USItype)uu.s.low >> b) | carries;
+    }
+
+  return w.ll;
+}
+
diff --git a/arch/arm/lib/memchr.S b/arch/arm/lib/memchr.S
new file mode 100644
index 00000000000..ac34fe55d21
--- /dev/null
+++ b/arch/arm/lib/memchr.S
@@ -0,0 +1,25 @@
+/*
+ *  linux/arch/arm/lib/memchr.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  ASM optimised string functions
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.align	5
+ENTRY(memchr)
+1:	subs	r2, r2, #1
+	bmi	2f
+	ldrb	r3, [r0], #1
+	teq	r3, r1
+	bne	1b
+	sub	r0, r0, #1
+2:	movne	r0, #0
+	RETINSTR(mov,pc,lr)
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
new file mode 100644
index 00000000000..f5a593ceb8c
--- /dev/null
+++ b/arch/arm/lib/memcpy.S
@@ -0,0 +1,393 @@
+/*
+ *  linux/arch/arm/lib/memcpy.S
+ *
+ *  Copyright (C) 1995-1999 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  ASM optimised string functions
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.text
+
+#define ENTER	\
+		mov	ip,sp	;\
+		stmfd	sp!,{r0,r4-r9,fp,ip,lr,pc}	;\
+		sub	fp,ip,#4
+
+#define EXIT	\
+		LOADREGS(ea, fp, {r0, r4 - r9, fp, sp, pc})
+
+#define EXITEQ	\
+		LOADREGS(eqea, fp, {r0, r4 - r9, fp, sp, pc})
+
+/*
+ * Prototype: void memcpy(void *to,const void *from,unsigned long n);
+ */
+ENTRY(memcpy)
+ENTRY(memmove)
+		ENTER
+		cmp	r1, r0
+		bcc	23f
+		subs	r2, r2, #4
+		blt	6f
+	PLD(	pld	[r1, #0]		)
+		ands	ip, r0, #3
+		bne	7f
+		ands	ip, r1, #3
+		bne	8f
+
+1:		subs	r2, r2, #8
+		blt	5f
+		subs	r2, r2, #20
+		blt	4f
+	PLD(	pld	[r1, #28]		)
+	PLD(	subs	r2, r2, #64		)
+	PLD(	blt	3f			)
+2:	PLD(	pld	[r1, #60]		)
+	PLD(	pld	[r1, #92]		)
+		ldmia	r1!, {r3 - r9, ip}
+		subs	r2, r2, #32
+		stmgeia	r0!, {r3 - r9, ip}
+		ldmgeia	r1!, {r3 - r9, ip}
+		subges	r2, r2, #32
+		stmia	r0!, {r3 - r9, ip}
+		bge	2b
+3:	PLD(	ldmia	r1!, {r3 - r9, ip}	)
+	PLD(	adds	r2, r2, #32		)
+	PLD(	stmgeia	r0!, {r3 - r9, ip}	)
+	PLD(	ldmgeia	r1!, {r3 - r9, ip}	)
+	PLD(	subges	r2, r2, #32		)
+	PLD(	stmia	r0!, {r3 - r9, ip}	)
+4:		cmn	r2, #16
+		ldmgeia	r1!, {r3 - r6}
+		subge	r2, r2, #16
+		stmgeia	r0!, {r3 - r6}
+		adds	r2, r2, #20
+		ldmgeia	r1!, {r3 - r5}
+		subge	r2, r2, #12
+		stmgeia	r0!, {r3 - r5}
+5:		adds	r2, r2, #8
+		blt	6f
+		subs	r2, r2, #4
+		ldrlt	r3, [r1], #4
+		ldmgeia	r1!, {r4, r5}
+		subge	r2, r2, #4
+		strlt	r3, [r0], #4
+		stmgeia	r0!, {r4, r5}
+
+6:		adds	r2, r2, #4
+		EXITEQ
+		cmp	r2, #2
+		ldrb	r3, [r1], #1
+		ldrgeb	r4, [r1], #1
+		ldrgtb	r5, [r1], #1
+		strb	r3, [r0], #1
+		strgeb	r4, [r0], #1
+		strgtb	r5, [r0], #1
+		EXIT
+
+7:		rsb	ip, ip, #4
+		cmp	ip, #2
+		ldrb	r3, [r1], #1
+		ldrgeb	r4, [r1], #1
+		ldrgtb	r5, [r1], #1
+		strb	r3, [r0], #1
+		strgeb	r4, [r0], #1
+		strgtb	r5, [r0], #1
+		subs	r2, r2, ip
+		blt	6b
+		ands	ip, r1, #3
+		beq	1b
+
+8:		bic	r1, r1, #3
+		ldr	r7, [r1], #4
+		cmp	ip, #2
+		bgt	18f
+		beq	13f
+		cmp	r2, #12
+		blt	11f
+	PLD(	pld	[r1, #12]		)
+		sub	r2, r2, #12
+	PLD(	subs	r2, r2, #32		)
+	PLD(	blt	10f			)
+	PLD(	pld	[r1, #28]		)
+9:	PLD(	pld	[r1, #44]		)
+10:		mov	r3, r7, pull #8
+		ldmia	r1!, {r4 - r7}
+		subs	r2, r2, #16
+		orr	r3, r3, r4, push #24
+		mov	r4, r4, pull #8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		stmia	r0!, {r3 - r6}
+		bge	9b
+	PLD(	cmn	r2, #32			)
+	PLD(	bge	10b			)
+	PLD(	add	r2, r2, #32		)
+		adds	r2, r2, #12
+		blt	12f
+11:		mov	r3, r7, pull #8
+		ldr	r7, [r1], #4
+		subs	r2, r2, #4
+		orr	r3, r3, r7, push #24
+		str	r3, [r0], #4
+		bge	11b
+12:		sub	r1, r1, #3
+		b	6b
+
+13:		cmp	r2, #12
+		blt	16f
+	PLD(	pld	[r1, #12]		)
+		sub	r2, r2, #12
+	PLD(	subs	r2, r2, #32		)
+	PLD(	blt	15f			)
+	PLD(	pld	[r1, #28]		)
+14:	PLD(	pld	[r1, #44]		)
+15:		mov	r3, r7, pull #16
+		ldmia	r1!, {r4 - r7}
+		subs	r2, r2, #16
+		orr	r3, r3, r4, push #16
+		mov	r4, r4, pull #16
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		stmia	r0!, {r3 - r6}
+		bge	14b
+	PLD(	cmn	r2, #32			)
+	PLD(	bge	15b			)
+	PLD(	add	r2, r2, #32		)
+		adds	r2, r2, #12
+		blt	17f
+16:		mov	r3, r7, pull #16
+		ldr	r7, [r1], #4
+		subs	r2, r2, #4
+		orr	r3, r3, r7, push #16
+		str	r3, [r0], #4
+		bge	16b
+17:		sub	r1, r1, #2
+		b	6b
+
+18:		cmp	r2, #12
+		blt	21f
+	PLD(	pld	[r1, #12]		)
+		sub	r2, r2, #12
+	PLD(	subs	r2, r2, #32		)
+	PLD(	blt	20f			)
+	PLD(	pld	[r1, #28]		)
+19:	PLD(	pld	[r1, #44]		)
+20:		mov	r3, r7, pull #24
+		ldmia	r1!, {r4 - r7}
+		subs	r2, r2, #16
+		orr	r3, r3, r4, push #8
+		mov	r4, r4, pull #24
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		stmia	r0!, {r3 - r6}
+		bge	19b
+	PLD(	cmn	r2, #32			)
+	PLD(	bge	20b			)
+	PLD(	add	r2, r2, #32		)
+		adds	r2, r2, #12
+		blt	22f
+21:		mov	r3, r7, pull #24
+		ldr	r7, [r1], #4
+		subs	r2, r2, #4
+		orr	r3, r3, r7, push #8
+		str	r3, [r0], #4
+		bge	21b
+22:		sub	r1, r1, #1
+		b	6b
+
+
+23:		add	r1, r1, r2
+		add	r0, r0, r2
+		subs	r2, r2, #4
+		blt	29f
+	PLD(	pld	[r1, #-4]		)
+		ands	ip, r0, #3
+		bne	30f
+		ands	ip, r1, #3
+		bne	31f
+
+24:		subs	r2, r2, #8
+		blt	28f
+		subs	r2, r2, #20
+		blt	27f
+	PLD(	pld	[r1, #-32]		)
+	PLD(	subs	r2, r2, #64		)
+	PLD(	blt	26f			)
+25:	PLD(	pld	[r1, #-64]		)
+	PLD(	pld	[r1, #-96]		)
+		ldmdb	r1!, {r3 - r9, ip}
+		subs	r2, r2, #32
+		stmgedb	r0!, {r3 - r9, ip}
+		ldmgedb	r1!, {r3 - r9, ip}
+		subges	r2, r2, #32
+		stmdb	r0!, {r3 - r9, ip}
+		bge	25b
+26:	PLD(	ldmdb	r1!, {r3 - r9, ip}	)
+	PLD(	adds	r2, r2, #32		)
+	PLD(	stmgedb	r0!, {r3 - r9, ip}	)
+	PLD(	ldmgedb	r1!, {r3 - r9, ip}	)
+	PLD(	subges	r2, r2, #32		)
+	PLD(	stmdb	r0!, {r3 - r9, ip}	)
+27:		cmn	r2, #16
+		ldmgedb	r1!, {r3 - r6}
+		subge	r2, r2, #16
+		stmgedb	r0!, {r3 - r6}
+		adds	r2, r2, #20
+		ldmgedb	r1!, {r3 - r5}
+		subge	r2, r2, #12
+		stmgedb	r0!, {r3 - r5}
+28:		adds	r2, r2, #8
+		blt	29f
+		subs	r2, r2, #4
+		ldrlt	r3, [r1, #-4]!
