diff --git a/arch/i386/lib/Makefile b/arch/i386/lib/Makefile
new file mode 100644
index 0000000..7b1932d
--- /dev/null
+++ b/arch/i386/lib/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for i386-specific library files..
+#
+
+
+lib-y = checksum.o delay.o usercopy.o getuser.o putuser.o memcpy.o strstr.o \
+	bitops.o
+
+lib-$(CONFIG_X86_USE_3DNOW) += mmx.o
+lib-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o
diff --git a/arch/i386/lib/bitops.c b/arch/i386/lib/bitops.c
new file mode 100644
index 0000000..97db385
--- /dev/null
+++ b/arch/i386/lib/bitops.c
@@ -0,0 +1,70 @@
+#include <linux/bitops.h>
+#include <linux/module.h>
+
+/**
+ * find_next_bit - find the first set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The maximum size to search
+ */
+int find_next_bit(const unsigned long *addr, int size, int offset)
+{
+	const unsigned long *p = addr + (offset >> 5);
+	int set = 0, bit = offset & 31, res;
+
+	if (bit) {
+		/*
+		 * Look for nonzero in the first 32 bits:
+		 */
+		__asm__("bsfl %1,%0\n\t"
+			"jne 1f\n\t"
+			"movl $32, %0\n"
+			"1:"
+			: "=r" (set)
+			: "r" (*p >> bit));
+		if (set < (32 - bit))
+			return set + offset;
+		set = 32 - bit;
+		p++;
+	}
+	/*
+	 * No set bit yet, search remaining full words for a bit
+	 */
+	res = find_first_bit (p, size - 32 * (p - addr));
+	return (offset + set + res);
+}
+EXPORT_SYMBOL(find_next_bit);
+
+/**
+ * find_next_zero_bit - find the first zero bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The maximum size to search
+ */
+int find_next_zero_bit(const unsigned long *addr, int size, int offset)
+{
+	unsigned long * p = ((unsigned long *) addr) + (offset >> 5);
+	int set = 0, bit = offset & 31, res;
+
+	if (bit) {
+		/*
+		 * Look for zero in the first 32 bits.
+		 */
+		__asm__("bsfl %1,%0\n\t"
+			"jne 1f\n\t"
+			"movl $32, %0\n"
+			"1:"
+			: "=r" (set)
+			: "r" (~(*p >> bit)));
+		if (set < (32 - bit))
+			return set + offset;
+		set = 32 - bit;
+		p++;
+	}
+	/*
+	 * No zero yet, search remaining full bytes for a zero
+	 */
+	res = find_first_zero_bit (p, size - 32 * (p - (unsigned long *) addr));
+	return (offset + set + res);
+}
+EXPORT_SYMBOL(find_next_zero_bit);
diff --git a/arch/i386/lib/checksum.S b/arch/i386/lib/checksum.S
new file mode 100644
index 0000000..94c7867
--- /dev/null
+++ b/arch/i386/lib/checksum.S
@@ -0,0 +1,496 @@
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		IP/TCP/UDP checksumming routines
+ *
+ * Authors:	Jorge Cwik, <jorge@laser.satlink.net>
+ *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
+ *		Tom May, <ftom@netcom.com>
+ *              Pentium Pro/II routines:
+ *              Alexander Kjeldaas <astor@guardian.no>
+ *              Finn Arne Gangstad <finnag@guardian.no>
+ *		Lots of code moved from tcp.c and ip.c; see those files
+ *		for more names.
+ *
+ * Changes:     Ingo Molnar, converted csum_partial_copy() to 2.1 exception
+ *			     handling.
+ *		Andi Kleen,  add zeroing on error
+ *                   converted to pure assembler
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <asm/errno.h>
+				
+/*
+ * computes a partial checksum, e.g. for TCP/UDP fragments
+ */
+
+/*	
+unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
+ */
+		
+.text
+.align 4
+.globl csum_partial								
+		
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+	  /*		
+	   * Experiments with Ethernet and SLIP connections show that buff
+	   * is aligned on either a 2-byte or 4-byte boundary.  We get at
+	   * least a twofold speedup on 486 and Pentium if it is 4-byte aligned.
+	   * Fortunately, it is easy to convert 2-byte alignment to 4-byte
+	   * alignment for the unrolled loop.
+	   */		
+csum_partial:	
+	pushl %esi
+	pushl %ebx
+	movl 20(%esp),%eax	# Function arg: unsigned int sum
+	movl 16(%esp),%ecx	# Function arg: int len
+	movl 12(%esp),%esi	# Function arg: unsigned char *buff
+	testl $3, %esi		# Check alignment.
+	jz 2f			# Jump if alignment is ok.
+	testl $1, %esi		# Check alignment.
+	jz 10f			# Jump if alignment is boundary of 2bytes.
+
+	# buf is odd
+	dec %ecx
+	jl 8f
+	movzbl (%esi), %ebx
+	adcl %ebx, %eax
+	roll $8, %eax
+	inc %esi
+	testl $2, %esi
+	jz 2f
+10:
+	subl $2, %ecx		# Alignment uses up two bytes.
+	jae 1f			# Jump if we had at least two bytes.
+	addl $2, %ecx		# ecx was < 2.  Deal with it.
+	jmp 4f
+1:	movw (%esi), %bx
+	addl $2, %esi
+	addw %bx, %ax
+	adcl $0, %eax
+2:
+	movl %ecx, %edx
+	shrl $5, %ecx
+	jz 2f
+	testl %esi, %esi
+1:	movl (%esi), %ebx
+	adcl %ebx, %eax
+	movl 4(%esi), %ebx
+	adcl %ebx, %eax
+	movl 8(%esi), %ebx
+	adcl %ebx, %eax
+	movl 12(%esi), %ebx
+	adcl %ebx, %eax
+	movl 16(%esi), %ebx
+	adcl %ebx, %eax
+	movl 20(%esi), %ebx
+	adcl %ebx, %eax
+	movl 24(%esi), %ebx
+	adcl %ebx, %eax
+	movl 28(%esi), %ebx
+	adcl %ebx, %eax
+	lea 32(%esi), %esi
+	dec %ecx
+	jne 1b
+	adcl $0, %eax
+2:	movl %edx, %ecx
+	andl $0x1c, %edx
+	je 4f
+	shrl $2, %edx		# This clears CF
+3:	adcl (%esi), %eax
+	lea 4(%esi), %esi
+	dec %edx
+	jne 3b
+	adcl $0, %eax
+4:	andl $3, %ecx
+	jz 7f
+	cmpl $2, %ecx
+	jb 5f
+	movw (%esi),%cx
+	leal 2(%esi),%esi
+	je 6f
+	shll $16,%ecx
+5:	movb (%esi),%cl
+6:	addl %ecx,%eax
+	adcl $0, %eax 
+7:	
+	testl $1, 12(%esp)
+	jz 8f
+	roll $8, %eax
+8:
+	popl %ebx
+	popl %esi
+	ret
+
+#else
+
+/* Version for PentiumII/PPro */
+
+csum_partial:
+	pushl %esi
+	pushl %ebx
+	movl 20(%esp),%eax	# Function arg: unsigned int sum
+	movl 16(%esp),%ecx	# Function arg: int len
+	movl 12(%esp),%esi	# Function arg:	const unsigned char *buf
+
+	testl $3, %esi         
+	jnz 25f                 
+10:
+	movl %ecx, %edx
+	movl %ecx, %ebx
+	andl $0x7c, %ebx
+	shrl $7, %ecx
+	addl %ebx,%esi
+	shrl $2, %ebx  
+	negl %ebx
+	lea 45f(%ebx,%ebx,2), %ebx
+	testl %esi, %esi
+	jmp *%ebx
+
+	# Handle 2-byte-aligned regions
+20:	addw (%esi), %ax
+	lea 2(%esi), %esi
+	adcl $0, %eax
+	jmp 10b
+25:
+	testl $1, %esi         
+	jz 30f                 
+	# buf is odd
+	dec %ecx
