Merge branch 'master'

17 files changed, 3531 insertions, 0 deletions

diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
new file mode 100644
index 000000000000..34f5c2e074c9
--- /dev/null
+++ b/arch/powerpc/lib/Makefile
@@ -0,0 +1,20 @@
+#
+# Makefile for ppc-specific library files..
+#
+
+ifeq ($(CONFIG_PPC_MERGE),y)
+obj-y			:= string.o strcase.o
+obj-$(CONFIG_PPC32)	+= div64.o copy_32.o checksum_32.o
+endif
+
+obj-y			+= bitops.o
+obj-$(CONFIG_PPC64)	+= checksum_64.o copypage_64.o copyuser_64.o \
+			   memcpy_64.o usercopy_64.o mem_64.o string.o \
+			   strcase.o
+obj-$(CONFIG_PPC_ISERIES) += e2a.o
+obj-$(CONFIG_XMON)	+= sstep.o
+
+ifeq ($(CONFIG_PPC64),y)
+obj-$(CONFIG_SMP)	+= locks.o
+obj-$(CONFIG_DEBUG_KERNEL) += sstep.o
+endif
diff --git a/arch/powerpc/lib/bitops.c b/arch/powerpc/lib/bitops.c
new file mode 100644
index 000000000000..b67ce3004ebf
--- /dev/null
+++ b/arch/powerpc/lib/bitops.c
@@ -0,0 +1,150 @@
+#include <linux/types.h>
+#include <linux/module.h>
+#include <asm/byteorder.h>
+#include <asm/bitops.h>
+
+/**
+ * find_next_bit - find the next 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
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+			    unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp &= (~0UL << offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if ((tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
+
+found_first:
+	tmp &= (~0UL >> (64 - size));
+	if (tmp == 0UL)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + __ffs(tmp);
+}
+EXPORT_SYMBOL(find_next_bit);
+
+/*
+ * This implementation of find_{first,next}_zero_bit was stolen from
+ * Linus' asm-alpha/bitops.h.
+ */
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+				 unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp |= ~0UL >> (BITS_PER_LONG - offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (~tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if (~(tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
+
+found_first:
+	tmp |= ~0UL << size;
+	if (tmp == ~0UL)	/* Are any bits zero? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + ffz(tmp);
+}
+EXPORT_SYMBOL(find_next_zero_bit);
+
+static inline unsigned int ext2_ilog2(unsigned int x)
+{
+	int lz;
+
+	asm("cntlzw %0,%1": "=r"(lz):"r"(x));
+	return 31 - lz;
+}
+
+static inline unsigned int ext2_ffz(unsigned int x)
+{
+	u32 rc;
+	if ((x = ~x) == 0)
+		return 32;
+	rc = ext2_ilog2(x & -x);
+	return rc;
+}
+
+unsigned long find_next_zero_le_bit(const unsigned long *addr,
+				    unsigned long size, unsigned long offset)
+{
+	const unsigned int *p = ((const unsigned int *)addr) + (offset >> 5);
+	unsigned int result = offset & ~31;
+	unsigned int tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset &= 31;
+	if (offset) {
+		tmp = cpu_to_le32p(p++);
+		tmp |= ~0U >> (32 - offset);	/* bug or feature ? */
+		if (size < 32)
+			goto found_first;
+		if (tmp != ~0)
+			goto found_middle;
+		size -= 32;
+		result += 32;
+	}
+	while (size >= 32) {
+		if ((tmp = cpu_to_le32p(p++)) != ~0)
+			goto found_middle;
+		result += 32;
+		size -= 32;
+	}
+	if (!size)
+		return result;
+	tmp = cpu_to_le32p(p);
+found_first:
+	tmp |= ~0 << size;
+	if (tmp == ~0)		/* Are any bits zero? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + ext2_ffz(tmp);
+}
+EXPORT_SYMBOL(find_next_zero_le_bit);
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
new file mode 100644
index 000000000000..7874e8a80455
--- /dev/null
+++ b/arch/powerpc/lib/checksum_32.S
@@ -0,0 +1,225 @@
+/*
+ * This file contains assembly-language implementations
+ * of IP-style 1's complement checksum routines.
+ *	
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  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.
+ *
+ * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au).
+ */
+
+#include <linux/sys.h>
+#include <asm/processor.h>
+#include <asm/errno.h>
+#include <asm/ppc_asm.h>
+
+	.text
+
+/*
+ * ip_fast_csum(buf, len) -- Optimized for IP header
+ * len is in words and is always >= 5.
+ */
+_GLOBAL(ip_fast_csum)
+	lwz	r0,0(r3)
+	lwzu	r5,4(r3)
+	addic.	r4,r4,-2
+	addc	r0,r0,r5
+	mtctr	r4
+	blelr-
+1:	lwzu	r4,4(r3)
+	adde	r0,r0,r4
+	bdnz	1b
+	addze	r0,r0		/* add in final carry */
+	rlwinm	r3,r0,16,0,31	/* fold two halves together */
+	add	r3,r0,r3
+	not	r3,r3
+	srwi	r3,r3,16
+	blr
+
+/*
+ * Compute checksum of TCP or UDP pseudo-header:
+ *   csum_tcpudp_magic(saddr, daddr, len, proto, sum)
+ */	
+_GLOBAL(csum_tcpudp_magic)
+	rlwimi	r5,r6,16,0,15	/* put proto in upper half of len */
+	addc	r0,r3,r4	/* add 4 32-bit words together */
+	adde	r0,r0,r5
+	adde	r0,r0,r7
+	addze	r0,r0		/* add in final carry */
+	rlwinm	r3,r0,16,0,31	/* fold two halves together */
+	add	r3,r0,r3
+	not	r3,r3
+	srwi	r3,r3,16
+	blr
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * csum_partial(buff, len, sum)
+ */
+_GLOBAL(csum_partial)
+	addic	r0,r5,0
+	subi	r3,r3,4
+	srwi.	r6,r4,2
+	beq	3f		/* if we're doing < 4 bytes */
+	andi.	r5,r3,2		/* Align buffer to longword boundary */
+	beq+	1f
+	lhz	r5,4(r3)	/* do 2 bytes to get aligned */
+	addi	r3,r3,2
+	subi	r4,r4,2
+	addc	r0,r0,r5
+	srwi.	r6,r4,2		/* # words to do */
+	beq	3f
+1:	mtctr	r6
+2:	lwzu	r5,4(r3)	/* the bdnz has zero overhead, so it should */
+	adde	r0,r0,r5	/* be unnecessary to unroll this loop */
+	bdnz	2b
+	andi.	r4,r4,3
+3:	cmpwi	0,r4,2
+	blt+	4f
+	lhz	r5,4(r3)
+	addi	r3,r3,2
+	subi	r4,r4,2
+	adde	r0,r0,r5
+4:	cmpwi	0,r4,1
+	bne+	5f
+	lbz	r5,4(r3)
+	slwi	r5,r5,8		/* Upper byte of word */
+	adde	r0,r0,r5
+5:	addze	r3,r0		/* add in final carry */
+	blr
+
+/*
+ * Computes the checksum of a memory block at src, length len,
+ * and adds in "sum" (32-bit), while copying the block to dst.
+ * If an access exception occurs on src or dst, it stores -EFAULT
+ * to *src_err or *dst_err respectively, and (for an error on
+ * src) zeroes the rest of dst.
+ *
+ * csum_partial_copy_generic(src, dst, len, sum, src_err, dst_err)
+ */
+_GLOBAL(csum_partial_copy_generic)
+	addic	r0,r6,0
+	subi	r3,r3,4
+	subi	r4,r4,4
+	srwi.	r6,r5,2
+	beq	3f		/* if we're doing < 4 bytes */
+	andi.	r9,r4,2		/* Align dst to longword boundary */
+	beq+	1f
+81:	lhz	r6,4(r3)	/* do 2 bytes to get aligned */
+	addi	r3,r3,2
+	subi	r5,r5,2
+91:	sth	r6,4(r4)
+	addi	r4,r4,2
+	addc	r0,r0,r6
+	srwi.	r6,r5,2		/* # words to do */
+	beq	3f
+1:	srwi.	r6,r5,4		/* # groups of 4 words to do */
+	beq	10f
+	mtctr	r6
+71:	lwz	r6,4(r3)
+72:	lwz	r9,8(r3)
+73:	lwz	r10,12(r3)
+74:	lwzu	r11,16(r3)
+	adde	r0,r0,r6
+75:	stw	r6,4(r4)
+	adde	r0,r0,r9
+76:	stw	r9,8(r4)
+	adde	r0,r0,r10
+77:	stw	r10,12(r4)
+	adde	r0,r0,r11
+78:	stwu	r11,16(r4)
+	bdnz	71b
+10:	rlwinm.	r6,r5,30,30,31	/* # words left to do */
+	beq	13f
+	mtctr	r6
+82:	lwzu	r9,4(r3)
+92:	stwu	r9,4(r4)
+	adde	r0,r0,r9
+	bdnz	82b
+13:	andi.	r5,r5,3
+3:	cmpwi	0,r5,2
+	blt+	4f
+83:	lhz	r6,4(r3)
+	addi	r3,r3,2
+	subi	r5,r5,2
+93:	sth	r6,4(r4)
+	addi	r4,r4,2
+	adde	r0,r0,r6
+4:	cmpwi	0,r5,1
+	bne+	5f
+84:	lbz	r6,4(r3)
+94:	stb	r6,4(r4)
+	slwi	r6,r6,8		/* Upper byte of word */
+	adde	r0,r0,r6
+5:	addze	r3,r0		/* add in final carry */
+	blr
+
+/* These shouldn't go in the fixup section, since that would
+   cause the ex_table addresses to get out of order. */
+
+src_error_4:
+	mfctr	r6		/* update # bytes remaining from ctr */
+	rlwimi	r5,r6,4,0,27
+	b	79f
+src_error_1:
+	li	r6,0
+	subi	r5,r5,2
+95:	sth	r6,4(r4)
+	addi	r4,r4,2
+79:	srwi.	r6,r5,2
+	beq	3f
+	mtctr	r6
+src_error_2:
+	li	r6,0
+96:	stwu	r6,4(r4)
+	bdnz	96b
+3:	andi.	r5,r5,3
+	beq	src_error
+src_error_3:
+	li	r6,0
+	mtctr	r5
+	addi	r4,r4,3
+97:	stbu	r6,1(r4)
+	bdnz	97b
+src_error:
+	cmpwi	0,r7,0
+	beq	1f
+	li	r6,-EFAULT
+	stw	r6,0(r7)
+1:	addze	r3,r0
+	blr
+
+dst_error:
+	cmpwi	0,r8,0
+	beq	1f
+	li	r6,-EFAULT
+	stw	r6,0(r8)
+1:	addze	r3,r0
+	blr
+
+.section __ex_table,"a"
+	.long	81b,src_error_1
+	.long	91b,dst_error
+	.long	71b,src_error_4
+	.long	72b,src_error_4
+	.long	73b,src_error_4
+	.long	74b,src_error_4
+	.long	75b,dst_error
+	.long	76b,dst_error
+	.long	77b,dst_error
+	.long	78b,dst_error
+	.long	82b,src_error_2
+	.long	92b,dst_error
+	.long	83b,src_error_3
+	.long	93b,dst_error
+	.long	84b,src_error_3
+	.long	94b,dst_error
+	.long	95b,dst_error
+	.long	96b,dst_error
+	.long	97b,dst_error
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
new file mode 100644
index 000000000000..ef96c6c58efc
--- /dev/null
+++ b/arch/powerpc/lib/checksum_64.S
@@ -0,0 +1,229 @@
+/*
+ * This file contains assembly-language implementations
+ * of IP-style 1's complement checksum routines.