+		ldmgedb	r1!, {r4, r5}
+		subge	r2, r2, #4
+		strlt	r3, [r0, #-4]!
+		stmgedb	r0!, {r4, r5}
+
+29:		adds	r2, r2, #4
+		EXITEQ
+		cmp	r2, #2
+		ldrb	r3, [r1, #-1]!
+		ldrgeb	r4, [r1, #-1]!
+		ldrgtb	r5, [r1, #-1]!
+		strb	r3, [r0, #-1]!
+		strgeb	r4, [r0, #-1]!
+		strgtb	r5, [r0, #-1]!
+		EXIT
+
+30:		cmp	ip, #2
+		ldrb	r3, [r1, #-1]!
+		ldrgeb	r4, [r1, #-1]!
+		ldrgtb	r5, [r1, #-1]!
+		strb	r3, [r0, #-1]!
+		strgeb	r4, [r0, #-1]!
+		strgtb	r5, [r0, #-1]!
+		subs	r2, r2, ip
+		blt	29b
+		ands	ip, r1, #3
+		beq	24b
+
+31:		bic	r1, r1, #3
+		ldr	r3, [r1], #0
+		cmp	ip, #2
+		blt	41f
+		beq	36f
+		cmp	r2, #12
+		blt	34f
+	PLD(	pld	[r1, #-16]		)
+		sub	r2, r2, #12
+	PLD(	subs	r2, r2, #32		)
+	PLD(	blt	33f			)
+	PLD(	pld	[r1, #-32]		)
+32:	PLD(	pld	[r1, #-48]		)
+33:		mov	r7, r3, push #8
+		ldmdb	r1!, {r3, r4, r5, r6}
+		subs	r2, r2, #16
+		orr	r7, r7, r6, pull #24
+		mov	r6, r6, push #8
+		orr	r6, r6, r5, pull #24
+		mov	r5, r5, push #8
+		orr	r5, r5, r4, pull #24
+		mov	r4, r4, push #8
+		orr	r4, r4, r3, pull #24
+		stmdb	r0!, {r4, r5, r6, r7}
+		bge	32b
+	PLD(	cmn	r2, #32			)
+	PLD(	bge	33b			)
+	PLD(	add	r2, r2, #32		)
+		adds	r2, r2, #12
+		blt	35f
+34:		mov	ip, r3, push #8
+		ldr	r3, [r1, #-4]!
+		subs	r2, r2, #4
+		orr	ip, ip, r3, pull #24
+		str	ip, [r0, #-4]!
+		bge	34b
+35:		add	r1, r1, #3
+		b	29b
+
+36:		cmp	r2, #12
+		blt	39f
+	PLD(	pld	[r1, #-16]		)
+		sub	r2, r2, #12
+	PLD(	subs	r2, r2, #32		)
+	PLD(	blt	38f			)
+	PLD(	pld	[r1, #-32]		)
+37:	PLD(	pld	[r1, #-48]		)
+38:		mov	r7, r3, push #16
+		ldmdb	r1!, {r3, r4, r5, r6}
+		subs	r2, r2, #16
+		orr	r7, r7, r6, pull #16
+		mov	r6, r6, push #16
+		orr	r6, r6, r5, pull #16
+		mov	r5, r5, push #16
+		orr	r5, r5, r4, pull #16
+		mov	r4, r4, push #16
+		orr	r4, r4, r3, pull #16
+		stmdb	r0!, {r4, r5, r6, r7}
+		bge	37b
+	PLD(	cmn	r2, #32			)
+	PLD(	bge	38b			)
+	PLD(	add	r2, r2, #32		)
+		adds	r2, r2, #12
+		blt	40f
+39:		mov	ip, r3, push #16
+		ldr	r3, [r1, #-4]!
+		subs	r2, r2, #4
+		orr	ip, ip, r3, pull #16
+		str	ip, [r0, #-4]!
+		bge	39b
+40:		add	r1, r1, #2
+		b	29b
+
+41:		cmp	r2, #12
+		blt	44f
+	PLD(	pld	[r1, #-16]		)
+		sub	r2, r2, #12
+	PLD(	subs	r2, r2, #32		)
+	PLD(	blt	43f			)
+	PLD(	pld	[r1, #-32]		)
+42:	PLD(	pld	[r1, #-48]		)
+43:		mov	r7, r3, push #24
+		ldmdb	r1!, {r3, r4, r5, r6}
+		subs	r2, r2, #16
+		orr	r7, r7, r6, pull #8
+		mov	r6, r6, push #24
+		orr	r6, r6, r5, pull #8
+		mov	r5, r5, push #24
+		orr	r5, r5, r4, pull #8
+		mov	r4, r4, push #24
+		orr	r4, r4, r3, pull #8
+		stmdb	r0!, {r4, r5, r6, r7}
+		bge	42b
+	PLD(	cmn	r2, #32			)
+	PLD(	bge	43b			)
+	PLD(	add	r2, r2, #32		)
+		adds	r2, r2, #12
+		blt	45f
+44:		mov	ip, r3, push #24
+		ldr	r3, [r1, #-4]!
+		subs	r2, r2, #4
+		orr	ip, ip, r3, pull #8
+		str	ip, [r0, #-4]!
+		bge	44b
+45:		add	r1, r1, #1
+		b	29b
+
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
new file mode 100644
index 00000000000..a1795f59993
--- /dev/null
+++ b/arch/arm/lib/memset.S
@@ -0,0 +1,80 @@
+/*
+ *  linux/arch/arm/lib/memset.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  ASM optimised string functions
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.align	5
+	.word	0
+
+1:	subs	r2, r2, #4		@ 1 do we have enough
+	blt	5f			@ 1 bytes to align with?
+	cmp	r3, #2			@ 1
+	strltb	r1, [r0], #1		@ 1
+	strleb	r1, [r0], #1		@ 1
+	strb	r1, [r0], #1		@ 1
+	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
+/*
+ * The pointer is now aligned and the length is adjusted.  Try doing the
+ * memzero again.
+ */
+
+ENTRY(memset)
+	ands	r3, r0, #3		@ 1 unaligned?
+	bne	1b			@ 1
+/*
+ * we know that the pointer in r0 is aligned to a word boundary.