+	jl 90f
+	movzbl (%esi), %ebx
+	addl %ebx, %eax
+	adcl $0, %eax
+	roll $8, %eax
+	inc %esi
+	testl $2, %esi
+	jz 10b
+
+30:	subl $2, %ecx          
+	ja 20b                 
+	je 32f
+	addl $2, %ecx
+	jz 80f
+	movzbl (%esi),%ebx	# csumming 1 byte, 2-aligned
+	addl %ebx, %eax
+	adcl $0, %eax
+	jmp 80f
+32:
+	addw (%esi), %ax	# csumming 2 bytes, 2-aligned
+	adcl $0, %eax
+	jmp 80f
+
+40: 
+	addl -128(%esi), %eax
+	adcl -124(%esi), %eax
+	adcl -120(%esi), %eax
+	adcl -116(%esi), %eax   
+	adcl -112(%esi), %eax   
+	adcl -108(%esi), %eax
+	adcl -104(%esi), %eax
+	adcl -100(%esi), %eax
+	adcl -96(%esi), %eax
+	adcl -92(%esi), %eax
+	adcl -88(%esi), %eax
+	adcl -84(%esi), %eax
+	adcl -80(%esi), %eax
+	adcl -76(%esi), %eax
+	adcl -72(%esi), %eax
+	adcl -68(%esi), %eax
+	adcl -64(%esi), %eax     
+	adcl -60(%esi), %eax     
+	adcl -56(%esi), %eax     
+	adcl -52(%esi), %eax   
+	adcl -48(%esi), %eax   
+	adcl -44(%esi), %eax
+	adcl -40(%esi), %eax
+	adcl -36(%esi), %eax
+	adcl -32(%esi), %eax
+	adcl -28(%esi), %eax
+	adcl -24(%esi), %eax
+	adcl -20(%esi), %eax
+	adcl -16(%esi), %eax
+	adcl -12(%esi), %eax
+	adcl -8(%esi), %eax
+	adcl -4(%esi), %eax
+45:
+	lea 128(%esi), %esi
+	adcl $0, %eax
+	dec %ecx
+	jge 40b
+	movl %edx, %ecx
+50:	andl $3, %ecx
+	jz 80f
+
+	# Handle the last 1-3 bytes without jumping
+	notl %ecx		# 1->2, 2->1, 3->0, higher bits are masked
+	movl $0xffffff,%ebx	# by the shll and shrl instructions
+	shll $3,%ecx
+	shrl %cl,%ebx
+	andl -128(%esi),%ebx	# esi is 4-aligned so should be ok
+	addl %ebx,%eax
+	adcl $0,%eax
+80: 
+	testl $1, 12(%esp)
+	jz 90f
+	roll $8, %eax
+90: 
+	popl %ebx
+	popl %esi
+	ret
+				
+#endif
+
+/*
+unsigned int csum_partial_copy_generic (const char *src, char *dst,
+				  int len, int sum, int *src_err_ptr, int *dst_err_ptr)
+ */ 
+
+/*
+ * Copy from ds while checksumming, otherwise like csum_partial
+ *
+ * The macros SRC and DST specify the type of access for the instruction.
+ * thus we can call a custom exception handler for all access types.
+ *
+ * FIXME: could someone double-check whether I haven't mixed up some SRC and
+ *	  DST definitions? It's damn hard to trigger all cases.  I hope I got
+ *	  them all but there's no guarantee.
+ */
+
+#define SRC(y...)			\
+	9999: y;			\
+	.section __ex_table, "a";	\
+	.long 9999b, 6001f	;	\
+	.previous
+
+#define DST(y...)			\
+	9999: y;			\
+	.section __ex_table, "a";	\
+	.long 9999b, 6002f	;	\
+	.previous
+
+.align 4
+.globl csum_partial_copy_generic
+				
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+#define ARGBASE 16		
+#define FP		12
+		
+csum_partial_copy_generic:
+	subl  $4,%esp	
+	pushl %edi
+	pushl %esi
+	pushl %ebx
+	movl ARGBASE+16(%esp),%eax	# sum
+	movl ARGBASE+12(%esp),%ecx	# len
+	movl ARGBASE+4(%esp),%esi	# src
+	movl ARGBASE+8(%esp),%edi	# dst
+
+	testl $2, %edi			# Check alignment. 
+	jz 2f				# Jump if alignment is ok.
+	subl $2, %ecx			# Alignment uses up two bytes.
+	jae 1f				# Jump if we had at least two bytes.
+	addl $2, %ecx			# ecx was < 2.  Deal with it.
+	jmp 4f
+SRC(1:	movw (%esi), %bx	)
+	addl $2, %esi
+DST(	movw %bx, (%edi)	)
+	addl $2, %edi
+	addw %bx, %ax	
+	adcl $0, %eax
+2:
+	movl %ecx, FP(%esp)
+	shrl $5, %ecx
+	jz 2f
+	testl %esi, %esi
+SRC(1:	movl (%esi), %ebx	)
+SRC(	movl 4(%esi), %edx	)
+	adcl %ebx, %eax
+DST(	movl %ebx, (%edi)	)
+	adcl %edx, %eax
+DST(	movl %edx, 4(%edi)	)
+
+SRC(	movl 8(%esi), %ebx	)
+SRC(	movl 12(%esi), %edx	)
+	adcl %ebx, %eax
+DST(	movl %ebx, 8(%edi)	)
+	adcl %edx, %eax
+DST(	movl %edx, 12(%edi)	)
+
+SRC(	movl 16(%esi), %ebx 	)
+SRC(	movl 20(%esi), %edx	)
+	adcl %ebx, %eax
+DST(	movl %ebx, 16(%edi)	)
+	adcl %edx, %eax
+DST(	movl %edx, 20(%edi)	)
+
+SRC(	movl 24(%esi), %ebx	)
+SRC(	movl 28(%esi), %edx	)
+	adcl %ebx, %eax
+DST(	movl %ebx, 24(%edi)	)
+	adcl %edx, %eax
+DST(	movl %edx, 28(%edi)	)
+
+	lea 32(%esi), %esi
+	lea 32(%edi), %edi
+	dec %ecx
+	jne 1b
+	adcl $0, %eax
+2:	movl FP(%esp), %edx
+	movl %edx, %ecx
+	andl $0x1c, %edx
+	je 4f
+	shrl $2, %edx			# This clears CF
+SRC(3:	movl (%esi), %ebx	)
+	adcl %ebx, %eax
+DST(	movl %ebx, (%edi)	)
+	lea 4(%esi), %esi
+	lea 4(%edi), %edi
+	dec %edx
+	jne 3b
+	adcl $0, %eax
+4:	andl $3, %ecx
+	jz 7f
+	cmpl $2, %ecx
+	jb 5f
+SRC(	movw (%esi), %cx	)
+	leal 2(%esi), %esi
+DST(	movw %cx, (%edi)	)
+	leal 2(%edi), %edi
+	je 6f
+	shll $16,%ecx
+SRC(5:	movb (%esi), %cl	)
+DST(	movb %cl, (%edi)	)
+6:	addl %ecx, %eax
+	adcl $0, %eax
+7:
+5000:
+
+# Exception handler:
+.section .fixup, "ax"							
+
+6001:
+	movl ARGBASE+20(%esp), %ebx	# src_err_ptr
+	movl $-EFAULT, (%ebx)
+
+	# zero the complete destination - computing the rest
+	# is too much work 
+	movl ARGBASE+8(%esp), %edi	# dst
+	movl ARGBASE+12(%esp), %ecx	# len
+	xorl %eax,%eax
+	rep ; stosb
+
+	jmp 5000b
+
+6002:
+	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
+	movl $-EFAULT,(%ebx)
+	jmp 5000b
+
+.previous
+
+	popl %ebx
+	popl %esi
+	popl %edi
+	popl %ecx			# equivalent to addl $4,%esp
+	ret	
+
+#else
+
+/* Version for PentiumII/PPro */
+
+#define ROUND1(x) \
+	SRC(movl x(%esi), %ebx	)	;	\
+	addl %ebx, %eax			;	\
+	DST(movl %ebx, x(%edi)	)	; 
+
+#define ROUND(x) \
+	SRC(movl x(%esi), %ebx	)	;	\
+	adcl %ebx, %eax			;	\
+	DST(movl %ebx, x(%edi)	)	;
+
+#define ARGBASE 12
+		
+csum_partial_copy_generic:
+	pushl %ebx
+	pushl %edi
+	pushl %esi
+	movl ARGBASE+4(%esp),%esi	#src
+	movl ARGBASE+8(%esp),%edi	#dst	
+	movl ARGBASE+12(%esp),%ecx	#len
+	movl ARGBASE+16(%esp),%eax	#sum
+#	movl %ecx, %edx  
+	movl %ecx, %ebx  
+	movl %esi, %edx
+	shrl $6, %ecx     
+	andl $0x3c, %ebx  
+	negl %ebx
+	subl %ebx, %esi  
+	subl %ebx, %edi  
+	lea  -1(%esi),%edx
+	andl $-32,%edx
+	lea 3f(%ebx,%ebx), %ebx
+	testl %esi, %esi 
+	jmp *%ebx
+1:	addl $64,%esi
+	addl $64,%edi 
+	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
+	ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)	
+	ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)	
+	ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)	