+ *	
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  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.
+ *
+ * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au).
+ */
+
+#include <linux/sys.h>
+#include <asm/processor.h>
+#include <asm/errno.h>
+#include <asm/ppc_asm.h>
+
+/*
+ * ip_fast_csum(r3=buf, r4=len) -- Optimized for IP header
+ * len is in words and is always >= 5.
+ *
+ * In practice len == 5, but this is not guaranteed.  So this code does not
+ * attempt to use doubleword instructions.
+ */
+_GLOBAL(ip_fast_csum)
+	lwz	r0,0(r3)
+	lwzu	r5,4(r3)
+	addic.	r4,r4,-2
+	addc	r0,r0,r5
+	mtctr	r4
+	blelr-
+1:	lwzu	r4,4(r3)
+	adde	r0,r0,r4
+	bdnz	1b
+	addze	r0,r0		/* add in final carry */
+        rldicl  r4,r0,32,0      /* fold two 32-bit halves together */
+        add     r0,r0,r4
+        srdi    r0,r0,32
+	rlwinm	r3,r0,16,0,31	/* fold two halves together */
+	add	r3,r0,r3
+	not	r3,r3
+	srwi	r3,r3,16
+	blr
+
+/*
+ * Compute checksum of TCP or UDP pseudo-header:
+ *   csum_tcpudp_magic(r3=saddr, r4=daddr, r5=len, r6=proto, r7=sum)
+ * No real gain trying to do this specially for 64 bit, but
+ * the 32 bit addition may spill into the upper bits of
+ * the doubleword so we still must fold it down from 64.
+ */	
+_GLOBAL(csum_tcpudp_magic)
+	rlwimi	r5,r6,16,0,15	/* put proto in upper half of len */
+	addc	r0,r3,r4	/* add 4 32-bit words together */
+	adde	r0,r0,r5
+	adde	r0,r0,r7
+        rldicl  r4,r0,32,0      /* fold 64 bit value */
+        add     r0,r4,r0
+        srdi    r0,r0,32
+	rlwinm	r3,r0,16,0,31	/* fold two halves together */
+	add	r3,r0,r3
+	not	r3,r3
+	srwi	r3,r3,16
+	blr
+
+/*
+ * Computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit).
+ *
+ * This code assumes at least halfword alignment, though the length
+ * can be any number of bytes.  The sum is accumulated in r5.
+ *
+ * csum_partial(r3=buff, r4=len, r5=sum)
+ */
+_GLOBAL(csum_partial)
+        subi	r3,r3,8		/* we'll offset by 8 for the loads */
+        srdi.	r6,r4,3         /* divide by 8 for doubleword count */
+        addic   r5,r5,0         /* clear carry */
+        beq	3f              /* if we're doing < 8 bytes */
+        andi.	r0,r3,2         /* aligned on a word boundary already? */
+        beq+	1f
+        lhz     r6,8(r3)        /* do 2 bytes to get aligned */
+        addi    r3,r3,2
+        subi    r4,r4,2
+        addc    r5,r5,r6
+        srdi.   r6,r4,3         /* recompute number of doublewords */
+        beq     3f              /* any left? */
+1:      mtctr   r6
+2:      ldu     r6,8(r3)        /* main sum loop */
+        adde    r5,r5,r6
+        bdnz    2b
+        andi.	r4,r4,7         /* compute bytes left to sum after doublewords */
+3:	cmpwi	0,r4,4		/* is at least a full word left? */
+	blt	4f
+	lwz	r6,8(r3)	/* sum this word */
+	addi	r3,r3,4
+	subi	r4,r4,4
+	adde	r5,r5,r6
+4:	cmpwi	0,r4,2		/* is at least a halfword left? */
+        blt+	5f
+        lhz     r6,8(r3)        /* sum this halfword */
+        addi    r3,r3,2
+        subi    r4,r4,2
+        adde    r5,r5,r6
+5:	cmpwi	0,r4,1		/* is at least a byte left? */
+        bne+    6f
+        lbz     r6,8(r3)        /* sum this byte */
+        slwi    r6,r6,8         /* this byte is assumed to be the upper byte of a halfword */
+        adde    r5,r5,r6
+6:      addze	r5,r5		/* add in final carry */
+	rldicl  r4,r5,32,0      /* fold two 32-bit halves together */
+        add     r3,r4,r5
+        srdi    r3,r3,32
+        blr
+
+/*
+ * Computes the checksum of a memory block at src, length len,
+ * and adds in "sum" (32-bit), while copying the block to dst.
+ * If an access exception occurs on src or dst, it stores -EFAULT
+ * to *src_err or *dst_err respectively, and (for an error on
+ * src) zeroes the rest of dst.
+ *
+ * This code needs to be reworked to take advantage of 64 bit sum+copy.
+ * However, due to tokenring halfword alignment problems this will be very
+ * tricky.  For now we'll leave it until we instrument it somehow.
+ *
+ * csum_partial_copy_generic(r3=src, r4=dst, r5=len, r6=sum, r7=src_err, r8=dst_err)
+ */
+_GLOBAL(csum_partial_copy_generic)
+	addic	r0,r6,0
+	subi	r3,r3,4
+	subi	r4,r4,4
+	srwi.	r6,r5,2
+	beq	3f		/* if we're doing < 4 bytes */
+	andi.	r9,r4,2		/* Align dst to longword boundary */
+	beq+	1f
+81:	lhz	r6,4(r3)	/* do 2 bytes to get aligned */
+	addi	r3,r3,2
+	subi	r5,r5,2
+91:	sth	r6,4(r4)
+	addi	r4,r4,2
+	addc	r0,r0,r6
+	srwi.	r6,r5,2		/* # words to do */
+	beq	3f
+1:	mtctr	r6
+82:	lwzu	r6,4(r3)	/* the bdnz has zero overhead, so it should */
+92:	stwu	r6,4(r4)	/* be unnecessary to unroll this loop */
+	adde	r0,r0,r6
+	bdnz	82b
+	andi.	r5,r5,3
+3:	cmpwi	0,r5,2
+	blt+	4f
+83:	lhz	r6,4(r3)
+	addi	r3,r3,2
+	subi	r5,r5,2
+93:	sth	r6,4(r4)
+	addi	r4,r4,2
+	adde	r0,r0,r6
+4:	cmpwi	0,r5,1
+	bne+	5f
+84:	lbz	r6,4(r3)
+94:	stb	r6,4(r4)
+	slwi	r6,r6,8		/* Upper byte of word */
+	adde	r0,r0,r6
+5:	addze	r3,r0		/* add in final carry (unlikely with 64-bit regs) */
+        rldicl  r4,r3,32,0      /* fold 64 bit value */
+        add     r3,r4,r3
+        srdi    r3,r3,32
+	blr
+
+/* These shouldn't go in the fixup section, since that would
+   cause the ex_table addresses to get out of order. */
+
+	.globl src_error_1
+src_error_1:
+	li	r6,0
+	subi	r5,r5,2
+95:	sth	r6,4(r4)
+	addi	r4,r4,2
+	srwi.	r6,r5,2
+	beq	3f
+	mtctr	r6
+	.globl src_error_2
+src_error_2:
+	li	r6,0
+96:	stwu	r6,4(r4)
+	bdnz	96b
+3:	andi.	r5,r5,3
+	beq	src_error
+	.globl src_error_3
+src_error_3:
+	li	r6,0
+	mtctr	r5
+	addi	r4,r4,3
+97:	stbu	r6,1(r4)
+	bdnz	97b
+	.globl src_error
+src_error:
+	cmpdi	0,r7,0
+	beq	1f
+	li	r6,-EFAULT
+	stw	r6,0(r7)
+1:	addze	r3,r0
+	blr
+
+	.globl dst_error
+dst_error:
+	cmpdi	0,r8,0
+	beq	1f
+	li	r6,-EFAULT
+	stw	r6,0(r8)
+1:	addze	r3,r0
+	blr
+
+.section __ex_table,"a"
+	.align  3
+	.llong	81b,src_error_1
+	.llong	91b,dst_error
+	.llong	82b,src_error_2
+	.llong	92b,dst_error
+	.llong	83b,src_error_3
+	.llong	93b,dst_error
+	.llong	84b,src_error_3
+	.llong	94b,dst_error
+	.llong	95b,dst_error
+	.llong	96b,dst_error
+	.llong	97b,dst_error
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
new file mode 100644
index 000000000000..bee51414812e
--- /dev/null
+++ b/arch/powerpc/lib/copy_32.S
@@ -0,0 +1,543 @@
+/*
+ * Memory copy functions for 32-bit PowerPC.
+ *
+ * Copyright (C) 1996-2005 Paul Mackerras.