+ */
+	orr	r1, r1, r1, lsl #8
+	orr	r1, r1, r1, lsl #16
+	mov	r3, r1
+	cmp	r2, #16
+	blt	4f
+/*
+ * We need an extra register for this loop - save the return address and
+ * use the LR
+ */
+	str	lr, [sp, #-4]!
+	mov	ip, r1
+	mov	lr, r1
+
+2:	subs	r2, r2, #64
+	stmgeia	r0!, {r1, r3, ip, lr}	@ 64 bytes at a time.
+	stmgeia	r0!, {r1, r3, ip, lr}
+	stmgeia	r0!, {r1, r3, ip, lr}
+	stmgeia	r0!, {r1, r3, ip, lr}
+	bgt	2b
+	LOADREGS(eqfd, sp!, {pc})	@ Now <64 bytes to go.
+/*
+ * No need to correct the count; we're only testing bits from now on
+ */
+	tst	r2, #32
+	stmneia	r0!, {r1, r3, ip, lr}
+	stmneia	r0!, {r1, r3, ip, lr}
+	tst	r2, #16
+	stmneia	r0!, {r1, r3, ip, lr}
+	ldr	lr, [sp], #4
+
+4:	tst	r2, #8
+	stmneia	r0!, {r1, r3}
+	tst	r2, #4
+	strne	r1, [r0], #4
+/*
+ * When we get here, we've got less than 4 bytes to zero.  We
+ * may have an unaligned pointer as well.
+ */
+5:	tst	r2, #2
+	strneb	r1, [r0], #1
+	strneb	r1, [r0], #1
+	tst	r2, #1
+	strneb	r1, [r0], #1
+	RETINSTR(mov,pc,lr)
diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S
new file mode 100644
index 00000000000..51ccc60160f
--- /dev/null
+++ b/arch/arm/lib/memzero.S
@@ -0,0 +1,80 @@
+/*
+ *  linux/arch/arm/lib/memzero.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.align	5
+	.word	0
+/*
+ * Align the pointer in r0.  r3 contains the number of bytes that we are
+ * mis-aligned by, and r1 is the number of bytes.  If r1 < 4, then we
+ * don't bother; we use byte stores instead.
+ */
+1:	subs	r1, r1, #4		@ 1 do we have enough
+	blt	5f			@ 1 bytes to align with?
+	cmp	r3, #2			@ 1
+	strltb	r2, [r0], #1		@ 1
+	strleb	r2, [r0], #1		@ 1
+	strb	r2, [r0], #1		@ 1
+	add	r1, r1, r3		@ 1 (r1 = r1 - (4 - r3))
+/*
+ * The pointer is now aligned and the length is adjusted.  Try doing the
+ * memzero again.
+ */
+
+ENTRY(__memzero)
+	mov	r2, #0			@ 1
+	ands	r3, r0, #3		@ 1 unaligned?
+	bne	1b			@ 1
+/*
+ * r3 = 0, and we know that the pointer in r0 is aligned to a word boundary.
+ */
+	cmp	r1, #16			@ 1 we can skip this chunk if we
+	blt	4f			@ 1 have < 16 bytes
+/*
+ * We need an extra register for this loop - save the return address and
+ * use the LR
+ */
+	str	lr, [sp, #-4]!		@ 1
+	mov	ip, r2			@ 1
+	mov	lr, r2			@ 1
+
+3:	subs	r1, r1, #64		@ 1 write 32 bytes out per loop
+	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
+	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
+	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
+	stmgeia	r0!, {r2, r3, ip, lr}	@ 4
+	bgt	3b			@ 1
+	LOADREGS(eqfd, sp!, {pc})	@ 1/2 quick exit
+/*
+ * No need to correct the count; we're only testing bits from now on
+ */
+	tst	r1, #32			@ 1
+	stmneia	r0!, {r2, r3, ip, lr}	@ 4
+	stmneia	r0!, {r2, r3, ip, lr}	@ 4
+	tst	r1, #16			@ 1 16 bytes or more?
+	stmneia	r0!, {r2, r3, ip, lr}	@ 4
+	ldr	lr, [sp], #4		@ 1
+
+4:	tst	r1, #8			@ 1 8 bytes or more?
+	stmneia	r0!, {r2, r3}		@ 2
+	tst	r1, #4			@ 1 4 bytes or more?
+	strne	r2, [r0], #4		@ 1
+/*
+ * When we get here, we've got less than 4 bytes to zero.  We
+ * may have an unaligned pointer as well.
+ */
+5:	tst	r1, #2			@ 1 2 bytes or more?
+	strneb	r2, [r0], #1		@ 1
+	strneb	r2, [r0], #1		@ 1
+	tst	r1, #1			@ 1 a byte left over
+	strneb	r2, [r0], #1		@ 1
+	RETINSTR(mov,pc,lr)		@ 1
diff --git a/arch/arm/lib/muldi3.c b/arch/arm/lib/muldi3.c
new file mode 100644
index 00000000000..44d611b1cfd
--- /dev/null
+++ b/arch/arm/lib/muldi3.c
@@ -0,0 +1,77 @@
+/* More subroutines needed by GCC output code on some machines.  */
+/* Compile this one with gcc.  */
+/* Copyright (C) 1989, 92-98, 1999 Free Software Foundation, Inc.
+
+This file is part of GNU CC.
+
+GNU CC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 2, or (at your option)
+any later version.
+
+GNU CC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with GNU CC; see the file COPYING.  If not, write to
+the Free Software Foundation, 59 Temple Place - Suite 330,
+Boston, MA 02111-1307, USA.  */
+
+/* As a special exception, if you link this library with other files,
+   some of which are compiled with GCC, to produce an executable,
+   this library does not by itself cause the resulting executable
+   to be covered by the GNU General Public License.
+   This exception does not however invalidate any other reasons why
+   the executable file might be covered by the GNU General Public License.
+ */
+/* support functions required by the kernel. based on code from gcc-2.95.3 */
+/* I Molton     29/07/01 */
+
+#include "gcclib.h"
+
+#define umul_ppmm(xh, xl, a, b) \
+{register USItype __t0, __t1, __t2;                                     \
+  __asm__ ("%@ Inlined umul_ppmm					\n\
+        mov     %2, %5, lsr #16						\n\
+        mov     %0, %6, lsr #16						\n\
+        bic     %3, %5, %2, lsl #16					\n\
+        bic     %4, %6, %0, lsl #16					\n\
+        mul     %1, %3, %4						\n\
+        mul     %4, %2, %4						\n\
+        mul     %3, %0, %3						\n\
+        mul     %0, %2, %0						\n\
+        adds    %3, %4, %3						\n\
+        addcs   %0, %0, #65536						\n\
+        adds    %1, %1, %3, lsl #16					\n\
+        adc     %0, %0, %3, lsr #16"                                    \
+           : "=&r" ((USItype) (xh)),                                    \
+             "=r" ((USItype) (xl)),                                     \
+             "=&r" (__t0), "=&r" (__t1), "=r" (__t2)                    \
+           : "r" ((USItype) (a)),                                       \
+             "r" ((USItype) (b)));}
+
+
+#define __umulsidi3(u, v) \
+  ({DIunion __w;                                                        \
+    umul_ppmm (__w.s.high, __w.s.low, u, v);                            \
+    __w.ll; })
+
+
+DItype
+__muldi3 (DItype u, DItype v)
+{
+  DIunion w;
+  DIunion uu, vv;
+
+  uu.ll = u,
+  vv.ll = v;
+
+  w.ll = __umulsidi3 (uu.s.low, vv.s.low);
+  w.s.high += ((USItype) uu.s.low * (USItype) vv.s.high
+               + (USItype) uu.s.high * (USItype) vv.s.low);
+
+  return w.ll;
+}
+
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
new file mode 100644
index 00000000000..b09398d95aa
--- /dev/null
+++ b/arch/arm/lib/putuser.S
@@ -0,0 +1,76 @@
+/*
+ *  linux/arch/arm/lib/putuser.S
+ *
+ *  Copyright (C) 2001 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  Idea from x86 version, (C) Copyright 1998 Linus Torvalds
+ *
+ * These functions have a non-standard call interface to make
+ * them more efficient, especially as they return an error
+ * value in addition to the "real" return value.