+	ROUND (-16) ROUND(-12) ROUND(-8)  ROUND(-4)	
+3:	adcl $0,%eax
+	addl $64, %edx
+	dec %ecx
+	jge 1b
+4:	movl ARGBASE+12(%esp),%edx	#len
+	andl $3, %edx
+	jz 7f
+	cmpl $2, %edx
+	jb 5f
+SRC(	movw (%esi), %dx         )
+	leal 2(%esi), %esi
+DST(	movw %dx, (%edi)         )
+	leal 2(%edi), %edi
+	je 6f
+	shll $16,%edx
+5:
+SRC(	movb (%esi), %dl         )
+DST(	movb %dl, (%edi)         )
+6:	addl %edx, %eax
+	adcl $0, %eax
+7:
+.section .fixup, "ax"
+6001:	movl	ARGBASE+20(%esp), %ebx	# src_err_ptr	
+	movl $-EFAULT, (%ebx)
+	# zero the complete destination (computing the rest is too much work)
+	movl ARGBASE+8(%esp),%edi	# dst
+	movl ARGBASE+12(%esp),%ecx	# len
+	xorl %eax,%eax
+	rep; stosb
+	jmp 7b
+6002:	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
+	movl $-EFAULT, (%ebx)
+	jmp  7b			
+.previous				
+
+	popl %esi
+	popl %edi
+	popl %ebx
+	ret
+				
+#undef ROUND
+#undef ROUND1		
+		
+#endif
diff --git a/arch/i386/lib/dec_and_lock.c b/arch/i386/lib/dec_and_lock.c
new file mode 100644
index 0000000..ab43394
--- /dev/null
+++ b/arch/i386/lib/dec_and_lock.c
@@ -0,0 +1,40 @@
+/*
+ * x86 version of "atomic_dec_and_lock()" using
+ * the atomic "cmpxchg" instruction.
+ *
+ * (For CPU's lacking cmpxchg, we use the slow
+ * generic version, and this one never even gets
+ * compiled).
+ */
+
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+
+int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
+{
+	int counter;
+	int newcount;
+
+repeat:
+	counter = atomic_read(atomic);
+	newcount = counter-1;
+
+	if (!newcount)
+		goto slow_path;
+
+	asm volatile("lock; cmpxchgl %1,%2"
+		:"=a" (newcount)
+		:"r" (newcount), "m" (atomic->counter), "0" (counter));
+
+	/* If the above failed, "eax" will have changed */
+	if (newcount != counter)
+		goto repeat;
+	return 0;
+
+slow_path:
+	spin_lock(lock);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	spin_unlock(lock);
+	return 0;
+}
diff --git a/arch/i386/lib/delay.c b/arch/i386/lib/delay.c
new file mode 100644
index 0000000..080639f
--- /dev/null
+++ b/arch/i386/lib/delay.c
@@ -0,0 +1,49 @@
+/*
+ *	Precise Delay Loops for i386
+ *
+ *	Copyright (C) 1993 Linus Torvalds
+ *	Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *
+ *	The __delay function must _NOT_ be inlined as its execution time
+ *	depends wildly on alignment on many x86 processors. The additional
+ *	jump magic is needed to get the timing stable on all the CPU's
+ *	we have to worry about.
+ */
+
+#include <linux/config.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <asm/processor.h>
+#include <asm/delay.h>
+#include <asm/timer.h>
+
+#ifdef CONFIG_SMP
+#include <asm/smp.h>
+#endif
+
+extern struct timer_opts* timer;
+
+void __delay(unsigned long loops)
+{
+	cur_timer->delay(loops);
+}
+
+inline void __const_udelay(unsigned long xloops)
+{
+	int d0;
+	xloops *= 4;
+	__asm__("mull %0"
+		:"=d" (xloops), "=&a" (d0)
+		:"1" (xloops),"0" (cpu_data[_smp_processor_id()].loops_per_jiffy * (HZ/4)));
+        __delay(++xloops);
+}
+
+void __udelay(unsigned long usecs)
+{
+	__const_udelay(usecs * 0x000010c7);  /* 2**32 / 1000000 (rounded up) */
+}
+
+void __ndelay(unsigned long nsecs)
+{
+	__const_udelay(nsecs * 0x00005);  /* 2**32 / 1000000000 (rounded up) */
+}
diff --git a/arch/i386/lib/getuser.S b/arch/i386/lib/getuser.S
new file mode 100644
index 0000000..62d7f17
--- /dev/null
+++ b/arch/i386/lib/getuser.S
@@ -0,0 +1,70 @@
+/*
+ * __get_user functions.
+ *
+ * (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.
+ */
+#include <asm/thread_info.h>
+
+
+/*
+ * __get_user_X
+ *
+ * Inputs:	%eax contains the address
+ *
+ * Outputs:	%eax is error code (0 or -EFAULT)
+ *		%edx contains zero-extended value
+ *
+ * These functions should not modify any other registers,
+ * as they get called from within inline assembly.
+ */
+
+.text
+.align 4
+.globl __get_user_1
+__get_user_1:
+	GET_THREAD_INFO(%edx)
+	cmpl TI_addr_limit(%edx),%eax
+	jae bad_get_user
+1:	movzbl (%eax),%edx
+	xorl %eax,%eax
+	ret
+
+.align 4
+.globl __get_user_2
+__get_user_2:
+	addl $1,%eax
+	jc bad_get_user
+	GET_THREAD_INFO(%edx)
+	cmpl TI_addr_limit(%edx),%eax
+	jae bad_get_user
+2:	movzwl -1(%eax),%edx
+	xorl %eax,%eax
+	ret
+
+.align 4
+.globl __get_user_4
+__get_user_4:
+	addl $3,%eax
+	jc bad_get_user
+	GET_THREAD_INFO(%edx)
+	cmpl TI_addr_limit(%edx),%eax
+	jae bad_get_user
+3:	movl -3(%eax),%edx
+	xorl %eax,%eax
+	ret
+
+bad_get_user:
+	xorl %edx,%edx
+	movl $-14,%eax
+	ret
+
+.section __ex_table,"a"
+	.long 1b,bad_get_user
+	.long 2b,bad_get_user
+	.long 3b,bad_get_user
+.previous
diff --git a/arch/i386/lib/memcpy.c b/arch/i386/lib/memcpy.c
new file mode 100644
index 0000000..891b235
--- /dev/null
+++ b/arch/i386/lib/memcpy.c
@@ -0,0 +1,44 @@
+#include <linux/config.h>
+#include <linux/string.h>
+#include <linux/module.h>
+
+#undef memcpy
+#undef memset
+
+void *memcpy(void *to, const void *from, size_t n)
+{
+#ifdef CONFIG_X86_USE_3DNOW
+	return __memcpy3d(to, from, n);
+#else
+	return __memcpy(to, from, n);
+#endif
+}
+EXPORT_SYMBOL(memcpy);
+
+void *memset(void *s, int c, size_t count)
+{
+	return __memset(s, c, count);
+}
+EXPORT_SYMBOL(memset);
+
+void *memmove(void *dest, const void *src, size_t n)
+{
+	int d0, d1, d2;
+
+	if (dest < src) {
+		memcpy(dest,src,n);
+	} else {
+		__asm__ __volatile__(
+			"std\n\t"
+			"rep\n\t"
+			"movsb\n\t"
+			"cld"
+			: "=&c" (d0), "=&S" (d1), "=&D" (d2)
+			:"0" (n),
+			 "1" (n-1+(const char *)src),
+			 "2" (n-1+(char *)dest)
+			:"memory");
+	}
+	return dest;
+}
+EXPORT_SYMBOL(memmove);
diff --git a/arch/i386/lib/mmx.c b/arch/i386/lib/mmx.c
new file mode 100644
index 0000000..01f8b1a
--- /dev/null
+++ b/arch/i386/lib/mmx.c
@@ -0,0 +1,399 @@
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/hardirq.h>
+
+#include <asm/i387.h>
+
+
+/*
+ *	MMX 3DNow! library helper functions
+ *
+ *	To do:
+ *	We can use MMX just for prefetch in IRQ's. This may be a win. 