+ *
+ * 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/processor.h>
+#include <asm/cache.h>
+#include <asm/errno.h>
+#include <asm/ppc_asm.h>
+
+#define COPY_16_BYTES		\
+	lwz	r7,4(r4);	\
+	lwz	r8,8(r4);	\
+	lwz	r9,12(r4);	\
+	lwzu	r10,16(r4);	\
+	stw	r7,4(r6);	\
+	stw	r8,8(r6);	\
+	stw	r9,12(r6);	\
+	stwu	r10,16(r6)
+
+#define COPY_16_BYTES_WITHEX(n)	\
+8 ## n ## 0:			\
+	lwz	r7,4(r4);	\
+8 ## n ## 1:			\
+	lwz	r8,8(r4);	\
+8 ## n ## 2:			\
+	lwz	r9,12(r4);	\
+8 ## n ## 3:			\
+	lwzu	r10,16(r4);	\
+8 ## n ## 4:			\
+	stw	r7,4(r6);	\
+8 ## n ## 5:			\
+	stw	r8,8(r6);	\
+8 ## n ## 6:			\
+	stw	r9,12(r6);	\
+8 ## n ## 7:			\
+	stwu	r10,16(r6)
+
+#define COPY_16_BYTES_EXCODE(n)			\
+9 ## n ## 0:					\
+	addi	r5,r5,-(16 * n);		\
+	b	104f;				\
+9 ## n ## 1:					\
+	addi	r5,r5,-(16 * n);		\
+	b	105f;				\
+.section __ex_table,"a";			\
+	.align	2;				\
+	.long	8 ## n ## 0b,9 ## n ## 0b;	\
+	.long	8 ## n ## 1b,9 ## n ## 0b;	\
+	.long	8 ## n ## 2b,9 ## n ## 0b;	\
+	.long	8 ## n ## 3b,9 ## n ## 0b;	\
+	.long	8 ## n ## 4b,9 ## n ## 1b;	\
+	.long	8 ## n ## 5b,9 ## n ## 1b;	\
+	.long	8 ## n ## 6b,9 ## n ## 1b;	\
+	.long	8 ## n ## 7b,9 ## n ## 1b;	\
+	.text
+
+	.text
+	.stabs	"arch/powerpc/lib/",N_SO,0,0,0f
+	.stabs	"copy32.S",N_SO,0,0,0f
+0:
+
+CACHELINE_BYTES = L1_CACHE_BYTES
+LG_CACHELINE_BYTES = L1_CACHE_SHIFT
+CACHELINE_MASK = (L1_CACHE_BYTES-1)
+
+/*
+ * Use dcbz on the complete cache lines in the destination
+ * to set them to zero.  This requires that the destination
+ * area is cacheable.  -- paulus
+ */
+_GLOBAL(cacheable_memzero)
+	mr	r5,r4
+	li	r4,0
+	addi	r6,r3,-4
+	cmplwi	0,r5,4
+	blt	7f
+	stwu	r4,4(r6)
+	beqlr
+	andi.	r0,r6,3
+	add	r5,r0,r5
+	subf	r6,r0,r6
+	clrlwi	r7,r6,32-LG_CACHELINE_BYTES
+	add	r8,r7,r5
+	srwi	r9,r8,LG_CACHELINE_BYTES
+	addic.	r9,r9,-1	/* total number of complete cachelines */
+	ble	2f
+	xori	r0,r7,CACHELINE_MASK & ~3
+	srwi.	r0,r0,2
+	beq	3f
+	mtctr	r0
+4:	stwu	r4,4(r6)
+	bdnz	4b
+3:	mtctr	r9
+	li	r7,4
+#if !defined(CONFIG_8xx)
+10:	dcbz	r7,r6
+#else
+10:	stw	r4, 4(r6)
+	stw	r4, 8(r6)
+	stw	r4, 12(r6)
+	stw	r4, 16(r6)
+#if CACHE_LINE_SIZE >= 32
+	stw	r4, 20(r6)
+	stw	r4, 24(r6)
+	stw	r4, 28(r6)
+	stw	r4, 32(r6)
+#endif /* CACHE_LINE_SIZE */
+#endif
+	addi	r6,r6,CACHELINE_BYTES
+	bdnz	10b
+	clrlwi	r5,r8,32-LG_CACHELINE_BYTES
+	addi	r5,r5,4
+2:	srwi	r0,r5,2
+	mtctr	r0
+	bdz	6f
+1:	stwu	r4,4(r6)
+	bdnz	1b
+6:	andi.	r5,r5,3
+7:	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+	addi	r6,r6,3
+8:	stbu	r4,1(r6)
+	bdnz	8b
+	blr
+
+_GLOBAL(memset)
+	rlwimi	r4,r4,8,16,23
+	rlwimi	r4,r4,16,0,15
+	addi	r6,r3,-4
+	cmplwi	0,r5,4
+	blt	7f
+	stwu	r4,4(r6)
+	beqlr
+	andi.	r0,r6,3
+	add	r5,r0,r5
+	subf	r6,r0,r6
+	srwi	r0,r5,2
+	mtctr	r0
+	bdz	6f
+1:	stwu	r4,4(r6)
+	bdnz	1b
+6:	andi.	r5,r5,3
+7:	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+	addi	r6,r6,3
+8:	stbu	r4,1(r6)
+	bdnz	8b
+	blr
+
+/*
+ * This version uses dcbz on the complete cache lines in the
+ * destination area to reduce memory traffic.  This requires that
+ * the destination area is cacheable.
+ * We only use this version if the source and dest don't overlap.
+ * -- paulus.
+ */
+_GLOBAL(cacheable_memcpy)
+	add	r7,r3,r5		/* test if the src & dst overlap */
+	add	r8,r4,r5
+	cmplw	0,r4,r7
+	cmplw	1,r3,r8
+	crand	0,0,4			/* cr0.lt &= cr1.lt */
+	blt	memcpy			/* if regions overlap */
+
+	addi	r4,r4,-4
+	addi	r6,r3,-4
+	neg	r0,r3
+	andi.	r0,r0,CACHELINE_MASK	/* # bytes to start of cache line */
+	beq	58f
+
+	cmplw	0,r5,r0			/* is this more than total to do? */
+	blt	63f			/* if not much to do */
+	andi.	r8,r0,3			/* get it word-aligned first */
+	subf	r5,r0,r5
+	mtctr	r8
+	beq+	61f
+70:	lbz	r9,4(r4)		/* do some bytes */
+	stb	r9,4(r6)
+	addi	r4,r4,1
+	addi	r6,r6,1
+	bdnz	70b
+61:	srwi.	r0,r0,2
+	mtctr	r0
+	beq	58f
+72:	lwzu	r9,4(r4)		/* do some words */
+	stwu	r9,4(r6)
+	bdnz	72b
+
+58:	srwi.	r0,r5,LG_CACHELINE_BYTES /* # complete cachelines */
+	clrlwi	r5,r5,32-LG_CACHELINE_BYTES
+	li	r11,4
+	mtctr	r0
+	beq	63f
+53:
+#if !defined(CONFIG_8xx)
+	dcbz	r11,r6
+#endif
+	COPY_16_BYTES
+#if L1_CACHE_BYTES >= 32
+	COPY_16_BYTES
+#if L1_CACHE_BYTES >= 64
+	COPY_16_BYTES
+	COPY_16_BYTES
+#if L1_CACHE_BYTES >= 128
+	COPY_16_BYTES
+	COPY_16_BYTES
+	COPY_16_BYTES
+	COPY_16_BYTES
+#endif
+#endif
+#endif
+	bdnz	53b
+
+63:	srwi.	r0,r5,2
+	mtctr	r0
+	beq	64f
+30:	lwzu	r0,4(r4)
+	stwu	r0,4(r6)
+	bdnz	30b
+
+64:	andi.	r0,r5,3
+	mtctr	r0
+	beq+	65f
+40:	lbz	r0,4(r4)
+	stb	r0,4(r6)
+	addi	r4,r4,1
+	addi	r6,r6,1
+	bdnz	40b
+65:	blr
+
+_GLOBAL(memmove)
+	cmplw	0,r3,r4
+	bgt	backwards_memcpy
+	/* fall through */
+
+_GLOBAL(memcpy)
+	srwi.	r7,r5,3
+	addi	r6,r3,-4
+	addi	r4,r4,-4
+	beq	2f			/* if less than 8 bytes to do */
+	andi.	r0,r6,3			/* get dest word aligned */
+	mtctr	r7
+	bne	5f
+1:	lwz	r7,4(r4)
+	lwzu	r8,8(r4)
+	stw	r7,4(r6)
+	stwu	r8,8(r6)
+	bdnz	1b
+	andi.	r5,r5,7
+2:	cmplwi	0,r5,4
+	blt	3f
+	lwzu	r0,4(r4)
+	addi	r5,r5,-4
+	stwu	r0,4(r6)
+3:	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+	addi	r4,r4,3
+	addi	r6,r6,3
+4:	lbzu	r0,1(r4)
+	stbu	r0,1(r6)
+	bdnz	4b
+	blr
+5:	subfic	r0,r0,4
+	mtctr	r0
+6:	lbz	r7,4(r4)
+	addi	r4,r4,1
+	stb	r7,4(r6)
+	addi	r6,r6,1
+	bdnz	6b
+	subf	r5,r0,r5
+	rlwinm.	r7,r5,32-3,3,31
+	beq	2b
+	mtctr	r7
+	b	1b
+
+_GLOBAL(backwards_memcpy)
+	rlwinm.	r7,r5,32-3,3,31		/* r0 = r5 >> 3 */
+	add	r6,r3,r5
+	add	r4,r4,r5
+	beq	2f
+	andi.	r0,r6,3
+	mtctr	r7
+	bne	5f
+1:	lwz	r7,-4(r4)
+	lwzu	r8,-8(r4)
+	stw	r7,-4(r6)
+	stwu	r8,-8(r6)
+	bdnz	1b
+	andi.	r5,r5,7
+2:	cmplwi	0,r5,4
+	blt	3f
+	lwzu	r0,-4(r4)
+	subi	r5,r5,4
+	stwu	r0,-4(r6)
+3:	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+4:	lbzu	r0,-1(r4)
+	stbu	r0,-1(r6)
+	bdnz	4b
+	blr
+5:	mtctr	r0
+6:	lbzu	r7,-1(r4)
+	stbu	r7,-1(r6)
+	bdnz	6b
+	subf	r5,r0,r5
+	rlwinm.	r7,r5,32-3,3,31
+	beq	2b
+	mtctr	r7
+	b	1b
+
+_GLOBAL(__copy_tofrom_user)
+	addi	r4,r4,-4
+	addi	r6,r3,-4
+	neg	r0,r3
+	andi.	r0,r0,CACHELINE_MASK	/* # bytes to start of cache line */
+	beq	58f
+
+	cmplw	0,r5,r0			/* is this more than total to do? */
+	blt	63f			/* if not much to do */
+	andi.	r8,r0,3			/* get it word-aligned first */
+	mtctr	r8
+	beq+	61f
+70:	lbz	r9,4(r4)		/* do some bytes */
+71:	stb	r9,4(r6)
+	addi	r4,r4,1
+	addi	r6,r6,1
+	bdnz	70b
+61:	subf	r5,r0,r5
+	srwi.	r0,r0,2
+	mtctr	r0
+	beq	58f