+ *
+ * __put_user_X
+ *
+ * Inputs:	r0 contains the address
+ *		r2, r3 contains the value
+ * Outputs:	r0 is the error code
+ *		lr corrupted
+ *
+ * No other registers must be altered.  (see include/asm-arm/uaccess.h
+ * for specific ASM register usage).
+ *
+ * Note that ADDR_LIMIT is either 0 or 0xc0000000
+ * Note also that it is intended that __put_user_bad is not global.
+ */
+#include <asm/constants.h>
+#include <asm/thread_info.h>
+#include <asm/errno.h>
+
+	.global	__put_user_1
+__put_user_1:
+1:	strbt	r2, [r0]
+	mov	r0, #0
+	mov	pc, lr
+
+	.global	__put_user_2
+__put_user_2:
+	mov	ip, r2, lsr #8
+#ifndef __ARMEB__
+2:	strbt	r2, [r0], #1
+3:	strbt	ip, [r0]
+#else
+2:	strbt	ip, [r0], #1
+3:	strbt	r2, [r0]
+#endif
+	mov	r0, #0
+	mov	pc, lr
+
+	.global	__put_user_4
+__put_user_4:
+4:	strt	r2, [r0]
+	mov	r0, #0
+	mov	pc, lr
+
+	.global	__put_user_8
+__put_user_8:
+5:	strt	r2, [r0], #4
+6:	strt	r3, [r0]
+	mov	r0, #0
+	mov	pc, lr
+
+__put_user_bad:
+	mov	r0, #-EFAULT
+	mov	pc, lr
+
+.section __ex_table, "a"
+	.long	1b, __put_user_bad
+	.long	2b, __put_user_bad
+	.long	3b, __put_user_bad
+	.long	4b, __put_user_bad
+	.long	5b, __put_user_bad
+	.long	6b, __put_user_bad
+.previous
diff --git a/arch/arm/lib/setbit.S b/arch/arm/lib/setbit.S
new file mode 100644
index 00000000000..8f337df5d99
--- /dev/null
+++ b/arch/arm/lib/setbit.S
@@ -0,0 +1,29 @@
+/*
+ *  linux/arch/arm/lib/setbit.S
+ *
+ *  Copyright (C) 1995-1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+		.text
+
+/*
+ * Purpose  : Function to set a bit
+ * Prototype: int set_bit(int bit, void *addr)
+ */
+ENTRY(_set_bit_be)
+		eor	r0, r0, #0x18		@ big endian byte ordering
+ENTRY(_set_bit_le)
+		and	r2, r0, #7
+		mov	r3, #1
+		mov	r3, r3, lsl r2
+		save_and_disable_irqs ip, r2
+		ldrb	r2, [r1, r0, lsr #3]
+		orr	r2, r2, r3
+		strb	r2, [r1, r0, lsr #3]
+		restore_irqs ip
+		RETINSTR(mov,pc,lr)
diff --git a/arch/arm/lib/strchr.S b/arch/arm/lib/strchr.S
new file mode 100644
index 00000000000..5b9b493733f
--- /dev/null
+++ b/arch/arm/lib/strchr.S
@@ -0,0 +1,26 @@
+/*
+ *  linux/arch/arm/lib/strchr.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  ASM optimised string functions
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.text
+		.align	5
+ENTRY(strchr)
+		and	r1, r1, #0xff
+1:		ldrb	r2, [r0], #1
+		teq	r2, r1
+		teqne	r2, #0
+		bne	1b
+		teq	r2, r1
+		movne	r0, #0
+		subeq	r0, r0, #1
+		RETINSTR(mov,pc,lr)
diff --git a/arch/arm/lib/strncpy_from_user.S b/arch/arm/lib/strncpy_from_user.S
new file mode 100644
index 00000000000..629cc877527
--- /dev/null
+++ b/arch/arm/lib/strncpy_from_user.S
@@ -0,0 +1,43 @@
+/*
+ *  linux/arch/arm/lib/strncpy_from_user.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+
+	.text
+	.align	5
+
+/*
+ * Copy a string from user space to kernel space.
+ *  r0 = dst, r1 = src, r2 = byte length
+ * returns the number of characters copied (strlen of copied string),
+ *  -EFAULT on exception, or "len" if we fill the whole buffer
+ */
+ENTRY(__arch_strncpy_from_user)
+	save_lr
+	mov	ip, r1
+1:	subs	r2, r2, #1
+USER(	ldrplbt	r3, [r1], #1)
+	bmi	2f
+	strb	r3, [r0], #1
+	teq	r3, #0
+	bne	1b
+	sub	r1, r1, #1	@ take NUL character out of count
+2:	sub	r0, r1, ip
+	restore_pc
+
+	.section .fixup,"ax"
+	.align	0
+9001:	mov	r3, #0
+	strb	r3, [r0, #0]	@ null terminate
+	mov	r0, #-EFAULT
+	restore_pc
+	.previous
+
diff --git a/arch/arm/lib/strnlen_user.S b/arch/arm/lib/strnlen_user.S
new file mode 100644
index 00000000000..67bcd826812
--- /dev/null
+++ b/arch/arm/lib/strnlen_user.S
@@ -0,0 +1,40 @@
+/*
+ *  linux/arch/arm/lib/strnlen_user.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+
+	.text
+	.align	5
+
+/* Prototype: unsigned long __arch_strnlen_user(const char *str, long n)
+ * Purpose  : get length of a string in user memory
+ * Params   : str - address of string in user memory
+ * Returns  : length of string *including terminator*
+ *	      or zero on exception, or n + 1 if too long
+ */
+ENTRY(__arch_strnlen_user)
+	save_lr
+	mov	r2, r0
+1:
+USER(	ldrbt	r3, [r0], #1)
+	teq	r3, #0
+	beq	2f
+	subs	r1, r1, #1
+	bne	1b
+	add	r0, r0, #1
+2:	sub	r0, r0, r2
+	restore_pc
+
+	.section .fixup,"ax"
+	.align	0
+9001:	mov	r0, #0
+	restore_pc
+	.previous
diff --git a/arch/arm/lib/strrchr.S b/arch/arm/lib/strrchr.S
new file mode 100644
index 00000000000..fa923f026f1
--- /dev/null
+++ b/arch/arm/lib/strrchr.S
@@ -0,0 +1,25 @@
+/*
+ *  linux/arch/arm/lib/strrchr.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  ASM optimised string functions
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+		.text
+		.align	5
+ENTRY(strrchr)
+		mov	r3, #0
+1:		ldrb	r2, [r0], #1
+		teq	r2, r1
+		subeq	r3, r0, #1
+		teq	r2, #0
+		bne	1b
+		mov	r0, r3
+		RETINSTR(mov,pc,lr)
diff --git a/arch/arm/lib/testchangebit.S b/arch/arm/lib/testchangebit.S
new file mode 100644
index 00000000000..4aba4676b98
--- /dev/null
+++ b/arch/arm/lib/testchangebit.S
@@ -0,0 +1,29 @@
+/*
+ *  linux/arch/arm/lib/testchangebit.S
+ *
+ *  Copyright (C) 1995-1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+                .text
+
+ENTRY(_test_and_change_bit_be)
+		eor	r0, r0, #0x18		@ big endian byte ordering
+ENTRY(_test_and_change_bit_le)
+		add	r1, r1, r0, lsr #3
+		and	r3, r0, #7
+		mov	r0, #1
+		save_and_disable_irqs ip, r2
+		ldrb	r2, [r1]
+		tst	r2, r0, lsl r3
+		eor	r2, r2, r0, lsl r3
+		strb	r2, [r1]
+		restore_irqs ip
+		moveq	r0, #0
+		RETINSTR(mov,pc,lr)
+
+
diff --git a/arch/arm/lib/testclearbit.S b/arch/arm/lib/testclearbit.S
new file mode 100644
index 00000000000..e07c5bd2430
--- /dev/null
+++ b/arch/arm/lib/testclearbit.S
@@ -0,0 +1,29 @@
+/*
+ *  linux/arch/arm/lib/testclearbit.S
+ *
+ *  Copyright (C) 1995-1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+                .text
+
+ENTRY(_test_and_clear_bit_be)
+		eor	r0, r0, #0x18		@ big endian byte ordering