+ *		(reported so on K6-III)
+ *	We should use a better code neutral filler for the short jump
+ *		leal ebx. [ebx] is apparently best for K6-2, but Cyrix ??
+ *	We also want to clobber the filler register so we don't get any
+ *		register forwarding stalls on the filler. 
+ *
+ *	Add *user handling. Checksums are not a win with MMX on any CPU
+ *	tested so far for any MMX solution figured.
+ *
+ *	22/09/2000 - Arjan van de Ven 
+ *		Improved for non-egineering-sample Athlons 
+ *
+ */
+ 
+void *_mmx_memcpy(void *to, const void *from, size_t len)
+{
+	void *p;
+	int i;
+
+	if (unlikely(in_interrupt()))
+		return __memcpy(to, from, len);
+
+	p = to;
+	i = len >> 6; /* len/64 */
+
+	kernel_fpu_begin();
+
+	__asm__ __volatile__ (
+		"1: prefetch (%0)\n"		/* This set is 28 bytes */
+		"   prefetch 64(%0)\n"
+		"   prefetch 128(%0)\n"
+		"   prefetch 192(%0)\n"
+		"   prefetch 256(%0)\n"
+		"2:  \n"
+		".section .fixup, \"ax\"\n"
+		"3: movw $0x1AEB, 1b\n"	/* jmp on 26 bytes */
+		"   jmp 2b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4\n"
+		"	.long 1b, 3b\n"
+		".previous"
+		: : "r" (from) );
+		
+	
+	for(; i>5; i--)
+	{
+		__asm__ __volatile__ (
+		"1:  prefetch 320(%0)\n"
+		"2:  movq (%0), %%mm0\n"
+		"  movq 8(%0), %%mm1\n"
+		"  movq 16(%0), %%mm2\n"
+		"  movq 24(%0), %%mm3\n"
+		"  movq %%mm0, (%1)\n"
+		"  movq %%mm1, 8(%1)\n"
+		"  movq %%mm2, 16(%1)\n"
+		"  movq %%mm3, 24(%1)\n"
+		"  movq 32(%0), %%mm0\n"
+		"  movq 40(%0), %%mm1\n"
+		"  movq 48(%0), %%mm2\n"
+		"  movq 56(%0), %%mm3\n"
+		"  movq %%mm0, 32(%1)\n"
+		"  movq %%mm1, 40(%1)\n"
+		"  movq %%mm2, 48(%1)\n"
+		"  movq %%mm3, 56(%1)\n"
+		".section .fixup, \"ax\"\n"
+		"3: movw $0x05EB, 1b\n"	/* jmp on 5 bytes */
+		"   jmp 2b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4\n"
+		"	.long 1b, 3b\n"
+		".previous"
+		: : "r" (from), "r" (to) : "memory");
+		from+=64;
+		to+=64;
+	}
+
+	for(; i>0; i--)
+	{
+		__asm__ __volatile__ (
+		"  movq (%0), %%mm0\n"
+		"  movq 8(%0), %%mm1\n"
+		"  movq 16(%0), %%mm2\n"
+		"  movq 24(%0), %%mm3\n"
+		"  movq %%mm0, (%1)\n"
+		"  movq %%mm1, 8(%1)\n"
+		"  movq %%mm2, 16(%1)\n"
+		"  movq %%mm3, 24(%1)\n"
+		"  movq 32(%0), %%mm0\n"
+		"  movq 40(%0), %%mm1\n"
+		"  movq 48(%0), %%mm2\n"
+		"  movq 56(%0), %%mm3\n"
+		"  movq %%mm0, 32(%1)\n"
+		"  movq %%mm1, 40(%1)\n"
+		"  movq %%mm2, 48(%1)\n"
+		"  movq %%mm3, 56(%1)\n"
+		: : "r" (from), "r" (to) : "memory");
+		from+=64;
+		to+=64;
+	}
+	/*
+	 *	Now do the tail of the block
+	 */
+	__memcpy(to, from, len&63);
+	kernel_fpu_end();
+	return p;
+}
+
+#ifdef CONFIG_MK7
+
+/*
+ *	The K7 has streaming cache bypass load/store. The Cyrix III, K6 and
+ *	other MMX using processors do not.
+ */
+
+static void fast_clear_page(void *page)
+{
+	int i;
+
+	kernel_fpu_begin();
+	
+	__asm__ __volatile__ (
+		"  pxor %%mm0, %%mm0\n" : :
+	);
+
+	for(i=0;i<4096/64;i++)
+	{
+		__asm__ __volatile__ (
+		"  movntq %%mm0, (%0)\n"
+		"  movntq %%mm0, 8(%0)\n"
+		"  movntq %%mm0, 16(%0)\n"
+		"  movntq %%mm0, 24(%0)\n"
+		"  movntq %%mm0, 32(%0)\n"
+		"  movntq %%mm0, 40(%0)\n"
+		"  movntq %%mm0, 48(%0)\n"
+		"  movntq %%mm0, 56(%0)\n"
+		: : "r" (page) : "memory");
+		page+=64;
+	}
+	/* since movntq is weakly-ordered, a "sfence" is needed to become
+	 * ordered again.
+	 */
+	__asm__ __volatile__ (
+		"  sfence \n" : :
+	);
+	kernel_fpu_end();
+}
+
+static void fast_copy_page(void *to, void *from)
+{
+	int i;
+
+	kernel_fpu_begin();
+
+	/* maybe the prefetch stuff can go before the expensive fnsave...