+72:	lwzu	r9,4(r4)		/* do some words */
+73:	stwu	r9,4(r6)
+	bdnz	72b
+
+	.section __ex_table,"a"
+	.align	2
+	.long	70b,100f
+	.long	71b,101f
+	.long	72b,102f
+	.long	73b,103f
+	.text
+
+58:	srwi.	r0,r5,LG_CACHELINE_BYTES /* # complete cachelines */
+	clrlwi	r5,r5,32-LG_CACHELINE_BYTES
+	li	r11,4
+	beq	63f
+
+#ifdef CONFIG_8xx
+	/* Don't use prefetch on 8xx */
+	mtctr	r0
+	li	r0,0
+53:	COPY_16_BYTES_WITHEX(0)
+	bdnz	53b
+
+#else /* not CONFIG_8xx */
+	/* Here we decide how far ahead to prefetch the source */
+	li	r3,4
+	cmpwi	r0,1
+	li	r7,0
+	ble	114f
+	li	r7,1
+#if MAX_COPY_PREFETCH > 1
+	/* Heuristically, for large transfers we prefetch
+	   MAX_COPY_PREFETCH cachelines ahead.  For small transfers
+	   we prefetch 1 cacheline ahead. */
+	cmpwi	r0,MAX_COPY_PREFETCH
+	ble	112f
+	li	r7,MAX_COPY_PREFETCH
+112:	mtctr	r7
+111:	dcbt	r3,r4
+	addi	r3,r3,CACHELINE_BYTES
+	bdnz	111b
+#else
+	dcbt	r3,r4
+	addi	r3,r3,CACHELINE_BYTES
+#endif /* MAX_COPY_PREFETCH > 1 */
+
+114:	subf	r8,r7,r0
+	mr	r0,r7
+	mtctr	r8
+
+53:	dcbt	r3,r4
+54:	dcbz	r11,r6
+	.section __ex_table,"a"
+	.align	2
+	.long	54b,105f
+	.text
+/* the main body of the cacheline loop */
+	COPY_16_BYTES_WITHEX(0)
+#if L1_CACHE_BYTES >= 32
+	COPY_16_BYTES_WITHEX(1)
+#if L1_CACHE_BYTES >= 64
+	COPY_16_BYTES_WITHEX(2)
+	COPY_16_BYTES_WITHEX(3)
+#if L1_CACHE_BYTES >= 128
+	COPY_16_BYTES_WITHEX(4)
+	COPY_16_BYTES_WITHEX(5)
+	COPY_16_BYTES_WITHEX(6)
+	COPY_16_BYTES_WITHEX(7)
+#endif
+#endif
+#endif
+	bdnz	53b
+	cmpwi	r0,0
+	li	r3,4
+	li	r7,0
+	bne	114b
+#endif /* CONFIG_8xx */
+
+63:	srwi.	r0,r5,2
+	mtctr	r0
+	beq	64f
+30:	lwzu	r0,4(r4)
+31:	stwu	r0,4(r6)
+	bdnz	30b
+
+64:	andi.	r0,r5,3
+	mtctr	r0
+	beq+	65f
+40:	lbz	r0,4(r4)
+41:	stb	r0,4(r6)
+	addi	r4,r4,1
+	addi	r6,r6,1
+	bdnz	40b
+65:	li	r3,0
+	blr
+
+/* read fault, initial single-byte copy */
+100:	li	r9,0
+	b	90f
+/* write fault, initial single-byte copy */
+101:	li	r9,1
+90:	subf	r5,r8,r5
+	li	r3,0
+	b	99f
+/* read fault, initial word copy */
+102:	li	r9,0
+	b	91f
+/* write fault, initial word copy */
+103:	li	r9,1
+91:	li	r3,2
+	b	99f
+
+/*
+ * this stuff handles faults in the cacheline loop and branches to either
+ * 104f (if in read part) or 105f (if in write part), after updating r5
+ */
+	COPY_16_BYTES_EXCODE(0)
+#if L1_CACHE_BYTES >= 32
+	COPY_16_BYTES_EXCODE(1)
+#if L1_CACHE_BYTES >= 64
+	COPY_16_BYTES_EXCODE(2)
+	COPY_16_BYTES_EXCODE(3)
+#if L1_CACHE_BYTES >= 128
+	COPY_16_BYTES_EXCODE(4)
+	COPY_16_BYTES_EXCODE(5)
+	COPY_16_BYTES_EXCODE(6)
+	COPY_16_BYTES_EXCODE(7)
+#endif
+#endif
+#endif
+
+/* read fault in cacheline loop */
+104:	li	r9,0
+	b	92f
+/* fault on dcbz (effectively a write fault) */
+/* or write fault in cacheline loop */
+105:	li	r9,1
+92:	li	r3,LG_CACHELINE_BYTES
+	mfctr	r8
+	add	r0,r0,r8
+	b	106f
+/* read fault in final word loop */
+108:	li	r9,0
+	b	93f
+/* write fault in final word loop */
+109:	li	r9,1
+93:	andi.	r5,r5,3
+	li	r3,2
+	b	99f
+/* read fault in final byte loop */
+110:	li	r9,0
+	b	94f
+/* write fault in final byte loop */
+111:	li	r9,1
+94:	li	r5,0
+	li	r3,0
+/*
+ * At this stage the number of bytes not copied is
+ * r5 + (ctr << r3), and r9 is 0 for read or 1 for write.
+ */
+99:	mfctr	r0
+106:	slw	r3,r0,r3
+	add.	r3,r3,r5
+	beq	120f			/* shouldn't happen */
+	cmpwi	0,r9,0
+	bne	120f
+/* for a read fault, first try to continue the copy one byte at a time */
+	mtctr	r3
+130:	lbz	r0,4(r4)
+131:	stb	r0,4(r6)
+	addi	r4,r4,1
+	addi	r6,r6,1
+	bdnz	130b
+/* then clear out the destination: r3 bytes starting at 4(r6) */
+132:	mfctr	r3
+	srwi.	r0,r3,2
+	li	r9,0
+	mtctr	r0
+	beq	113f
+112:	stwu	r9,4(r6)
+	bdnz	112b
+113:	andi.	r0,r3,3
+	mtctr	r0
+	beq	120f
+114:	stb	r9,4(r6)
+	addi	r6,r6,1
+	bdnz	114b
+120:	blr
+
+	.section __ex_table,"a"
+	.align	2
+	.long	30b,108b
+	.long	31b,109b
+	.long	40b,110b
+	.long	41b,111b
+	.long	130b,132b
+	.long	131b,120b
+	.long	112b,120b
+	.long	114b,120b
+	.text
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
new file mode 100644
index 000000000000..733d61618bbf
--- /dev/null
+++ b/arch/powerpc/lib/copypage_64.S
@@ -0,0 +1,121 @@
+/*
+ * arch/ppc64/lib/copypage.S
+ *
+ * Copyright (C) 2002 Paul Mackerras, IBM Corp.
+ *
+ * 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 <asm/processor.h>
+#include <asm/ppc_asm.h>
+
+_GLOBAL(copy_page)
+	std	r31,-8(1)
+	std	r30,-16(1)
+	std	r29,-24(1)
+	std	r28,-32(1)
+	std	r27,-40(1)
+	std	r26,-48(1)
+	std	r25,-56(1)
+	std	r24,-64(1)
+	std	r23,-72(1)
+	std	r22,-80(1)
+	std	r21,-88(1)
+	std	r20,-96(1)
+	li	r5,4096/32 - 1
+	addi	r3,r3,-8
+	li	r12,5
+0:	addi	r5,r5,-24
+	mtctr	r12
+	ld	r22,640(4)
+	ld	r21,512(4)
+	ld	r20,384(4)
+	ld	r11,256(4)
+	ld	r9,128(4)
+	ld	r7,0(4)
+	ld	r25,648(4)
+	ld	r24,520(4)
+	ld	r23,392(4)
+	ld	r10,264(4)
+	ld	r8,136(4)
+	ldu	r6,8(4)
+	cmpwi	r5,24
+1:	std	r22,648(3)
+	std	r21,520(3)
+	std	r20,392(3)
+	std	r11,264(3)
+	std	r9,136(3)
+	std	r7,8(3)
+	ld	r28,648(4)
+	ld	r27,520(4)
+	ld	r26,392(4)
+	ld	r31,264(4)
+	ld	r30,136(4)
+	ld	r29,8(4)
+	std	r25,656(3)
+	std	r24,528(3)
+	std	r23,400(3)
+	std	r10,272(3)
+	std	r8,144(3)
+	std	r6,16(3)
+	ld	r22,656(4)
+	ld	r21,528(4)
+	ld	r20,400(4)
+	ld	r11,272(4)
+	ld	r9,144(4)
+	ld	r7,16(4)
+	std	r28,664(3)
+	std	r27,536(3)
+	std	r26,408(3)
+	std	r31,280(3)
+	std	r30,152(3)
+	stdu	r29,24(3)
+	ld	r25,664(4)
+	ld	r24,536(4)
+	ld	r23,408(4)
+	ld	r10,280(4)
+	ld	r8,152(4)
+	ldu	r6,24(4)
+	bdnz	1b
+	std	r22,648(3)
+	std	r21,520(3)
+	std	r20,392(3)
+	std	r11,264(3)
+	std	r9,136(3)
+	std	r7,8(3)
+	addi	r4,r4,640
+	addi	r3,r3,648
+	bge	0b
+	mtctr	r5
+	ld	r7,0(4)
+	ld	r8,8(4)
+	ldu	r9,16(4)
+3:	ld	r10,8(4)
+	std	r7,8(3)
+	ld	r7,16(4)
+	std	r8,16(3)
+	ld	r8,24(4)
+	std	r9,24(3)
+	ldu	r9,32(4)
+	stdu	r10,32(3)
+	bdnz	3b
+4:	ld	r10,8(4)
+	std	r7,8(3)
+	std	r8,16(3)
+	std	r9,24(3)
+	std	r10,32(3)
+9:	ld	r20,-96(1)
+	ld	r21,-88(1)
+	ld	r22,-80(1)
+	ld	r23,-72(1)
+	ld	r24,-64(1)
+	ld	r25,-56(1)
+	ld	r26,-48(1)
+	ld	r27,-40(1)
+	ld	r28,-32(1)
+	ld	r29,-24(1)
+	ld	r30,-16(1)
+	ld	r31,-8(1)
+	blr
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
new file mode 100644
index 000000000000..a0b3fbbd6fb1
--- /dev/null
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -0,0 +1,576 @@
+/*
+ * arch/ppc64/lib/copyuser.S
+ *
+ * Copyright (C) 2002 Paul Mackerras, IBM Corp.