+ENTRY(_test_and_clear_bit_le)
+		add	r1, r1, r0, lsr #3	@ Get byte offset
+		and	r3, r0, #7		@ Get bit offset
+		mov	r0, #1
+		save_and_disable_irqs ip, r2
+		ldrb	r2, [r1]
+		tst	r2, r0, lsl r3
+		bic	r2, r2, r0, lsl r3
+		strb	r2, [r1]
+		restore_irqs ip
+		moveq	r0, #0
+		RETINSTR(mov,pc,lr)
+
+
diff --git a/arch/arm/lib/testsetbit.S b/arch/arm/lib/testsetbit.S
new file mode 100644
index 00000000000..a570fc74cdd
--- /dev/null
+++ b/arch/arm/lib/testsetbit.S
@@ -0,0 +1,29 @@
+/*
+ *  linux/arch/arm/lib/testsetbit.S
+ *
+ *  Copyright (C) 1995-1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+                .text
+
+ENTRY(_test_and_set_bit_be)
+		eor	r0, r0, #0x18		@ big endian byte ordering
+ENTRY(_test_and_set_bit_le)
+		add	r1, r1, r0, lsr #3	@ Get byte offset
+		and	r3, r0, #7		@ Get bit offset
+		mov	r0, #1
+		save_and_disable_irqs ip, r2
+		ldrb	r2, [r1]
+		tst	r2, r0, lsl r3
+		orr	r2, r2, r0, lsl r3
+		strb	r2, [r1]
+		restore_irqs ip
+		moveq	r0, #0
+		RETINSTR(mov,pc,lr)
+
+
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
new file mode 100644
index 00000000000..d3ed0636c00
--- /dev/null
+++ b/arch/arm/lib/uaccess.S
@@ -0,0 +1,697 @@
+/*
+ *  linux/arch/arm/lib/uaccess.S
+ *
+ *  Copyright (C) 1995, 1996,1997,1998 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  Routines to block copy data to/from user memory
+ *   These are highly optimised both for the 4k page size
+ *   and for various alignments.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+
+		.text
+
+#define PAGE_SHIFT 12
+
+/* Prototype: int __arch_copy_to_user(void *to, const char *from, size_t n)
+ * Purpose  : copy a block to user memory from kernel memory
+ * Params   : to   - user memory
+ *          : from - kernel memory
+ *          : n    - number of bytes to copy
+ * Returns  : Number of bytes NOT copied.
+ */
+
+.c2u_dest_not_aligned:
+		rsb	ip, ip, #4
+		cmp	ip, #2
+		ldrb	r3, [r1], #1
+USER(		strbt	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(		strgebt	r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #1
+USER(		strgtbt	r3, [r0], #1)			@ May fault
+		sub	r2, r2, ip
+		b	.c2u_dest_aligned
+
+ENTRY(__arch_copy_to_user)
+		stmfd	sp!, {r2, r4 - r7, lr}
+		cmp	r2, #4
+		blt	.c2u_not_enough
+	PLD(	pld	[r1, #0]		)
+	PLD(	pld	[r0, #0]		)
+		ands	ip, r0, #3
+		bne	.c2u_dest_not_aligned
+.c2u_dest_aligned:
+
+		ands	ip, r1, #3
+		bne	.c2u_src_not_aligned
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.c2u_0fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.c2u_0nowords
+		ldr	r3, [r1], #4
+USER(		strt	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.c2u_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #32
+		blt	.c2u_0rem8lp
+	PLD(	pld	[r1, #28]		)
+	PLD(	pld	[r0, #28]		)
+	PLD(	subs	ip, ip, #64			)
+	PLD(	blt	.c2u_0cpynopld		)
+	PLD(	pld	[r1, #60]		)
+	PLD(	pld	[r0, #60]		)
+
+.c2u_0cpy8lp:
+	PLD(	pld	[r1, #92]		)
+	PLD(	pld	[r0, #92]		)
+.c2u_0cpynopld:	ldmia	r1!, {r3 - r6}
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		ldmia	r1!, {r3 - r6}
+		subs	ip, ip, #32
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.c2u_0cpy8lp
+	PLD(	cmn	ip, #64			)
+	PLD(	bge	.c2u_0cpynopld		)
+	PLD(	add	ip, ip, #64		)
+
+.c2u_0rem8lp:	cmn	ip, #16
+		ldmgeia	r1!, {r3 - r6}
+		stmgeia	r0!, {r3 - r6}			@ Shouldnt fault
+		tst	ip, #8
+		ldmneia	r1!, {r3 - r4}
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		ldrne	r3, [r1], #4
+		strnet	r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.c2u_0fupi
+.c2u_0nowords:	teq	ip, #0
+		beq	.c2u_finished
+.c2u_nowords:	cmp	ip, #2
+		ldrb	r3, [r1], #1
+USER(		strbt	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(		strgebt	r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #1
+USER(		strgtbt	r3, [r0], #1)			@ May fault
+		b	.c2u_finished
+
+.c2u_not_enough:
+		movs	ip, r2
+		bne	.c2u_nowords
+.c2u_finished:	mov	r0, #0
+		LOADREGS(fd,sp!,{r2, r4 - r7, pc})
+
+.c2u_src_not_aligned:
+		bic	r1, r1, #3
+		ldr	r7, [r1], #4
+		cmp	ip, #2
+		bgt	.c2u_3fupi
+		beq	.c2u_2fupi
+.c2u_1fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.c2u_1nowords
+		mov	r3, r7, pull #8
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #24
+USER(		strt	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.c2u_1fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.c2u_1rem8lp
+	PLD(	pld	[r1, #12]		)
+	PLD(	pld	[r0, #12]		)
+	PLD(	subs	ip, ip, #32		)
+	PLD(	blt	.c2u_1cpynopld		)
+	PLD(	pld	[r1, #28]		)
+	PLD(	pld	[r0, #28]		)
+
+.c2u_1cpy8lp:
+	PLD(	pld	[r1, #44]		)
+	PLD(	pld	[r0, #44]		)
+.c2u_1cpynopld:	mov	r3, r7, pull #8
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #24
+		mov	r4, r4, pull #8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.c2u_1cpy8lp
+	PLD(	cmn	ip, #32			)
+	PLD(	bge	.c2u_1cpynopld		)
+	PLD(	add	ip, ip, #32		)
+
+.c2u_1rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #8
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #24
+		movne	r4, r4, pull #8
+		orrne	r4, r4, r7, push #24
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #8
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #24
+		strnet	r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.c2u_1fupi
+.c2u_1nowords:	mov	r3, r7, get_byte_1
+		teq	ip, #0
+		beq	.c2u_finished
+		cmp	ip, #2
+USER(		strbt	r3, [r0], #1)			@ May fault
+		movge	r3, r7, get_byte_2
+USER(		strgebt	r3, [r0], #1)			@ May fault
+		movgt	r3, r7, get_byte_3
+USER(		strgtbt	r3, [r0], #1)			@ May fault
+		b	.c2u_finished
+
+.c2u_2fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.c2u_2nowords
+		mov	r3, r7, pull #16
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #16
+USER(		strt	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.c2u_2fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.c2u_2rem8lp
+	PLD(	pld	[r1, #12]		)
+	PLD(	pld	[r0, #12]		)
+	PLD(	subs	ip, ip, #32		)
+	PLD(	blt	.c2u_2cpynopld		)
+	PLD(	pld	[r1, #28]		)