+	 * but that is for later. -AV
+	 */
+	__asm__ __volatile__ (
+		"1: prefetch (%0)\n"
+		"   prefetch 64(%0)\n"
+		"   prefetch 128(%0)\n"
+		"   prefetch 192(%0)\n"
+		"   prefetch 256(%0)\n"
+		"2:  \n"
+		".section .fixup, \"ax\"\n"
+		"3: movw $0x1AEB, 1b\n"	/* jmp on 26 bytes */
+		"   jmp 2b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4\n"
+		"	.long 1b, 3b\n"
+		".previous"
+		: : "r" (from) );
+
+	for(i=0; i<(4096-320)/64; i++)
+	{
+		__asm__ __volatile__ (
+		"1: prefetch 320(%0)\n"
+		"2: movq (%0), %%mm0\n"
+		"   movntq %%mm0, (%1)\n"
+		"   movq 8(%0), %%mm1\n"
+		"   movntq %%mm1, 8(%1)\n"
+		"   movq 16(%0), %%mm2\n"
+		"   movntq %%mm2, 16(%1)\n"
+		"   movq 24(%0), %%mm3\n"
+		"   movntq %%mm3, 24(%1)\n"
+		"   movq 32(%0), %%mm4\n"
+		"   movntq %%mm4, 32(%1)\n"
+		"   movq 40(%0), %%mm5\n"
+		"   movntq %%mm5, 40(%1)\n"
+		"   movq 48(%0), %%mm6\n"
+		"   movntq %%mm6, 48(%1)\n"
+		"   movq 56(%0), %%mm7\n"
+		"   movntq %%mm7, 56(%1)\n"
+		".section .fixup, \"ax\"\n"
+		"3: movw $0x05EB, 1b\n"	/* jmp on 5 bytes */
+		"   jmp 2b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4\n"
+		"	.long 1b, 3b\n"
+		".previous"
+		: : "r" (from), "r" (to) : "memory");
+		from+=64;
+		to+=64;
+	}
+	for(i=(4096-320)/64; i<4096/64; i++)
+	{
+		__asm__ __volatile__ (
+		"2: movq (%0), %%mm0\n"
+		"   movntq %%mm0, (%1)\n"
+		"   movq 8(%0), %%mm1\n"
+		"   movntq %%mm1, 8(%1)\n"
+		"   movq 16(%0), %%mm2\n"
+		"   movntq %%mm2, 16(%1)\n"
+		"   movq 24(%0), %%mm3\n"
+		"   movntq %%mm3, 24(%1)\n"
+		"   movq 32(%0), %%mm4\n"
+		"   movntq %%mm4, 32(%1)\n"
+		"   movq 40(%0), %%mm5\n"
+		"   movntq %%mm5, 40(%1)\n"
+		"   movq 48(%0), %%mm6\n"
+		"   movntq %%mm6, 48(%1)\n"
+		"   movq 56(%0), %%mm7\n"
+		"   movntq %%mm7, 56(%1)\n"
+		: : "r" (from), "r" (to) : "memory");
+		from+=64;
+		to+=64;
+	}
+	/* since movntq is weakly-ordered, a "sfence" is needed to become
+	 * ordered again.
+	 */
+	__asm__ __volatile__ (
+		"  sfence \n" : :
+	);
+	kernel_fpu_end();
+}
+
+#else
+
+/*
+ *	Generic MMX implementation without K7 specific streaming
+ */
+ 
+static void fast_clear_page(void *page)
+{
+	int i;
+	
+	kernel_fpu_begin();
+	
+	__asm__ __volatile__ (
+		"  pxor %%mm0, %%mm0\n" : :
+	);
+
+	for(i=0;i<4096/128;i++)
+	{
+		__asm__ __volatile__ (
+		"  movq %%mm0, (%0)\n"
+		"  movq %%mm0, 8(%0)\n"
+		"  movq %%mm0, 16(%0)\n"
+		"  movq %%mm0, 24(%0)\n"
+		"  movq %%mm0, 32(%0)\n"
+		"  movq %%mm0, 40(%0)\n"
+		"  movq %%mm0, 48(%0)\n"
+		"  movq %%mm0, 56(%0)\n"
+		"  movq %%mm0, 64(%0)\n"
+		"  movq %%mm0, 72(%0)\n"
+		"  movq %%mm0, 80(%0)\n"
+		"  movq %%mm0, 88(%0)\n"
+		"  movq %%mm0, 96(%0)\n"
+		"  movq %%mm0, 104(%0)\n"
+		"  movq %%mm0, 112(%0)\n"
+		"  movq %%mm0, 120(%0)\n"
+		: : "r" (page) : "memory");
+		page+=128;
+	}
+
+	kernel_fpu_end();
+}
+
+static void fast_copy_page(void *to, void *from)
+{
+	int i;
+	
+	
+	kernel_fpu_begin();
+
+	__asm__ __volatile__ (
+		"1: prefetch (%0)\n"
+		"   prefetch 64(%0)\n"
+		"   prefetch 128(%0)\n"
+		"   prefetch 192(%0)\n"
+		"   prefetch 256(%0)\n"
+		"2:  \n"
+		".section .fixup, \"ax\"\n"
+		"3: movw $0x1AEB, 1b\n"	/* jmp on 26 bytes */
+		"   jmp 2b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4\n"
+		"	.long 1b, 3b\n"
+		".previous"
+		: : "r" (from) );
+
+	for(i=0; i<4096/64; i++)
+	{
+		__asm__ __volatile__ (
+		"1: prefetch 320(%0)\n"
+		"2: movq (%0), %%mm0\n"
+		"   movq 8(%0), %%mm1\n"
+		"   movq 16(%0), %%mm2\n"
+		"   movq 24(%0), %%mm3\n"
+		"   movq %%mm0, (%1)\n"
+		"   movq %%mm1, 8(%1)\n"
+		"   movq %%mm2, 16(%1)\n"
+		"   movq %%mm3, 24(%1)\n"
+		"   movq 32(%0), %%mm0\n"
+		"   movq 40(%0), %%mm1\n"
+		"   movq 48(%0), %%mm2\n"
+		"   movq 56(%0), %%mm3\n"
+		"   movq %%mm0, 32(%1)\n"
+		"   movq %%mm1, 40(%1)\n"
+		"   movq %%mm2, 48(%1)\n"
+		"   movq %%mm3, 56(%1)\n"
+		".section .fixup, \"ax\"\n"
+		"3: movw $0x05EB, 1b\n"	/* jmp on 5 bytes */
+		"   jmp 2b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4\n"
+		"	.long 1b, 3b\n"
+		".previous"
+		: : "r" (from), "r" (to) : "memory");
+		from+=64;
+		to+=64;
+	}
+	kernel_fpu_end();
+}
+
+
+#endif
+
+/*
+ *	Favour MMX for page clear and copy. 
+ */
+
+static void slow_zero_page(void * page)
+{
+	int d0, d1;
+	__asm__ __volatile__( \
+		"cld\n\t" \
+		"rep ; stosl" \
+		: "=&c" (d0), "=&D" (d1)
+		:"a" (0),"1" (page),"0" (1024)
+		:"memory");
+}
+ 
+void mmx_clear_page(void * page)
+{
+	if(unlikely(in_interrupt()))
+		slow_zero_page(page);
+	else
+		fast_clear_page(page);
+}
+
+static void slow_copy_page(void *to, void *from)
+{
+	int d0, d1, d2;
+	__asm__ __volatile__( \
+		"cld\n\t" \
+		"rep ; movsl" \
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2) \
+		: "0" (1024),"1" ((long) to),"2" ((long) from) \
+		: "memory");
+}
+  
+
+void mmx_copy_page(void *to, void *from)
+{
+	if(unlikely(in_interrupt()))
+		slow_copy_page(to, from);
+	else
+		fast_copy_page(to, from);
+}
diff --git a/arch/i386/lib/putuser.S b/arch/i386/lib/putuser.S
new file mode 100644
index 0000000..a32d9f5
--- /dev/null
+++ b/arch/i386/lib/putuser.S
@@ -0,0 +1,87 @@
+/*
+ * __put_user functions.
+ *
+ * (C) Copyright 2005 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.
+ */
+#include <asm/thread_info.h>
+
+
+/*
+ * __put_user_X
+ *
+ * Inputs:	%eax[:%edx] contains the data
+ *		%ecx contains the address
+ *
+ * Outputs:	%eax is error code (0 or -EFAULT)
+ *
+ * These functions should not modify any other registers,
+ * as they get called from within inline assembly.