+ *
+ * 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 <asm/processor.h>
+#include <asm/ppc_asm.h>
+
+	.align	7
+_GLOBAL(__copy_tofrom_user)
+	/* first check for a whole page copy on a page boundary */
+	cmpldi	cr1,r5,16
+	cmpdi	cr6,r5,4096
+	or	r0,r3,r4
+	neg	r6,r3		/* LS 3 bits = # bytes to 8-byte dest bdry */
+	andi.	r0,r0,4095
+	std	r3,-24(r1)
+	crand	cr0*4+2,cr0*4+2,cr6*4+2
+	std	r4,-16(r1)
+	std	r5,-8(r1)
+	dcbt	0,r4
+	beq	.Lcopy_page
+	andi.	r6,r6,7
+	mtcrf	0x01,r5
+	blt	cr1,.Lshort_copy
+	bne	.Ldst_unaligned
+.Ldst_aligned:
+	andi.	r0,r4,7
+	addi	r3,r3,-16
+	bne	.Lsrc_unaligned
+	srdi	r7,r5,4
+20:	ld	r9,0(r4)
+	addi	r4,r4,-8
+	mtctr	r7
+	andi.	r5,r5,7
+	bf	cr7*4+0,22f
+	addi	r3,r3,8
+	addi	r4,r4,8
+	mr	r8,r9
+	blt	cr1,72f
+21:	ld	r9,8(r4)
+70:	std	r8,8(r3)
+22:	ldu	r8,16(r4)
+71:	stdu	r9,16(r3)
+	bdnz	21b
+72:	std	r8,8(r3)
+	beq+	3f
+	addi	r3,r3,16
+23:	ld	r9,8(r4)
+.Ldo_tail:
+	bf	cr7*4+1,1f
+	rotldi	r9,r9,32
+73:	stw	r9,0(r3)
+	addi	r3,r3,4
+1:	bf	cr7*4+2,2f
+	rotldi	r9,r9,16
+74:	sth	r9,0(r3)
+	addi	r3,r3,2
+2:	bf	cr7*4+3,3f
+	rotldi	r9,r9,8
+75:	stb	r9,0(r3)
+3:	li	r3,0
+	blr
+
+.Lsrc_unaligned:
+	srdi	r6,r5,3
+	addi	r5,r5,-16
+	subf	r4,r0,r4
+	srdi	r7,r5,4
+	sldi	r10,r0,3
+	cmpldi	cr6,r6,3
+	andi.	r5,r5,7
+	mtctr	r7
+	subfic	r11,r10,64
+	add	r5,r5,r0
+	bt	cr7*4+0,28f
+
+24:	ld	r9,0(r4)	/* 3+2n loads, 2+2n stores */
+25:	ld	r0,8(r4)
+	sld	r6,r9,r10
+26:	ldu	r9,16(r4)
+	srd	r7,r0,r11
+	sld	r8,r0,r10
+	or	r7,r7,r6
+	blt	cr6,79f
+27:	ld	r0,8(r4)
+	b	2f
+
+28:	ld	r0,0(r4)	/* 4+2n loads, 3+2n stores */
+29:	ldu	r9,8(r4)
+	sld	r8,r0,r10
+	addi	r3,r3,-8
+	blt	cr6,5f
+30:	ld	r0,8(r4)
+	srd	r12,r9,r11
+	sld	r6,r9,r10
+31:	ldu	r9,16(r4)
+	or	r12,r8,r12
+	srd	r7,r0,r11
+	sld	r8,r0,r10
+	addi	r3,r3,16
+	beq	cr6,78f
+
+1:	or	r7,r7,r6
+32:	ld	r0,8(r4)
+76:	std	r12,8(r3)
+2:	srd	r12,r9,r11
+	sld	r6,r9,r10
+33:	ldu	r9,16(r4)
+	or	r12,r8,r12
+77:	stdu	r7,16(r3)
+	srd	r7,r0,r11
+	sld	r8,r0,r10
+	bdnz	1b
+
+78:	std	r12,8(r3)
+	or	r7,r7,r6
+79:	std	r7,16(r3)
+5:	srd	r12,r9,r11
+	or	r12,r8,r12
+80:	std	r12,24(r3)
+	bne	6f
+	li	r3,0
+	blr
+6:	cmpwi	cr1,r5,8
+	addi	r3,r3,32
+	sld	r9,r9,r10
+	ble	cr1,.Ldo_tail
+34:	ld	r0,8(r4)
+	srd	r7,r0,r11
+	or	r9,r7,r9
+	b	.Ldo_tail
+
+.Ldst_unaligned:
+	mtcrf	0x01,r6		/* put #bytes to 8B bdry into cr7 */
+	subf	r5,r6,r5
+	li	r7,0
+	cmpldi	r1,r5,16
+	bf	cr7*4+3,1f
+35:	lbz	r0,0(r4)
+81:	stb	r0,0(r3)
+	addi	r7,r7,1
+1:	bf	cr7*4+2,2f
+36:	lhzx	r0,r7,r4
+82:	sthx	r0,r7,r3
+	addi	r7,r7,2
+2:	bf	cr7*4+1,3f
+37:	lwzx	r0,r7,r4
+83:	stwx	r0,r7,r3
+3:	mtcrf	0x01,r5
+	add	r4,r6,r4
+	add	r3,r6,r3
+	b	.Ldst_aligned
+
+.Lshort_copy:
+	bf	cr7*4+0,1f
+38:	lwz	r0,0(r4)
+39:	lwz	r9,4(r4)
+	addi	r4,r4,8
+84:	stw	r0,0(r3)
+85:	stw	r9,4(r3)
+	addi	r3,r3,8
+1:	bf	cr7*4+1,2f
+40:	lwz	r0,0(r4)
+	addi	r4,r4,4
+86:	stw	r0,0(r3)
+	addi	r3,r3,4
+2:	bf	cr7*4+2,3f
+41:	lhz	r0,0(r4)
+	addi	r4,r4,2
+87:	sth	r0,0(r3)
+	addi	r3,r3,2
+3:	bf	cr7*4+3,4f
+42:	lbz	r0,0(r4)
+88:	stb	r0,0(r3)
+4:	li	r3,0
+	blr
+
+/*
+ * exception handlers follow
+ * we have to return the number of bytes not copied
+ * for an exception on a load, we set the rest of the destination to 0
+ */
+
+136:
+137:
+	add	r3,r3,r7
+	b	1f
+130:
+131:
+	addi	r3,r3,8
+120:
+122:
+124:
+125:
+126:
+127:
+128:
+129:
+133:
+	addi	r3,r3,8
+121:
+132:
+	addi	r3,r3,8
+123:
+134:
+135:
+138:
+139:
+140:
+141:
+142:
+
+/*
+ * here we have had a fault on a load and r3 points to the first
+ * unmodified byte of the destination
+ */
+1:	ld	r6,-24(r1)
+	ld	r4,-16(r1)
+	ld	r5,-8(r1)
+	subf	r6,r6,r3
+	add	r4,r4,r6
+	subf	r5,r6,r5	/* #bytes left to go */
+
+/*
+ * first see if we can copy any more bytes before hitting another exception
+ */
+	mtctr	r5
+43:	lbz	r0,0(r4)
+	addi	r4,r4,1
+89:	stb	r0,0(r3)
+	addi	r3,r3,1
+	bdnz	43b
+	li	r3,0		/* huh? all copied successfully this time? */
+	blr
+
+/*
+ * here we have trapped again, need to clear ctr bytes starting at r3
+ */
+143:	mfctr	r5
+	li	r0,0
+	mr	r4,r3
+	mr	r3,r5		/* return the number of bytes not copied */
+1:	andi.	r9,r4,7
+	beq	3f
+90:	stb	r0,0(r4)
+	addic.	r5,r5,-1
+	addi	r4,r4,1
+	bne	1b
+	blr
+3:	cmpldi	cr1,r5,8
+	srdi	r9,r5,3
+	andi.	r5,r5,7
+	blt	cr1,93f
+	mtctr	r9
+91:	std	r0,0(r4)
+	addi	r4,r4,8
+	bdnz	91b
+93:	beqlr
+	mtctr	r5	
+92:	stb	r0,0(r4)
+	addi	r4,r4,1
+	bdnz	92b
+	blr
+
+/*
+ * exception handlers for stores: we just need to work
+ * out how many bytes weren't copied
+ */
+182:
+183:
+	add	r3,r3,r7
+	b	1f
+180:
+	addi	r3,r3,8
+171:
+177:
+	addi	r3,r3,8
+170:
+172:
+176:
+178:
+	addi	r3,r3,4
+185:
+	addi	r3,r3,4
+173:
+174:
+175:
+179:
+181:
+184:
+186:
+187:
+188:
+189:	
+1:
+	ld	r6,-24(r1)
+	ld	r5,-8(r1)
+	add	r6,r6,r5
+	subf	r3,r3,r6	/* #bytes not copied */
+190:
+191:
+192:
+	blr			/* #bytes not copied in r3 */
+
+	.section __ex_table,"a"
+	.align	3
+	.llong	20b,120b
+	.llong	21b,121b
+	.llong	70b,170b
+	.llong	22b,122b
+	.llong	71b,171b
+	.llong	72b,172b
+	.llong	23b,123b
+	.llong	73b,173b
+	.llong	74b,174b
+	.llong	75b,175b
+	.llong	24b,124b
+	.llong	25b,125b
+	.llong	26b,126b
+	.llong	27b,127b
+	.llong	28b,128b
+	.llong	29b,129b
+	.llong	30b,130b
+	.llong	31b,131b
+	.llong	32b,132b
+	.llong	76b,176b
+	.llong	33b,133b
+	.llong	77b,177b
+	.llong	78b,178b
+	.llong	79b,179b
+	.llong	80b,180b
+	.llong	34b,134b
+	.llong	35b,135b
+	.llong	81b,181b
+	.llong	36b,136b
+	.llong	82b,182b
+	.llong	37b,137b
+	.llong	83b,183b
+	.llong	38b,138b
+	.llong	39b,139b
+	.llong	84b,184b
+	.llong	85b,185b
+	.llong	40b,140b
+	.llong	86b,186b
+	.llong	41b,141b
+	.llong	87b,187b
+	.llong	42b,142b
+	.llong	88b,188b
+	.llong	43b,143b
+	.llong	89b,189b
+	.llong	90b,190b
+	.llong	91b,191b
+	.llong	92b,192b
+	
+	.text
+
+/*
+ * Routine to copy a whole page of data, optimized for POWER4.