+	PLD(	pld	[r0, #28]		)
+
+.c2u_2cpy8lp:
+	PLD(	pld	[r1, #44]		)
+	PLD(	pld	[r0, #44]		)
+.c2u_2cpynopld:	mov	r3, r7, pull #16
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #16
+		mov	r4, r4, pull #16
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.c2u_2cpy8lp
+	PLD(	cmn	ip, #32			)
+	PLD(	bge	.c2u_2cpynopld		)
+	PLD(	add	ip, ip, #32		)
+
+.c2u_2rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #16
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #16
+		movne	r4, r4, pull #16
+		orrne	r4, r4, r7, push #16
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #16
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #16
+		strnet	r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.c2u_2fupi
+.c2u_2nowords:	mov	r3, r7, get_byte_2
+		teq	ip, #0
+		beq	.c2u_finished
+		cmp	ip, #2
+USER(		strbt	r3, [r0], #1)			@ May fault
+		movge	r3, r7, get_byte_3
+USER(		strgebt	r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #0
+USER(		strgtbt	r3, [r0], #1)			@ May fault
+		b	.c2u_finished
+
+.c2u_3fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.c2u_3nowords
+		mov	r3, r7, pull #24
+		ldr	r7, [r1], #4
+		orr	r3, r3, r7, push #8
+USER(		strt	r3, [r0], #4)			@ May fault
+		mov	ip, r0, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.c2u_3fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.c2u_3rem8lp
+	PLD(	pld	[r1, #12]		)
+	PLD(	pld	[r0, #12]		)
+	PLD(	subs	ip, ip, #32		)
+	PLD(	blt	.c2u_3cpynopld		)
+	PLD(	pld	[r1, #28]		)
+	PLD(	pld	[r0, #28]		)
+
+.c2u_3cpy8lp:
+	PLD(	pld	[r1, #44]		)
+	PLD(	pld	[r0, #44]		)
+.c2u_3cpynopld:	mov	r3, r7, pull #24
+		ldmia	r1!, {r4 - r7}
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #8
+		mov	r4, r4, pull #24
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		stmia	r0!, {r3 - r6}			@ Shouldnt fault
+		bpl	.c2u_3cpy8lp
+	PLD(	cmn	ip, #32			)
+	PLD(	bge	.c2u_3cpynopld		)
+	PLD(	add	ip, ip, #32		)
+
+.c2u_3rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #24
+		ldmneia	r1!, {r4, r7}
+		orrne	r3, r3, r4, push #8
+		movne	r4, r4, pull #24
+		orrne	r4, r4, r7, push #8
+		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
+		tst	ip, #4
+		movne	r3, r7, pull #24
+		ldrne	r7, [r1], #4
+		orrne	r3, r3, r7, push #8
+		strnet	r3, [r0], #4			@ Shouldnt fault
+		ands	ip, ip, #3
+		beq	.c2u_3fupi
+.c2u_3nowords:	mov	r3, r7, get_byte_3
+		teq	ip, #0
+		beq	.c2u_finished
+		cmp	ip, #2
+USER(		strbt	r3, [r0], #1)			@ May fault
+		ldrgeb	r3, [r1], #1
+USER(		strgebt	r3, [r0], #1)			@ May fault
+		ldrgtb	r3, [r1], #0
+USER(		strgtbt	r3, [r0], #1)			@ May fault
+		b	.c2u_finished
+
+		.section .fixup,"ax"
+		.align	0
+9001:		LOADREGS(fd,sp!, {r0, r4 - r7, pc})
+		.previous
+
+/* Prototype: unsigned long __arch_copy_from_user(void *to,const void *from,unsigned long n);
+ * Purpose  : copy a block from user memory to kernel memory
+ * Params   : to   - kernel memory
+ *          : from - user memory
+ *          : n    - number of bytes to copy
+ * Returns  : Number of bytes NOT copied.
+ */
+.cfu_dest_not_aligned:
+		rsb	ip, ip, #4
+		cmp	ip, #2
+USER(		ldrbt	r3, [r1], #1)			@ May fault
+		strb	r3, [r0], #1
+USER(		ldrgebt	r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		sub	r2, r2, ip
+		b	.cfu_dest_aligned
+
+ENTRY(__arch_copy_from_user)
+		stmfd	sp!, {r0, r2, r4 - r7, lr}
+		cmp	r2, #4
+		blt	.cfu_not_enough
+	PLD(	pld	[r1, #0]		)
+	PLD(	pld	[r0, #0]		)
+		ands	ip, r0, #3
+		bne	.cfu_dest_not_aligned
+.cfu_dest_aligned:
+		ands	ip, r1, #3
+		bne	.cfu_src_not_aligned
+/*
+ * Seeing as there has to be at least 8 bytes to copy, we can
+ * copy one word, and force a user-mode page fault...
+ */
+
+.cfu_0fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.cfu_0nowords
+USER(		ldrt	r3, [r1], #4)
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.cfu_0fupi
+/*
+ * ip = max no. of bytes to copy before needing another "strt" insn
+ */
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #32
+		blt	.cfu_0rem8lp
+	PLD(	pld	[r1, #28]		)
+	PLD(	pld	[r0, #28]		)
+	PLD(	subs	ip, ip, #64			)
+	PLD(	blt	.cfu_0cpynopld		)
+	PLD(	pld	[r1, #60]		)
+	PLD(	pld	[r0, #60]		)
+
+.cfu_0cpy8lp:
+	PLD(	pld	[r1, #92]		)
+	PLD(	pld	[r0, #92]		)
+.cfu_0cpynopld:	ldmia	r1!, {r3 - r6}			@ Shouldnt fault
+		stmia	r0!, {r3 - r6}
+		ldmia	r1!, {r3 - r6}			@ Shouldnt fault
+		subs	ip, ip, #32
+		stmia	r0!, {r3 - r6}
+		bpl	.cfu_0cpy8lp
+	PLD(	cmn	ip, #64			)
+	PLD(	bge	.cfu_0cpynopld		)
+	PLD(	add	ip, ip, #64		)
+
+.cfu_0rem8lp:	cmn	ip, #16
+		ldmgeia	r1!, {r3 - r6}			@ Shouldnt fault
+		stmgeia	r0!, {r3 - r6}
+		tst	ip, #8
+		ldmneia	r1!, {r3 - r4}			@ Shouldnt fault
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		ldrnet	r3, [r1], #4			@ Shouldnt fault
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.cfu_0fupi
+.cfu_0nowords:	teq	ip, #0
+		beq	.cfu_finished
+.cfu_nowords:	cmp	ip, #2
+USER(		ldrbt	r3, [r1], #1)			@ May fault
+		strb	r3, [r0], #1
+USER(		ldrgebt	r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.cfu_finished
+
+.cfu_not_enough:
+		movs	ip, r2
+		bne	.cfu_nowords
+.cfu_finished:	mov	r0, #0
+		add	sp, sp, #8
+		LOADREGS(fd,sp!,{r4 - r7, pc})
+
+.cfu_src_not_aligned:
+		bic	r1, r1, #3
+USER(		ldrt	r7, [r1], #4)			@ May fault
+		cmp	ip, #2
+		bgt	.cfu_3fupi
+		beq	.cfu_2fupi
+.cfu_1fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.cfu_1nowords
+		mov	r3, r7, pull #8
+USER(		ldrt	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #24
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.cfu_1fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.cfu_1rem8lp
+	PLD(	pld	[r1, #12]		)
+	PLD(	pld	[r0, #12]		)
+	PLD(	subs	ip, ip, #32		)
+	PLD(	blt	.cfu_1cpynopld		)
+	PLD(	pld	[r1, #28]		)
+	PLD(	pld	[r0, #28]		)
+
+.cfu_1cpy8lp:
+	PLD(	pld	[r1, #44]		)
+	PLD(	pld	[r0, #44]		)
+.cfu_1cpynopld:	mov	r3, r7, pull #8
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #24
+		mov	r4, r4, pull #8