+ */
+
+#define ENTER	pushl %ebx ; GET_THREAD_INFO(%ebx)
+#define EXIT	popl %ebx ; ret
+
+.text
+.align 4
+.globl __put_user_1
+__put_user_1:
+	ENTER
+	cmpl TI_addr_limit(%ebx),%ecx
+	jae bad_put_user
+1:	movb %al,(%ecx)
+	xorl %eax,%eax
+	EXIT
+
+.align 4
+.globl __put_user_2
+__put_user_2:
+	ENTER
+	movl TI_addr_limit(%ebx),%ebx
+	subl $1,%ebx
+	cmpl %ebx,%ecx
+	jae bad_put_user
+2:	movw %ax,(%ecx)
+	xorl %eax,%eax
+	EXIT
+
+.align 4
+.globl __put_user_4
+__put_user_4:
+	ENTER
+	movl TI_addr_limit(%ebx),%ebx
+	subl $3,%ebx
+	cmpl %ebx,%ecx
+	jae bad_put_user
+3:	movl %eax,(%ecx)
+	xorl %eax,%eax
+	EXIT
+
+.align 4
+.globl __put_user_8
+__put_user_8:
+	ENTER
+	movl TI_addr_limit(%ebx),%ebx
+	subl $7,%ebx
+	cmpl %ebx,%ecx
+	jae bad_put_user
+4:	movl %eax,(%ecx)
+5:	movl %edx,4(%ecx)
+	xorl %eax,%eax
+	EXIT
+
+bad_put_user:
+	movl $-14,%eax
+	EXIT
+
+.section __ex_table,"a"
+	.long 1b,bad_put_user
+	.long 2b,bad_put_user
+	.long 3b,bad_put_user
+	.long 4b,bad_put_user
+	.long 5b,bad_put_user
+.previous
diff --git a/arch/i386/lib/strstr.c b/arch/i386/lib/strstr.c
new file mode 100644
index 0000000..a3dafbf
--- /dev/null
+++ b/arch/i386/lib/strstr.c
@@ -0,0 +1,31 @@
+#include <linux/string.h>
+
+char * strstr(const char * cs,const char * ct)
+{
+int	d0, d1;
+register char * __res;
+__asm__ __volatile__(
+	"movl %6,%%edi\n\t"
+	"repne\n\t"
+	"scasb\n\t"
+	"notl %%ecx\n\t"
+	"decl %%ecx\n\t"	/* NOTE! This also sets Z if searchstring='' */
+	"movl %%ecx,%%edx\n"
+	"1:\tmovl %6,%%edi\n\t"
+	"movl %%esi,%%eax\n\t"
+	"movl %%edx,%%ecx\n\t"
+	"repe\n\t"
+	"cmpsb\n\t"
+	"je 2f\n\t"		/* also works for empty string, see above */
+	"xchgl %%eax,%%esi\n\t"
+	"incl %%esi\n\t"
+	"cmpb $0,-1(%%eax)\n\t"
+	"jne 1b\n\t"
+	"xorl %%eax,%%eax\n\t"
+	"2:"
+	:"=a" (__res), "=&c" (d0), "=&S" (d1)
+	:"0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
+	:"dx", "di");
+return __res;
+}
+
diff --git a/arch/i386/lib/usercopy.c b/arch/i386/lib/usercopy.c
new file mode 100644
index 0000000..51aa2bb
--- /dev/null
+++ b/arch/i386/lib/usercopy.c
@@ -0,0 +1,636 @@
+/* 
+ * User address space access functions.
+ * The non inlined parts of asm-i386/uaccess.h are here.
+ *
+ * Copyright 1997 Andi Kleen <ak@muc.de>
+ * Copyright 1997 Linus Torvalds
+ */
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/blkdev.h>
+#include <linux/module.h>
+#include <asm/uaccess.h>
+#include <asm/mmx.h>
+
+static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned long n)
+{
+#ifdef CONFIG_X86_INTEL_USERCOPY
+	if (n >= 64 && ((a1 ^ a2) & movsl_mask.mask))
+		return 0;
+#endif
+	return 1;
+}
+#define movsl_is_ok(a1,a2,n) \
+	__movsl_is_ok((unsigned long)(a1),(unsigned long)(a2),(n))
+
+/*
+ * Copy a null terminated string from userspace.
+ */
+
+#define __do_strncpy_from_user(dst,src,count,res)			   \
+do {									   \
+	int __d0, __d1, __d2;						   \
+	might_sleep();							   \
+	__asm__ __volatile__(						   \
+		"	testl %1,%1\n"					   \
+		"	jz 2f\n"					   \
+		"0:	lodsb\n"					   \
+		"	stosb\n"					   \
+		"	testb %%al,%%al\n"				   \
+		"	jz 1f\n"					   \
+		"	decl %1\n"					   \
+		"	jnz 0b\n"					   \
+		"1:	subl %1,%0\n"					   \
+		"2:\n"							   \
+		".section .fixup,\"ax\"\n"				   \
+		"3:	movl %5,%0\n"					   \
+		"	jmp 2b\n"					   \
+		".previous\n"						   \
+		".section __ex_table,\"a\"\n"				   \
+		"	.align 4\n"					   \
+		"	.long 0b,3b\n"					   \
+		".previous"						   \
+		: "=d"(res), "=c"(count), "=&a" (__d0), "=&S" (__d1),	   \
+		  "=&D" (__d2)						   \
+		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
+		: "memory");						   \
+} while (0)
+
+/**
+ * __strncpy_from_user: - Copy a NUL terminated string from userspace, with less checking.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @src:   Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ * 
+ * Copies a NUL-terminated string from userspace to kernel space.
+ * Caller must check the specified block with access_ok() before calling
+ * this function.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+long
+__strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	long res;
+	__do_strncpy_from_user(dst, src, count, res);
+	return res;
+}
+
+/**
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @src:   Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ * 
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	long res = -EFAULT;
+	if (access_ok(VERIFY_READ, src, 1))
+		__do_strncpy_from_user(dst, src, count, res);
+	return res;
+}
+
+
+/*
+ * Zero Userspace
+ */
+
+#define __do_clear_user(addr,size)					\
+do {									\
+	int __d0;							\
+	might_sleep();							\
+  	__asm__ __volatile__(						\
+		"0:	rep; stosl\n"					\
+		"	movl %2,%0\n"					\
+		"1:	rep; stosb\n"					\
+		"2:\n"							\
+		".section .fixup,\"ax\"\n"				\
+		"3:	lea 0(%2,%0,4),%0\n"				\
+		"	jmp 2b\n"					\
+		".previous\n"						\
+		".section __ex_table,\"a\"\n"				\
+		"	.align 4\n"					\
+		"	.long 0b,3b\n"					\
+		"	.long 1b,2b\n"					\
+		".previous"						\
+		: "=&c"(size), "=&D" (__d0)				\
+		: "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0));	\
+} while (0)
+
+/**
+ * clear_user: - Zero a block of memory in user space.
+ * @to:   Destination address, in user space.
+ * @n:    Number of bytes to zero.
+ *
+ * Zero a block of memory in user space.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+unsigned long
+clear_user(void __user *to, unsigned long n)
+{
+	might_sleep();
+	if (access_ok(VERIFY_WRITE, to, n))
+		__do_clear_user(to, n);
+	return n;
+}
+
+/**
+ * __clear_user: - Zero a block of memory in user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @n:    Number of bytes to zero.
+ *
+ * Zero a block of memory in user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+unsigned long
+__clear_user(void __user *to, unsigned long n)
+{
+	__do_clear_user(to, n);
+	return n;
+}
+
+/**
+ * strlen_user: - Get the size of a string in user space.
+ * @s: The string to measure.
+ * @n: The maximum valid length
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * On exception, returns 0.
+ * If the string is too long, returns a value greater than @n.