+ * On POWER4 it is more than 50% faster than the simple loop
+ * above (following the .Ldst_aligned label) but it runs slightly
+ * slower on POWER3.
+ */
+.Lcopy_page:
+	std	r31,-32(1)
+	std	r30,-40(1)
+	std	r29,-48(1)
+	std	r28,-56(1)
+	std	r27,-64(1)
+	std	r26,-72(1)
+	std	r25,-80(1)
+	std	r24,-88(1)
+	std	r23,-96(1)
+	std	r22,-104(1)
+	std	r21,-112(1)
+	std	r20,-120(1)
+	li	r5,4096/32 - 1
+	addi	r3,r3,-8
+	li	r0,5
+0:	addi	r5,r5,-24
+	mtctr	r0
+20:	ld	r22,640(4)
+21:	ld	r21,512(4)
+22:	ld	r20,384(4)
+23:	ld	r11,256(4)
+24:	ld	r9,128(4)
+25:	ld	r7,0(4)
+26:	ld	r25,648(4)
+27:	ld	r24,520(4)
+28:	ld	r23,392(4)
+29:	ld	r10,264(4)
+30:	ld	r8,136(4)
+31:	ldu	r6,8(4)
+	cmpwi	r5,24
+1:
+32:	std	r22,648(3)
+33:	std	r21,520(3)
+34:	std	r20,392(3)
+35:	std	r11,264(3)
+36:	std	r9,136(3)
+37:	std	r7,8(3)
+38:	ld	r28,648(4)
+39:	ld	r27,520(4)
+40:	ld	r26,392(4)
+41:	ld	r31,264(4)
+42:	ld	r30,136(4)
+43:	ld	r29,8(4)
+44:	std	r25,656(3)
+45:	std	r24,528(3)
+46:	std	r23,400(3)
+47:	std	r10,272(3)
+48:	std	r8,144(3)
+49:	std	r6,16(3)
+50:	ld	r22,656(4)
+51:	ld	r21,528(4)
+52:	ld	r20,400(4)
+53:	ld	r11,272(4)
+54:	ld	r9,144(4)
+55:	ld	r7,16(4)
+56:	std	r28,664(3)
+57:	std	r27,536(3)
+58:	std	r26,408(3)
+59:	std	r31,280(3)
+60:	std	r30,152(3)
+61:	stdu	r29,24(3)
+62:	ld	r25,664(4)
+63:	ld	r24,536(4)
+64:	ld	r23,408(4)
+65:	ld	r10,280(4)
+66:	ld	r8,152(4)
+67:	ldu	r6,24(4)
+	bdnz	1b
+68:	std	r22,648(3)
+69:	std	r21,520(3)
+70:	std	r20,392(3)
+71:	std	r11,264(3)
+72:	std	r9,136(3)
+73:	std	r7,8(3)
+74:	addi	r4,r4,640
+75:	addi	r3,r3,648
+	bge	0b
+	mtctr	r5
+76:	ld	r7,0(4)
+77:	ld	r8,8(4)
+78:	ldu	r9,16(4)
+3:
+79:	ld	r10,8(4)
+80:	std	r7,8(3)
+81:	ld	r7,16(4)
+82:	std	r8,16(3)
+83:	ld	r8,24(4)
+84:	std	r9,24(3)
+85:	ldu	r9,32(4)
+86:	stdu	r10,32(3)
+	bdnz	3b
+4:
+87:	ld	r10,8(4)
+88:	std	r7,8(3)
+89:	std	r8,16(3)
+90:	std	r9,24(3)
+91:	std	r10,32(3)
+9:	ld	r20,-120(1)
+	ld	r21,-112(1)
+	ld	r22,-104(1)
+	ld	r23,-96(1)
+	ld	r24,-88(1)
+	ld	r25,-80(1)
+	ld	r26,-72(1)
+	ld	r27,-64(1)
+	ld	r28,-56(1)
+	ld	r29,-48(1)
+	ld	r30,-40(1)
+	ld	r31,-32(1)
+	li	r3,0
+	blr
+
+/*
+ * on an exception, reset to the beginning and jump back into the
+ * standard __copy_tofrom_user
+ */
+100:	ld	r20,-120(1)
+	ld	r21,-112(1)
+	ld	r22,-104(1)
+	ld	r23,-96(1)
+	ld	r24,-88(1)
+	ld	r25,-80(1)
+	ld	r26,-72(1)
+	ld	r27,-64(1)
+	ld	r28,-56(1)
+	ld	r29,-48(1)
+	ld	r30,-40(1)
+	ld	r31,-32(1)
+	ld	r3,-24(r1)
+	ld	r4,-16(r1)
+	li	r5,4096
+	b	.Ldst_aligned
+
+	.section __ex_table,"a"
+	.align	3
+	.llong	20b,100b
+	.llong	21b,100b
+	.llong	22b,100b
+	.llong	23b,100b
+	.llong	24b,100b
+	.llong	25b,100b
+	.llong	26b,100b
+	.llong	27b,100b
+	.llong	28b,100b
+	.llong	29b,100b
+	.llong	30b,100b
+	.llong	31b,100b
+	.llong	32b,100b
+	.llong	33b,100b
+	.llong	34b,100b
+	.llong	35b,100b
+	.llong	36b,100b
+	.llong	37b,100b
+	.llong	38b,100b
+	.llong	39b,100b
+	.llong	40b,100b
+	.llong	41b,100b
+	.llong	42b,100b
+	.llong	43b,100b
+	.llong	44b,100b
+	.llong	45b,100b
+	.llong	46b,100b
+	.llong	47b,100b
+	.llong	48b,100b
+	.llong	49b,100b
+	.llong	50b,100b
+	.llong	51b,100b
+	.llong	52b,100b
+	.llong	53b,100b
+	.llong	54b,100b
+	.llong	55b,100b
+	.llong	56b,100b
+	.llong	57b,100b
+	.llong	58b,100b
+	.llong	59b,100b
+	.llong	60b,100b
+	.llong	61b,100b
+	.llong	62b,100b
+	.llong	63b,100b
+	.llong	64b,100b
+	.llong	65b,100b
+	.llong	66b,100b
+	.llong	67b,100b
+	.llong	68b,100b
+	.llong	69b,100b
+	.llong	70b,100b
+	.llong	71b,100b
+	.llong	72b,100b
+	.llong	73b,100b
+	.llong	74b,100b
+	.llong	75b,100b
+	.llong	76b,100b
+	.llong	77b,100b
+	.llong	78b,100b
+	.llong	79b,100b
+	.llong	80b,100b
+	.llong	81b,100b
+	.llong	82b,100b
+	.llong	83b,100b
+	.llong	84b,100b
+	.llong	85b,100b
+	.llong	86b,100b
+	.llong	87b,100b
+	.llong	88b,100b
+	.llong	89b,100b
+	.llong	90b,100b
+	.llong	91b,100b
diff --git a/arch/powerpc/lib/div64.S b/arch/powerpc/lib/div64.S
new file mode 100644
index 000000000000..83d9832fd919
--- /dev/null
+++ b/arch/powerpc/lib/div64.S
@@ -0,0 +1,59 @@
+/*
+ * Divide a 64-bit unsigned number by a 32-bit unsigned number.
+ * This routine assumes that the top 32 bits of the dividend are
+ * non-zero to start with.
+ * On entry, r3 points to the dividend, which get overwritten with
+ * the 64-bit quotient, and r4 contains the divisor.
+ * On exit, r3 contains the remainder.
+ *
+ * Copyright (C) 2002 Paul Mackerras, IBM Corp.
+ *
+ * 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 <asm/ppc_asm.h>
+#include <asm/processor.h>
+
+_GLOBAL(__div64_32)
+	lwz	r5,0(r3)	# get the dividend into r5/r6
+	lwz	r6,4(r3)
+	cmplw	r5,r4
+	li	r7,0
+	li	r8,0
+	blt	1f
+	divwu	r7,r5,r4	# if dividend.hi >= divisor,
+	mullw	r0,r7,r4	# quotient.hi = dividend.hi / divisor
+	subf.	r5,r0,r5	# dividend.hi %= divisor
+	beq	3f
+1:	mr	r11,r5		# here dividend.hi != 0
+	andis.	r0,r5,0xc000
+	bne	2f
+	cntlzw	r0,r5		# we are shifting the dividend right
+	li	r10,-1		# to make it < 2^32, and shifting
+	srw	r10,r10,r0	# the divisor right the same amount,
+	addc	r9,r4,r10	# rounding up (so the estimate cannot
+	andc	r11,r6,r10	# ever be too large, only too small)
+	andc	r9,r9,r10
+	addze	r9,r9
+	or	r11,r5,r11
+	rotlw	r9,r9,r0
+	rotlw	r11,r11,r0
+	divwu	r11,r11,r9	# then we divide the shifted quantities
+2:	mullw	r10,r11,r4	# to get an estimate of the quotient,
+	mulhwu	r9,r11,r4	# multiply the estimate by the divisor,
+	subfc	r6,r10,r6	# take the product from the divisor,
+	add	r8,r8,r11	# and add the estimate to the accumulated
+	subfe.	r5,r9,r5	# quotient
+	bne	1b
+3:	cmplw	r6,r4
+	blt	4f
+	divwu	r0,r6,r4	# perform the remaining 32-bit division
+	mullw	r10,r0,r4	# and get the remainder
+	add	r8,r8,r0
+	subf	r6,r10,r6
+4:	stw	r7,0(r3)	# return the quotient in *r3
+	stw	r8,4(r3)
+	mr	r3,r6		# return the remainder in r3
+	blr
diff --git a/arch/powerpc/lib/e2a.c b/arch/powerpc/lib/e2a.c
new file mode 100644
index 000000000000..d2b834887920
--- /dev/null
+++ b/arch/powerpc/lib/e2a.c
@@ -0,0 +1,108 @@
+/*
+ *  arch/ppc64/lib/e2a.c
+ *
+ *  EBCDIC to ASCII conversion
+ *
+ * This function moved here from arch/ppc64/kernel/viopath.c
+ *
+ * (C) Copyright 2000-2004 IBM Corporation
+ *
+ * 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) anyu later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software Foundation,
+ * Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ */
+
+#include <linux/module.h>
+
+unsigned char e2a(unsigned char x)
+{
+	switch (x) {
+	case 0xF0:
+		return '0';
+	case 0xF1:
+		return '1';
+	case 0xF2:
+		return '2';
+	case 0xF3:
+		return '3';
+	case 0xF4:
+		return '4';
+	case 0xF5:
+		return '5';
+	case 0xF6:
+		return '6';
+	case 0xF7:
+		return '7';
+	case 0xF8:
+		return '8';
+	case 0xF9:
+		return '9';
+	case 0xC1:
+		return 'A';
+	case 0xC2:
+		return 'B';
+	case 0xC3:
+		return 'C';
+	case 0xC4:
+		return 'D';
+	case 0xC5:
+		return 'E';
+	case 0xC6:
+		return 'F';
+	case 0xC7:
+		return 'G';
+	case 0xC8:
+		return 'H';
+	case 0xC9:
+		return 'I';
+	case 0xD1:
+		return 'J';
+	case 0xD2:
+		return 'K';
+	case 0xD3:
+		return 'L';
+	case 0xD4:
+		return 'M';
+	case 0xD5:
+		return 'N';
+	case 0xD6:
+		return 'O';
+	case 0xD7:
+		return 'P';
+	case 0xD8:
+		return 'Q';
+	case 0xD9:
+		return 'R';
+	case 0xE2:
+		return 'S';
+	case 0xE3:
+		return 'T';
+	case 0xE4:
+		return 'U';
+	case 0xE5:
+		return 'V';
+	case 0xE6:
+		return 'W';
+	case 0xE7:
+		return 'X';
+	case 0xE8:
+		return 'Y';
+	case 0xE9:
+		return 'Z';
+	}
+	return ' ';
+}
+EXPORT_SYMBOL(e2a);
+
+
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
new file mode 100644
index 000000000000..2a912f411eb4
--- /dev/null
+++ b/arch/powerpc/lib/locks.c
@@ -0,0 +1,96 @@
+/*
+ * Spin and read/write lock operations.