+		orr	r4, r4, r5, push #24
+		mov	r5, r5, pull #8
+		orr	r5, r5, r6, push #24
+		mov	r6, r6, pull #8
+		orr	r6, r6, r7, push #24
+		stmia	r0!, {r3 - r6}
+		bpl	.cfu_1cpy8lp
+	PLD(	cmn	ip, #32			)
+	PLD(	bge	.cfu_1cpynopld		)
+	PLD(	add	ip, ip, #32		)
+
+.cfu_1rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #8
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #24
+		movne	r4, r4, pull #8
+		orrne	r4, r4, r7, push #24
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #8
+USER(		ldrnet	r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #24
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.cfu_1fupi
+.cfu_1nowords:	mov	r3, r7, get_byte_1
+		teq	ip, #0
+		beq	.cfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+		movge	r3, r7, get_byte_2
+		strgeb	r3, [r0], #1
+		movgt	r3, r7, get_byte_3
+		strgtb	r3, [r0], #1
+		b	.cfu_finished
+
+.cfu_2fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.cfu_2nowords
+		mov	r3, r7, pull #16
+USER(		ldrt	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #16
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.cfu_2fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.cfu_2rem8lp
+	PLD(	pld	[r1, #12]		)
+	PLD(	pld	[r0, #12]		)
+	PLD(	subs	ip, ip, #32		)
+	PLD(	blt	.cfu_2cpynopld		)
+	PLD(	pld	[r1, #28]		)
+	PLD(	pld	[r0, #28]		)
+
+.cfu_2cpy8lp:
+	PLD(	pld	[r1, #44]		)
+	PLD(	pld	[r0, #44]		)
+.cfu_2cpynopld:	mov	r3, r7, pull #16
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		subs	ip, ip, #16
+		orr	r3, r3, r4, push #16
+		mov	r4, r4, pull #16
+		orr	r4, r4, r5, push #16
+		mov	r5, r5, pull #16
+		orr	r5, r5, r6, push #16
+		mov	r6, r6, pull #16
+		orr	r6, r6, r7, push #16
+		stmia	r0!, {r3 - r6}
+		bpl	.cfu_2cpy8lp
+	PLD(	cmn	ip, #32			)
+	PLD(	bge	.cfu_2cpynopld		)
+	PLD(	add	ip, ip, #32		)
+
+.cfu_2rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #16
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #16
+		movne	r4, r4, pull #16
+		orrne	r4, r4, r7, push #16
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #16
+USER(		ldrnet	r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #16
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.cfu_2fupi
+.cfu_2nowords:	mov	r3, r7, get_byte_2
+		teq	ip, #0
+		beq	.cfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+		movge	r3, r7, get_byte_3
+		strgeb	r3, [r0], #1
+USER(		ldrgtbt	r3, [r1], #0)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.cfu_finished
+
+.cfu_3fupi:	subs	r2, r2, #4
+		addmi	ip, r2, #4
+		bmi	.cfu_3nowords
+		mov	r3, r7, pull #24
+USER(		ldrt	r7, [r1], #4)			@ May fault
+		orr	r3, r3, r7, push #8
+		str	r3, [r0], #4
+		mov	ip, r1, lsl #32 - PAGE_SHIFT
+		rsb	ip, ip, #0
+		movs	ip, ip, lsr #32 - PAGE_SHIFT
+		beq	.cfu_3fupi
+		cmp	r2, ip
+		movlt	ip, r2
+		sub	r2, r2, ip
+		subs	ip, ip, #16
+		blt	.cfu_3rem8lp
+	PLD(	pld	[r1, #12]		)
+	PLD(	pld	[r0, #12]		)
+	PLD(	subs	ip, ip, #32		)
+	PLD(	blt	.cfu_3cpynopld		)
+	PLD(	pld	[r1, #28]		)
+	PLD(	pld	[r0, #28]		)
+
+.cfu_3cpy8lp:
+	PLD(	pld	[r1, #44]		)
+	PLD(	pld	[r0, #44]		)
+.cfu_3cpynopld:	mov	r3, r7, pull #24
+		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
+		orr	r3, r3, r4, push #8
+		mov	r4, r4, pull #24
+		orr	r4, r4, r5, push #8
+		mov	r5, r5, pull #24
+		orr	r5, r5, r6, push #8
+		mov	r6, r6, pull #24
+		orr	r6, r6, r7, push #8
+		stmia	r0!, {r3 - r6}
+		subs	ip, ip, #16
+		bpl	.cfu_3cpy8lp
+	PLD(	cmn	ip, #32			)
+	PLD(	bge	.cfu_3cpynopld		)
+	PLD(	add	ip, ip, #32		)
+
+.cfu_3rem8lp:	tst	ip, #8
+		movne	r3, r7, pull #24
+		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
+		orrne	r3, r3, r4, push #8
+		movne	r4, r4, pull #24
+		orrne	r4, r4, r7, push #8
+		stmneia	r0!, {r3 - r4}
+		tst	ip, #4
+		movne	r3, r7, pull #24
+USER(		ldrnet	r7, [r1], #4)			@ May fault
+		orrne	r3, r3, r7, push #8
+		strne	r3, [r0], #4
+		ands	ip, ip, #3
+		beq	.cfu_3fupi
+.cfu_3nowords:	mov	r3, r7, get_byte_3
+		teq	ip, #0
+		beq	.cfu_finished
+		cmp	ip, #2
+		strb	r3, [r0], #1
+USER(		ldrgebt	r3, [r1], #1)			@ May fault
+		strgeb	r3, [r0], #1
+USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+		strgtb	r3, [r0], #1
+		b	.cfu_finished
+
+		.section .fixup,"ax"
+		.align	0
+		/*
+		 * We took an exception.  r0 contains a pointer to
+		 * the byte not copied.
+		 */
+9001:		ldr	r2, [sp], #4			@ void *to
+		sub	r2, r0, r2			@ bytes copied
+		ldr	r1, [sp], #4			@ unsigned long count
+		subs	r4, r1, r2			@ bytes left to copy
+		movne	r1, r4
+		blne	__memzero
+		mov	r0, r4
+		LOADREGS(fd,sp!, {r4 - r7, pc})
+		.previous
+
+/* Prototype: int __arch_clear_user(void *addr, size_t sz)
+ * Purpose  : clear some user memory
+ * Params   : addr - user memory address to clear
+ *          : sz   - number of bytes to clear
+ * Returns  : number of bytes NOT cleared
+ */
+ENTRY(__arch_clear_user)
+		stmfd	sp!, {r1, lr}
+		mov	r2, #0
+		cmp	r1, #4
+		blt	2f
+		ands	ip, r0, #3
+		beq	1f
+		cmp	ip, #2
+USER(		strbt	r2, [r0], #1)
+USER(		strlebt	r2, [r0], #1)
+USER(		strltbt	r2, [r0], #1)
+		rsb	ip, ip, #4
+		sub	r1, r1, ip		@  7  6  5  4  3  2  1
+1:		subs	r1, r1, #8		@ -1 -2 -3 -4 -5 -6 -7
+USER(		strplt	r2, [r0], #4)
+USER(		strplt	r2, [r0], #4)
+		bpl	1b
+		adds	r1, r1, #4		@  3  2  1  0 -1 -2 -3
+USER(		strplt	r2, [r0], #4)
+2:		tst	r1, #2			@ 1x 1x 0x 0x 1x 1x 0x
+USER(		strnebt	r2, [r0], #1)
+USER(		strnebt	r2, [r0], #1)
+		tst	r1, #1			@ x1 x0 x1 x0 x1 x0 x1
+USER(		strnebt	r2, [r0], #1)
+		mov	r0, #0
+		LOADREGS(fd,sp!, {r1, pc})
+
+		.section .fixup,"ax"
+		.align	0
+9001:		LOADREGS(fd,sp!, {r0, pc})
+		.previous
+
diff --git a/arch/arm/lib/ucmpdi2.c b/arch/arm/lib/ucmpdi2.c
new file mode 100644
index 00000000000..6c6ae63efa0
--- /dev/null
+++ b/arch/arm/lib/ucmpdi2.c
@@ -0,0 +1,51 @@
+/* More subroutines needed by GCC output code on some machines.  */
+/* Compile this one with gcc.  */
+/* Copyright (C) 1989, 92-98, 1999 Free Software Foundation, Inc.