+ */
+long strnlen_user(const char __user *s, long n)
+{
+	unsigned long mask = -__addr_ok(s);
+	unsigned long res, tmp;
+
+	might_sleep();
+
+	__asm__ __volatile__(
+		"	testl %0, %0\n"
+		"	jz 3f\n"
+		"	andl %0,%%ecx\n"
+		"0:	repne; scasb\n"
+		"	setne %%al\n"
+		"	subl %%ecx,%0\n"
+		"	addl %0,%%eax\n"
+		"1:\n"
+		".section .fixup,\"ax\"\n"
+		"2:	xorl %%eax,%%eax\n"
+		"	jmp 1b\n"
+		"3:	movb $1,%%al\n"
+		"	jmp 1b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4\n"
+		"	.long 0b,2b\n"
+		".previous"
+		:"=r" (n), "=D" (s), "=a" (res), "=c" (tmp)
+		:"0" (n), "1" (s), "2" (0), "3" (mask)
+		:"cc");
+	return res & mask;
+}
+
+#ifdef CONFIG_X86_INTEL_USERCOPY
+static unsigned long
+__copy_user_intel(void __user *to, const void *from, unsigned long size)
+{
+	int d0, d1;
+	__asm__ __volatile__(
+		       "       .align 2,0x90\n"
+		       "1:     movl 32(%4), %%eax\n"
+		       "       cmpl $67, %0\n"
+		       "       jbe 3f\n"
+		       "2:     movl 64(%4), %%eax\n"
+		       "       .align 2,0x90\n"
+		       "3:     movl 0(%4), %%eax\n"
+		       "4:     movl 4(%4), %%edx\n"
+		       "5:     movl %%eax, 0(%3)\n"
+		       "6:     movl %%edx, 4(%3)\n"
+		       "7:     movl 8(%4), %%eax\n"
+		       "8:     movl 12(%4),%%edx\n"
+		       "9:     movl %%eax, 8(%3)\n"
+		       "10:    movl %%edx, 12(%3)\n"
+		       "11:    movl 16(%4), %%eax\n"
+		       "12:    movl 20(%4), %%edx\n"
+		       "13:    movl %%eax, 16(%3)\n"
+		       "14:    movl %%edx, 20(%3)\n"
+		       "15:    movl 24(%4), %%eax\n"
+		       "16:    movl 28(%4), %%edx\n"
+		       "17:    movl %%eax, 24(%3)\n"
+		       "18:    movl %%edx, 28(%3)\n"
+		       "19:    movl 32(%4), %%eax\n"
+		       "20:    movl 36(%4), %%edx\n"
+		       "21:    movl %%eax, 32(%3)\n"
+		       "22:    movl %%edx, 36(%3)\n"
+		       "23:    movl 40(%4), %%eax\n"
+		       "24:    movl 44(%4), %%edx\n"
+		       "25:    movl %%eax, 40(%3)\n"
+		       "26:    movl %%edx, 44(%3)\n"
+		       "27:    movl 48(%4), %%eax\n"
+		       "28:    movl 52(%4), %%edx\n"
+		       "29:    movl %%eax, 48(%3)\n"
+		       "30:    movl %%edx, 52(%3)\n"
+		       "31:    movl 56(%4), %%eax\n"
+		       "32:    movl 60(%4), %%edx\n"
+		       "33:    movl %%eax, 56(%3)\n"
+		       "34:    movl %%edx, 60(%3)\n"
+		       "       addl $-64, %0\n"
+		       "       addl $64, %4\n"
+		       "       addl $64, %3\n"
+		       "       cmpl $63, %0\n"
+		       "       ja  1b\n"
+		       "35:    movl  %0, %%eax\n"
+		       "       shrl  $2, %0\n"
+		       "       andl  $3, %%eax\n"
+		       "       cld\n"
+		       "99:    rep; movsl\n"
+		       "36:    movl %%eax, %0\n"
+		       "37:    rep; movsb\n"
+		       "100:\n"
+		       ".section .fixup,\"ax\"\n"
+		       "101:   lea 0(%%eax,%0,4),%0\n"
+		       "       jmp 100b\n"
+		       ".previous\n"
+		       ".section __ex_table,\"a\"\n"
+		       "       .align 4\n"
+		       "       .long 1b,100b\n"
+		       "       .long 2b,100b\n"
+		       "       .long 3b,100b\n"
+		       "       .long 4b,100b\n"
+		       "       .long 5b,100b\n"
+		       "       .long 6b,100b\n"
+		       "       .long 7b,100b\n"
+		       "       .long 8b,100b\n"
+		       "       .long 9b,100b\n"
+		       "       .long 10b,100b\n"
+		       "       .long 11b,100b\n"
+		       "       .long 12b,100b\n"
+		       "       .long 13b,100b\n"
+		       "       .long 14b,100b\n"
+		       "       .long 15b,100b\n"
+		       "       .long 16b,100b\n"
+		       "       .long 17b,100b\n"
+		       "       .long 18b,100b\n"
+		       "       .long 19b,100b\n"
+		       "       .long 20b,100b\n"
+		       "       .long 21b,100b\n"
+		       "       .long 22b,100b\n"
+		       "       .long 23b,100b\n"
+		       "       .long 24b,100b\n"
+		       "       .long 25b,100b\n"
+		       "       .long 26b,100b\n"
+		       "       .long 27b,100b\n"
+		       "       .long 28b,100b\n"
+		       "       .long 29b,100b\n"
+		       "       .long 30b,100b\n"
+		       "       .long 31b,100b\n"
+		       "       .long 32b,100b\n"
+		       "       .long 33b,100b\n"
+		       "       .long 34b,100b\n"
+		       "       .long 35b,100b\n"
+		       "       .long 36b,100b\n"
+		       "       .long 37b,100b\n"
+		       "       .long 99b,101b\n"
+		       ".previous"
+		       : "=&c"(size), "=&D" (d0), "=&S" (d1)
+		       :  "1"(to), "2"(from), "0"(size)
+		       : "eax", "edx", "memory");
+	return size;
+}
+
+static unsigned long
+__copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size)
+{
+	int d0, d1;
+	__asm__ __volatile__(
+		       "        .align 2,0x90\n"
+		       "0:      movl 32(%4), %%eax\n"
+		       "        cmpl $67, %0\n"      
+		       "        jbe 2f\n"            
+		       "1:      movl 64(%4), %%eax\n"
+		       "        .align 2,0x90\n"     
+		       "2:      movl 0(%4), %%eax\n" 
+		       "21:     movl 4(%4), %%edx\n" 
+		       "        movl %%eax, 0(%3)\n" 
+		       "        movl %%edx, 4(%3)\n" 
+		       "3:      movl 8(%4), %%eax\n" 
+		       "31:     movl 12(%4),%%edx\n" 
+		       "        movl %%eax, 8(%3)\n" 
+		       "        movl %%edx, 12(%3)\n"
+		       "4:      movl 16(%4), %%eax\n"
+		       "41:     movl 20(%4), %%edx\n"
+		       "        movl %%eax, 16(%3)\n"
+		       "        movl %%edx, 20(%3)\n"
+		       "10:     movl 24(%4), %%eax\n"
+		       "51:     movl 28(%4), %%edx\n"
+		       "        movl %%eax, 24(%3)\n"
+		       "        movl %%edx, 28(%3)\n"
+		       "11:     movl 32(%4), %%eax\n"
+		       "61:     movl 36(%4), %%edx\n"
+		       "        movl %%eax, 32(%3)\n"
+		       "        movl %%edx, 36(%3)\n"
+		       "12:     movl 40(%4), %%eax\n"
+		       "71:     movl 44(%4), %%edx\n"
+		       "        movl %%eax, 40(%3)\n"
+		       "        movl %%edx, 44(%3)\n"
+		       "13:     movl 48(%4), %%eax\n"
+		       "81:     movl 52(%4), %%edx\n"
+		       "        movl %%eax, 48(%3)\n"
+		       "        movl %%edx, 52(%3)\n"
+		       "14:     movl 56(%4), %%eax\n"
+		       "91:     movl 60(%4), %%edx\n"
+		       "        movl %%eax, 56(%3)\n"
+		       "        movl %%edx, 60(%3)\n"
+		       "        addl $-64, %0\n"     
+		       "        addl $64, %4\n"      
+		       "        addl $64, %3\n"      
+		       "        cmpl $63, %0\n"      
+		       "        ja  0b\n"            
+		       "5:      movl  %0, %%eax\n"   
+		       "        shrl  $2, %0\n"      
+		       "        andl $3, %%eax\n"    
+		       "        cld\n"               
+		       "6:      rep; movsl\n"   