+ *
+ * Copyright (C) 2001-2004 Paul Mackerras <paulus@au.ibm.com>, IBM
+ * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
+ * Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM
+ *   Rework to support virtual processors
+ *
+ * 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 <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/stringify.h>
+#include <linux/smp.h>
+
+/* waiting for a spinlock... */
+#if defined(CONFIG_PPC_SPLPAR) || defined(CONFIG_PPC_ISERIES)
+#include <asm/hvcall.h>
+#include <asm/iseries/hv_call.h>
+
+void __spin_yield(raw_spinlock_t *lock)
+{
+	unsigned int lock_value, holder_cpu, yield_count;
+	struct paca_struct *holder_paca;
+
+	lock_value = lock->slock;
+	if (lock_value == 0)
+		return;
+	holder_cpu = lock_value & 0xffff;
+	BUG_ON(holder_cpu >= NR_CPUS);
+	holder_paca = &paca[holder_cpu];
+	yield_count = holder_paca->lppaca.yield_count;
+	if ((yield_count & 1) == 0)
+		return;		/* virtual cpu is currently running */
+	rmb();
+	if (lock->slock != lock_value)
+		return;		/* something has changed */
+#ifdef CONFIG_PPC_ISERIES
+	HvCall2(HvCallBaseYieldProcessor, HvCall_YieldToProc,
+		((u64)holder_cpu << 32) | yield_count);
+#else
+	plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(holder_cpu),
+			   yield_count);
+#endif
+}
+
+/*
+ * Waiting for a read lock or a write lock on a rwlock...
+ * This turns out to be the same for read and write locks, since
+ * we only know the holder if it is write-locked.
+ */
+void __rw_yield(raw_rwlock_t *rw)
+{
+	int lock_value;
+	unsigned int holder_cpu, yield_count;
+	struct paca_struct *holder_paca;
+
+	lock_value = rw->lock;
+	if (lock_value >= 0)
+		return;		/* no write lock at present */
+	holder_cpu = lock_value & 0xffff;
+	BUG_ON(holder_cpu >= NR_CPUS);
+	holder_paca = &paca[holder_cpu];
+	yield_count = holder_paca->lppaca.yield_count;
+	if ((yield_count & 1) == 0)
+		return;		/* virtual cpu is currently running */
+	rmb();
+	if (rw->lock != lock_value)
+		return;		/* something has changed */
+#ifdef CONFIG_PPC_ISERIES
+	HvCall2(HvCallBaseYieldProcessor, HvCall_YieldToProc,
+		((u64)holder_cpu << 32) | yield_count);
+#else
+	plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(holder_cpu),
+			   yield_count);
+#endif
+}
+#endif
+
+void __raw_spin_unlock_wait(raw_spinlock_t *lock)
+{
+	while (lock->slock) {
+		HMT_low();
+		if (SHARED_PROCESSOR)
+			__spin_yield(lock);
+	}
+	HMT_medium();
+}
+
+EXPORT_SYMBOL(__raw_spin_unlock_wait);
diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S
new file mode 100644
index 000000000000..68df20283ff5
--- /dev/null
+++ b/arch/powerpc/lib/mem_64.S
@@ -0,0 +1,119 @@
+/*
+ * String handling functions for PowerPC.
+ *
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ * 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 <asm/processor.h>
+#include <asm/errno.h>
+#include <asm/ppc_asm.h>
+
+_GLOBAL(memset)
+	neg	r0,r3
+	rlwimi	r4,r4,8,16,23
+	andi.	r0,r0,7			/* # bytes to be 8-byte aligned */
+	rlwimi	r4,r4,16,0,15
+	cmplw	cr1,r5,r0		/* do we get that far? */
+	rldimi	r4,r4,32,0
+	mtcrf	1,r0
+	mr	r6,r3
+	blt	cr1,8f
+	beq+	3f			/* if already 8-byte aligned */
+	subf	r5,r0,r5
+	bf	31,1f
+	stb	r4,0(r6)
+	addi	r6,r6,1
+1:	bf	30,2f
+	sth	r4,0(r6)
+	addi	r6,r6,2
+2:	bf	29,3f
+	stw	r4,0(r6)
+	addi	r6,r6,4
+3:	srdi.	r0,r5,6
+	clrldi	r5,r5,58
+	mtctr	r0
+	beq	5f
+4:	std	r4,0(r6)
+	std	r4,8(r6)
+	std	r4,16(r6)
+	std	r4,24(r6)
+	std	r4,32(r6)
+	std	r4,40(r6)
+	std	r4,48(r6)
+	std	r4,56(r6)
+	addi	r6,r6,64
+	bdnz	4b
+5:	srwi.	r0,r5,3
+	clrlwi	r5,r5,29
+	mtcrf	1,r0
+	beq	8f
+	bf	29,6f
+	std	r4,0(r6)
+	std	r4,8(r6)
+	std	r4,16(r6)
+	std	r4,24(r6)
+	addi	r6,r6,32
+6:	bf	30,7f
+	std	r4,0(r6)
+	std	r4,8(r6)
+	addi	r6,r6,16
+7:	bf	31,8f
+	std	r4,0(r6)
+	addi	r6,r6,8
+8:	cmpwi	r5,0
+	mtcrf	1,r5
+	beqlr+
+	bf	29,9f
+	stw	r4,0(r6)
+	addi	r6,r6,4
+9:	bf	30,10f
+	sth	r4,0(r6)
+	addi	r6,r6,2
+10:	bflr	31
+	stb	r4,0(r6)
+	blr
+
+_GLOBAL(memmove)
+	cmplw	0,r3,r4
+	bgt	.backwards_memcpy
+	b	.memcpy
+
+_GLOBAL(backwards_memcpy)
+	rlwinm.	r7,r5,32-3,3,31		/* r0 = r5 >> 3 */
+	add	r6,r3,r5
+	add	r4,r4,r5
+	beq	2f
+	andi.	r0,r6,3
+	mtctr	r7
+	bne	5f
+1:	lwz	r7,-4(r4)
+	lwzu	r8,-8(r4)
+	stw	r7,-4(r6)
+	stwu	r8,-8(r6)
+	bdnz	1b
+	andi.	r5,r5,7
+2:	cmplwi	0,r5,4
+	blt	3f
+	lwzu	r0,-4(r4)
+	subi	r5,r5,4
+	stwu	r0,-4(r6)
+3:	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+4:	lbzu	r0,-1(r4)
+	stbu	r0,-1(r6)
+	bdnz	4b
+	blr
+5:	mtctr	r0
+6:	lbzu	r7,-1(r4)
+	stbu	r7,-1(r6)
+	bdnz	6b
+	subf	r5,r0,r5
+	rlwinm.	r7,r5,32-3,3,31
+	beq	2b
+	mtctr	r7
+	b	1b
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
new file mode 100644
index 000000000000..9ccacdf5bcb9
--- /dev/null
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -0,0 +1,172 @@
+/*
+ * arch/ppc64/lib/memcpy.S
+ *
+ * Copyright (C) 2002 Paul Mackerras, IBM Corp.