+
+This file is part of GNU CC.
+
+GNU CC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 2, or (at your option)
+any later version.
+
+GNU CC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with GNU CC; see the file COPYING.  If not, write to
+the Free Software Foundation, 59 Temple Place - Suite 330,
+Boston, MA 02111-1307, USA.  */
+
+/* As a special exception, if you link this library with other files,
+   some of which are compiled with GCC, to produce an executable,
+   this library does not by itself cause the resulting executable
+   to be covered by the GNU General Public License.
+   This exception does not however invalidate any other reasons why
+   the executable file might be covered by the GNU General Public License.
+ */
+/* support functions required by the kernel. based on code from gcc-2.95.3 */
+/* I Molton     29/07/01 */
+
+#include "gcclib.h"
+
+word_type
+__ucmpdi2 (DItype a, DItype b)
+{
+  DIunion au, bu;
+
+  au.ll = a, bu.ll = b;
+
+  if ((USItype) au.s.high < (USItype) bu.s.high)
+    return 0;
+  else if ((USItype) au.s.high > (USItype) bu.s.high)
+    return 2;
+  if ((USItype) au.s.low < (USItype) bu.s.low)
+    return 0;
+  else if ((USItype) au.s.low > (USItype) bu.s.low)
+    return 2;
+  return 1;
+}
+
diff --git a/arch/arm/lib/udivdi3.c b/arch/arm/lib/udivdi3.c
new file mode 100644
index 00000000000..d25195f673f
--- /dev/null
+++ b/arch/arm/lib/udivdi3.c
@@ -0,0 +1,242 @@
+/* More subroutines needed by GCC output code on some machines.  */
+/* Compile this one with gcc.  */
+/* Copyright (C) 1989, 92-98, 1999 Free Software Foundation, Inc.
+
+This file is part of GNU CC.
+
+GNU CC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 2, or (at your option)
+any later version.
+
+GNU CC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with GNU CC; see the file COPYING.  If not, write to
+the Free Software Foundation, 59 Temple Place - Suite 330,
+Boston, MA 02111-1307, USA.  */
+
+/* As a special exception, if you link this library with other files,
+   some of which are compiled with GCC, to produce an executable,
+   this library does not by itself cause the resulting executable
+   to be covered by the GNU General Public License.
+   This exception does not however invalidate any other reasons why
+   the executable file might be covered by the GNU General Public License.
+ */
+/* support functions required by the kernel. based on code from gcc-2.95.3 */
+/* I Molton     29/07/01 */
+
+#include "gcclib.h"
+#include "longlong.h"
+
+static const UQItype __clz_tab[] =
+{
+  0,1,2,2,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,
+  6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,6,
+  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
+  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+  8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,
+};
+
+UDItype
+__udivmoddi4 (UDItype n, UDItype d, UDItype *rp)
+{
+  DIunion ww;
+  DIunion nn, dd;
+  DIunion rr;
+  USItype d0, d1, n0, n1, n2;
+  USItype q0, q1;
+  USItype b, bm;
+
+  nn.ll = n;
+  dd.ll = d;
+
+  d0 = dd.s.low;
+  d1 = dd.s.high;
+  n0 = nn.s.low;
+  n1 = nn.s.high;
+
+  if (d1 == 0)
+    {
+      if (d0 > n1)
+        {
+          /* 0q = nn / 0D */
+
+          count_leading_zeros (bm, d0);
+
+          if (bm != 0)
+            {
+              /* Normalize, i.e. make the most significant bit of the
+                 denominator set.  */
+
+              d0 = d0 << bm;
+              n1 = (n1 << bm) | (n0 >> (SI_TYPE_SIZE - bm));
+              n0 = n0 << bm;
+            }
+
+          udiv_qrnnd (q0, n0, n1, n0, d0);
+          q1 = 0;
+
+          /* Remainder in n0 >> bm.  */
+        }
+      else
+        {
+          /* qq = NN / 0d */
+
+          if (d0 == 0)
+            d0 = 1 / d0;        /* Divide intentionally by zero.  */
+
+          count_leading_zeros (bm, d0);
+
+          if (bm == 0)
+            {
+              /* From (n1 >= d0) /\ (the most significant bit of d0 is set),
+                 conclude (the most significant bit of n1 is set) /\ (the
+                 leading quotient digit q1 = 1).
+
+                 This special case is necessary, not an optimization.
+                 (Shifts counts of SI_TYPE_SIZE are undefined.)  */
+
+              n1 -= d0;
+              q1 = 1;
+            }
+          else
+            {
+              /* Normalize.  */
+
+              b = SI_TYPE_SIZE - bm;
+
+              d0 = d0 << bm;
+              n2 = n1 >> b;
+              n1 = (n1 << bm) | (n0 >> b);
+              n0 = n0 << bm;
+
+              udiv_qrnnd (q1, n1, n2, n1, d0);
+            }
+
+          /* n1 != d0...  */
+
+          udiv_qrnnd (q0, n0, n1, n0, d0);
+
+          /* Remainder in n0 >> bm.  */
+        }
+
+      if (rp != 0)
+        {
+          rr.s.low = n0 >> bm;
+          rr.s.high = 0;
+          *rp = rr.ll;
+        }
+    }
+  else
+    {
+      if (d1 > n1)
+        {
+          /* 00 = nn / DD */
+
+          q0 = 0;
+          q1 = 0;
+
+          /* Remainder in n1n0.  */
+          if (rp != 0)
+            {
+              rr.s.low = n0;
+              rr.s.high = n1;
+              *rp = rr.ll;
+            }
+        }
+      else
+        {
+          /* 0q = NN / dd */
+
+          count_leading_zeros (bm, d1);
+          if (bm == 0)
+            {
+              /* From (n1 >= d1) /\ (the most significant bit of d1 is set),
+                 conclude (the most significant bit of n1 is set) /\ (the
+                 quotient digit q0 = 0 or 1).
+
+                 This special case is necessary, not an optimization.  */
+
+              /* The condition on the next line takes advantage of that
+                 n1 >= d1 (true due to program flow).  */
+              if (n1 > d1 || n0 >= d0)
+                {
+                  q0 = 1;
+                  sub_ddmmss (n1, n0, n1, n0, d1, d0);
+                }
+              else
+                q0 = 0;
+
+              q1 = 0;
+
+              if (rp != 0)
+                {
+                  rr.s.low = n0;
+                  rr.s.high = n1;
+                  *rp = rr.ll;
+                }
+            }
+          else
+            {
+              USItype m1, m0;
+              /* Normalize.  */
+
+              b = SI_TYPE_SIZE - bm;
+
+              d1 = (d1 << bm) | (d0 >> b);
+              d0 = d0 << bm;
+              n2 = n1 >> b;
+              n1 = (n1 << bm) | (n0 >> b);
+              n0 = n0 << bm;
+
+              udiv_qrnnd (q0, n1, n2, n1, d1);
+              umul_ppmm (m1, m0, q0, d0);
+
+              if (m1 > n1 || (m1 == n1 && m0 > n0))
+                {
+                  q0--;
+                  sub_ddmmss (m1, m0, m1, m0, d1, d0);
+                }
+
+              q1 = 0;
+
+              /* Remainder in (n1n0 - m1m0) >> bm.  */
+              if (rp != 0)
+                {
+                  sub_ddmmss (n1, n0, n1, n0, m1, m0);
+                  rr.s.low = (n1 << b) | (n0 >> bm);
+                  rr.s.high = n1 >> bm;
+                  *rp = rr.ll;
+                }
+            }
+        }
+    }
+
+  ww.s.low = q0;
+  ww.s.high = q1;
+  return ww.ll;
+}
+
+UDItype
+__udivdi3 (UDItype n, UDItype d)
+{
+  return __udivmoddi4 (n, d, (UDItype *) 0);
+}
+
+UDItype
+__umoddi3 (UDItype u, UDItype v)
+{
+  UDItype w;
+
+  (void) __udivmoddi4 (u ,v, &w);
+
+  return w;
+}
+