+		       "        movl %%eax,%0\n"
+		       "7:      rep; movsb\n"	
+		       "8:\n"			
+		       ".section .fixup,\"ax\"\n"
+		       "9:      lea 0(%%eax,%0,4),%0\n"	
+		       "16:     pushl %0\n"	
+		       "        pushl %%eax\n"	
+		       "        xorl %%eax,%%eax\n"
+		       "        rep; stosb\n"	
+		       "        popl %%eax\n"	
+		       "        popl %0\n"	
+		       "        jmp 8b\n"	
+		       ".previous\n"		
+		       ".section __ex_table,\"a\"\n"
+		       "	.align 4\n"	   
+		       "	.long 0b,16b\n"	 
+		       "	.long 1b,16b\n"
+		       "	.long 2b,16b\n"
+		       "	.long 21b,16b\n"
+		       "	.long 3b,16b\n"	
+		       "	.long 31b,16b\n"
+		       "	.long 4b,16b\n"	
+		       "	.long 41b,16b\n"
+		       "	.long 10b,16b\n"
+		       "	.long 51b,16b\n"
+		       "	.long 11b,16b\n"
+		       "	.long 61b,16b\n"
+		       "	.long 12b,16b\n"
+		       "	.long 71b,16b\n"
+		       "	.long 13b,16b\n"
+		       "	.long 81b,16b\n"
+		       "	.long 14b,16b\n"
+		       "	.long 91b,16b\n"
+		       "	.long 6b,9b\n"	
+		       "        .long 7b,16b\n" 
+		       ".previous"		
+		       : "=&c"(size), "=&D" (d0), "=&S" (d1)
+		       :  "1"(to), "2"(from), "0"(size)
+		       : "eax", "edx", "memory");
+	return size;
+}
+#else
+/*
+ * Leave these declared but undefined.  They should not be any references to
+ * them
+ */
+unsigned long
+__copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size);
+unsigned long
+__copy_user_intel(void __user *to, const void *from, unsigned long size);
+#endif /* CONFIG_X86_INTEL_USERCOPY */
+
+/* Generic arbitrary sized copy.  */
+#define __copy_user(to,from,size)					\
+do {									\
+	int __d0, __d1, __d2;						\
+	__asm__ __volatile__(						\
+		"	cmp  $7,%0\n"					\
+		"	jbe  1f\n"					\
+		"	movl %1,%0\n"					\
+		"	negl %0\n"					\
+		"	andl $7,%0\n"					\
+		"	subl %0,%3\n"					\
+		"4:	rep; movsb\n"					\
+		"	movl %3,%0\n"					\
+		"	shrl $2,%0\n"					\
+		"	andl $3,%3\n"					\
+		"	.align 2,0x90\n"				\
+		"0:	rep; movsl\n"					\
+		"	movl %3,%0\n"					\
+		"1:	rep; movsb\n"					\
+		"2:\n"							\
+		".section .fixup,\"ax\"\n"				\
+		"5:	addl %3,%0\n"					\
+		"	jmp 2b\n"					\
+		"3:	lea 0(%3,%0,4),%0\n"				\
+		"	jmp 2b\n"					\
+		".previous\n"						\
+		".section __ex_table,\"a\"\n"				\
+		"	.align 4\n"					\
+		"	.long 4b,5b\n"					\
+		"	.long 0b,3b\n"					\
+		"	.long 1b,2b\n"					\
+		".previous"						\
+		: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2)	\
+		: "3"(size), "0"(size), "1"(to), "2"(from)		\
+		: "memory");						\
+} while (0)
+
+#define __copy_user_zeroing(to,from,size)				\
+do {									\
+	int __d0, __d1, __d2;						\
+	__asm__ __volatile__(						\
+		"	cmp  $7,%0\n"					\
+		"	jbe  1f\n"					\
+		"	movl %1,%0\n"					\
+		"	negl %0\n"					\
+		"	andl $7,%0\n"					\
+		"	subl %0,%3\n"					\
+		"4:	rep; movsb\n"					\
+		"	movl %3,%0\n"					\
+		"	shrl $2,%0\n"					\
+		"	andl $3,%3\n"					\
+		"	.align 2,0x90\n"				\
+		"0:	rep; movsl\n"					\
+		"	movl %3,%0\n"					\
+		"1:	rep; movsb\n"					\
+		"2:\n"							\
+		".section .fixup,\"ax\"\n"				\
+		"5:	addl %3,%0\n"					\
+		"	jmp 6f\n"					\
+		"3:	lea 0(%3,%0,4),%0\n"				\
+		"6:	pushl %0\n"					\
+		"	pushl %%eax\n"					\
+		"	xorl %%eax,%%eax\n"				\
+		"	rep; stosb\n"					\
+		"	popl %%eax\n"					\
+		"	popl %0\n"					\
+		"	jmp 2b\n"					\
+		".previous\n"						\
+		".section __ex_table,\"a\"\n"				\
+		"	.align 4\n"					\
+		"	.long 4b,5b\n"					\
+		"	.long 0b,3b\n"					\
+		"	.long 1b,6b\n"					\
+		".previous"						\
+		: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2)	\
+		: "3"(size), "0"(size), "1"(to), "2"(from)		\
+		: "memory");						\
+} while (0)
+
+
+unsigned long __copy_to_user_ll(void __user *to, const void *from, unsigned long n)
+{
+	BUG_ON((long) n < 0);
+#ifndef CONFIG_X86_WP_WORKS_OK
+	if (unlikely(boot_cpu_data.wp_works_ok == 0) &&
+			((unsigned long )to) < TASK_SIZE) {
+		/* 
+		 * CPU does not honor the WP bit when writing
+		 * from supervisory mode, and due to preemption or SMP,
+		 * the page tables can change at any time.
+		 * Do it manually.	Manfred <manfred@colorfullife.com>
+		 */
+		while (n) {
+		      	unsigned long offset = ((unsigned long)to)%PAGE_SIZE;
+			unsigned long len = PAGE_SIZE - offset;
+			int retval;
+			struct page *pg;
+			void *maddr;
+			
+			if (len > n)
+				len = n;
+
+survive:
+			down_read(&current->mm->mmap_sem);
+			retval = get_user_pages(current, current->mm,
+					(unsigned long )to, 1, 1, 0, &pg, NULL);
+
+			if (retval == -ENOMEM && current->pid == 1) {
+				up_read(&current->mm->mmap_sem);
+				blk_congestion_wait(WRITE, HZ/50);
+				goto survive;
+			}
+
+			if (retval != 1) {
+				up_read(&current->mm->mmap_sem);
+		       		break;
+		       	}
+
+			maddr = kmap_atomic(pg, KM_USER0);
+			memcpy(maddr + offset, from, len);
+			kunmap_atomic(maddr, KM_USER0);
+			set_page_dirty_lock(pg);
+			put_page(pg);
+			up_read(&current->mm->mmap_sem);
+
+			from += len;
+			to += len;
+			n -= len;
+		}
+		return n;
+	}
+#endif
+	if (movsl_is_ok(to, from, n))
+		__copy_user(to, from, n);
+	else
+		n = __copy_user_intel(to, from, n);
+	return n;
+}
+
+unsigned long
+__copy_from_user_ll(void *to, const void __user *from, unsigned long n)
+{
+	BUG_ON((long)n < 0);
+	if (movsl_is_ok(to, from, n))
+		__copy_user_zeroing(to, from, n);
+	else
+		n = __copy_user_zeroing_intel(to, from, n);
+	return n;
+}
+
+/**
+ * copy_to_user: - Copy a block of data into user space.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Copy data from kernel space to user space.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ */
+unsigned long
+copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	might_sleep();
+	BUG_ON((long) n < 0);
+	if (access_ok(VERIFY_WRITE, to, n))
+		n = __copy_to_user(to, from, n);
+	return n;
+}
+EXPORT_SYMBOL(copy_to_user);
+
+/**
+ * copy_from_user: - Copy a block of data from user space.
+ * @to:   Destination address, in kernel space.
+ * @from: Source address, in user space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Copy data from user space to kernel space.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * If some data could not be copied, this function will pad the copied
+ * data to the requested size using zero bytes.
+ */
+unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	might_sleep();
+	BUG_ON((long) n < 0);
+	if (access_ok(VERIFY_READ, from, n))
+		n = __copy_from_user(to, from, n);
+	else
+		memset(to, 0, n);
+	return n;
+}
+EXPORT_SYMBOL(copy_from_user);