+ *
+ * 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 <asm/processor.h>
+#include <asm/ppc_asm.h>
+
+	.align	7
+_GLOBAL(memcpy)
+	mtcrf	0x01,r5
+	cmpldi	cr1,r5,16
+	neg	r6,r3		# LS 3 bits = # bytes to 8-byte dest bdry
+	andi.	r6,r6,7
+	dcbt	0,r4
+	blt	cr1,.Lshort_copy
+	bne	.Ldst_unaligned
+.Ldst_aligned:
+	andi.	r0,r4,7
+	addi	r3,r3,-16
+	bne	.Lsrc_unaligned
+	srdi	r7,r5,4
+	ld	r9,0(r4)
+	addi	r4,r4,-8
+	mtctr	r7
+	andi.	r5,r5,7
+	bf	cr7*4+0,2f
+	addi	r3,r3,8
+	addi	r4,r4,8
+	mr	r8,r9
+	blt	cr1,3f
+1:	ld	r9,8(r4)
+	std	r8,8(r3)
+2:	ldu	r8,16(r4)
+	stdu	r9,16(r3)
+	bdnz	1b
+3:	std	r8,8(r3)
+	beqlr
+	addi	r3,r3,16
+	ld	r9,8(r4)
+.Ldo_tail:
+	bf	cr7*4+1,1f
+	rotldi	r9,r9,32
+	stw	r9,0(r3)
+	addi	r3,r3,4
+1:	bf	cr7*4+2,2f
+	rotldi	r9,r9,16
+	sth	r9,0(r3)
+	addi	r3,r3,2
+2:	bf	cr7*4+3,3f
+	rotldi	r9,r9,8
+	stb	r9,0(r3)
+3:	blr
+
+.Lsrc_unaligned:
+	srdi	r6,r5,3
+	addi	r5,r5,-16
+	subf	r4,r0,r4
+	srdi	r7,r5,4
+	sldi	r10,r0,3
+	cmpdi	cr6,r6,3
+	andi.	r5,r5,7
+	mtctr	r7
+	subfic	r11,r10,64
+	add	r5,r5,r0
+
+	bt	cr7*4+0,0f
+
+	ld	r9,0(r4)	# 3+2n loads, 2+2n stores
+	ld	r0,8(r4)
+	sld	r6,r9,r10
+	ldu	r9,16(r4)
+	srd	r7,r0,r11
+	sld	r8,r0,r10
+	or	r7,r7,r6
+	blt	cr6,4f
+	ld	r0,8(r4)
+	# s1<< in r8, d0=(s0<<|s1>>) in r7, s3 in r0, s2 in r9, nix in r6 & r12
+	b	2f
+
+0:	ld	r0,0(r4)	# 4+2n loads, 3+2n stores
+	ldu	r9,8(r4)
+	sld	r8,r0,r10
+	addi	r3,r3,-8
+	blt	cr6,5f
+	ld	r0,8(r4)
+	srd	r12,r9,r11
+	sld	r6,r9,r10
+	ldu	r9,16(r4)
+	or	r12,r8,r12
+	srd	r7,r0,r11
+	sld	r8,r0,r10
+	addi	r3,r3,16
+	beq	cr6,3f
+
+	# d0=(s0<<|s1>>) in r12, s1<< in r6, s2>> in r7, s2<< in r8, s3 in r9
+1:	or	r7,r7,r6
+	ld	r0,8(r4)
+	std	r12,8(r3)
+2:	srd	r12,r9,r11
+	sld	r6,r9,r10
+	ldu	r9,16(r4)
+	or	r12,r8,r12
+	stdu	r7,16(r3)
+	srd	r7,r0,r11
+	sld	r8,r0,r10
+	bdnz	1b
+
+3:	std	r12,8(r3)
+	or	r7,r7,r6
+4:	std	r7,16(r3)
+5:	srd	r12,r9,r11
+	or	r12,r8,r12
+	std	r12,24(r3)
+	beqlr
+	cmpwi	cr1,r5,8
+	addi	r3,r3,32
+	sld	r9,r9,r10
+	ble	cr1,.Ldo_tail
+	ld	r0,8(r4)
+	srd	r7,r0,r11
+	or	r9,r7,r9
+	b	.Ldo_tail
+
+.Ldst_unaligned:
+	mtcrf	0x01,r6		# put #bytes to 8B bdry into cr7
+	subf	r5,r6,r5
+	li	r7,0
+	cmpldi	r1,r5,16
+	bf	cr7*4+3,1f
+	lbz	r0,0(r4)
+	stb	r0,0(r3)
+	addi	r7,r7,1
+1:	bf	cr7*4+2,2f
+	lhzx	r0,r7,r4
+	sthx	r0,r7,r3
+	addi	r7,r7,2
+2:	bf	cr7*4+1,3f
+	lwzx	r0,r7,r4
+	stwx	r0,r7,r3
+3:	mtcrf	0x01,r5
+	add	r4,r6,r4
+	add	r3,r6,r3
+	b	.Ldst_aligned
+
+.Lshort_copy:
+	bf	cr7*4+0,1f
+	lwz	r0,0(r4)
+	lwz	r9,4(r4)
+	addi	r4,r4,8
+	stw	r0,0(r3)
+	stw	r9,4(r3)
+	addi	r3,r3,8
+1:	bf	cr7*4+1,2f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+2:	bf	cr7*4+2,3f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+3:	bf	cr7*4+3,4f
+	lbz	r0,0(r4)
+	stb	r0,0(r3)
+4:	blr
diff --git a/arch/powerpc/lib/rheap.c b/arch/powerpc/lib/rheap.c
new file mode 100644
index 000000000000..42c5de2c898f
--- /dev/null
+++ b/arch/powerpc/lib/rheap.c
@@ -0,0 +1,693 @@
+/*
+ * arch/ppc/syslib/rheap.c
+ *
+ * A Remote Heap.  Remote means that we don't touch the memory that the
+ * heap points to. Normal heap implementations use the memory they manage
+ * to place their list. We cannot do that because the memory we manage may
+ * have special properties, for example it is uncachable or of different
+ * endianess.
+ *
+ * Author: Pantelis Antoniou <panto@intracom.gr>
+ *
+ * 2004 (c) INTRACOM S.A. Greece. This file is licensed under
+ * the terms of the GNU General Public License version 2. This program
+ * is licensed "as is" without any warranty of any kind, whether express
+ * or implied.
+ */
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include <asm/rheap.h>
+
+/*
+ * Fixup a list_head, needed when copying lists.  If the pointers fall
+ * between s and e, apply the delta.  This assumes that
+ * sizeof(struct list_head *) == sizeof(unsigned long *).
+ */
+static inline void fixup(unsigned long s, unsigned long e, int d,
+			 struct list_head *l)
+{
+	unsigned long *pp;
+
+	pp = (unsigned long *)&l->next;
+	if (*pp >= s && *pp < e)
+		*pp += d;
+
+	pp = (unsigned long *)&l->prev;
+	if (*pp >= s && *pp < e)
+		*pp += d;
+}
+
+/* Grow the allocated blocks */
+static int grow(rh_info_t * info, int max_blocks)
+{
+	rh_block_t *block, *blk;
+	int i, new_blocks;
+	int delta;
+	unsigned long blks, blke;
+
+	if (max_blocks <= info->max_blocks)
+		return -EINVAL;
+
+	new_blocks = max_blocks - info->max_blocks;
+
+	block = kmalloc(sizeof(rh_block_t) * max_blocks, GFP_KERNEL);
+	if (block == NULL)
+		return -ENOMEM;
+
+	if (info->max_blocks > 0) {
+
+		/* copy old block area */
+		memcpy(block, info->block,
+		       sizeof(rh_block_t) * info->max_blocks);
+
+		delta = (char *)block - (char *)info->block;
+
+		/* and fixup list pointers */
+		blks = (unsigned long)info->block;
+		blke = (unsigned long)(info->block + info->max_blocks);
+
+		for (i = 0, blk = block; i < info->max_blocks; i++, blk++)
+			fixup(blks, blke, delta, &blk->list);
+
+		fixup(blks, blke, delta, &info->empty_list);
+		fixup(blks, blke, delta, &info->free_list);
+		fixup(blks, blke, delta, &info->taken_list);
+
+		/* free the old allocated memory */
+		if ((info->flags & RHIF_STATIC_BLOCK) == 0)
+			kfree(info->block);
+	}
+
+	info->block = block;
+	info->empty_slots += new_blocks;
+	info->max_blocks = max_blocks;
+	info->flags &= ~RHIF_STATIC_BLOCK;
+
+	/* add all new blocks to the free list */
+	for (i = 0, blk = block + info->max_blocks; i < new_blocks; i++, blk++)
+		list_add(&blk->list, &info->empty_list);
+
+	return 0;
+}
+
+/*
+ * Assure at least the required amount of empty slots.  If this function
+ * causes a grow in the block area then all pointers kept to the block
+ * area are invalid!
+ */
+static int assure_empty(rh_info_t * info, int slots)
+{
+	int max_blocks;
+
+	/* This function is not meant to be used to grow uncontrollably */
+	if (slots >= 4)
+		return -EINVAL;
+
+	/* Enough space */
+	if (info->empty_slots >= slots)
+		return 0;
+
+	/* Next 16 sized block */
+	max_blocks = ((info->max_blocks + slots) + 15) & ~15;
+
+	return grow(info, max_blocks);
+}
+
+static rh_block_t *get_slot(rh_info_t * info)
+{
+	rh_block_t *blk;
+
+	/* If no more free slots, and failure to extend. */
+	/* XXX: You should have called assure_empty before */
+	if (info->empty_slots == 0) {
+		printk(KERN_ERR "rh: out of slots; crash is imminent.\n");
+		return NULL;
+	}
+
+	/* Get empty slot to use */
+	blk = list_entry(info->empty_list.next, rh_block_t, list);
+	list_del_init(&blk->list);
+	info->empty_slots--;
+
+	/* Initialize */
+	blk->start = NULL;
+	blk->size = 0;
+	blk->owner = NULL;
+
+	return blk;
+}
+
+static inline void release_slot(rh_info_t * info, rh_block_t * blk)
+{
+	list_add(&blk->list, &info->empty_list);
+	info->empty_slots++;
+}
+
+static void attach_free_block(rh_info_t * info, rh_block_t * blkn)
+{
+	rh_block_t *blk;
+	rh_block_t *before;
+	rh_block_t *after;
+	rh_block_t *next;
+	int size;
+	unsigned long s, e, bs, be;
+	struct list_head *l;
+
+	/* We assume that they are aligned properly */
+	size = blkn->size;
+	s = (unsigned long)blkn->start;
+	e = s + size;
+
+	/* Find the blocks immediately before and after the given one
+	 * (if any) */
+	before = NULL;
+	after = NULL;
+	next = NULL;
+
+	list_for_each(l, &info->free_list) {
+		blk = list_entry(l, rh_block_t, list);
+
+		bs = (unsigned long)blk->start;
+		be = bs + blk->size;
+
+		if (next == NULL && s >= bs)
+			next = blk;
+
+		if (be == s)
+			before = blk;
+
+		if (e == bs)
+			after = blk;
+
+		/* If both are not null, break now */
+		if (before != NULL && after != NULL)
+			break;
+	}
+
+	/* Now check if they are really adjacent */
+	if (before != NULL && s != (unsigned long)before->start + before->size)
+		before = NULL;
+
+	if (after != NULL && e != (unsigned long)after->start)
+		after = NULL;
+
+	/* No coalescing; list insert and return */
+	if (before == NULL && after == NULL) {
+
+		if (next != NULL)
+			list_add(&blkn->list, &next->list);
+		else
+			list_add(&blkn->list, &info->free_list);
+
+		return;
+	}
+
+	/* We don't need it anymore */
+	release_slot(info, blkn);
+
+	/* Grow the before block */
+	if (before != NULL && after == NULL) {
+		before->size += size;
+		return;
+	}
+
+	/* Grow the after block backwards */
+	if (before == NULL && after != NULL) {
+		after->start = (int8_t *)after->start - size;
+		after->size += size;
+		return;
+	}
+
+	/* Grow the before block, and release the after block */
+	before->size += size + after->size;
+	list_del(&after->list);
+	release_slot(info, after);
+}
+
+static void attach_taken_block(rh_info_t * info, rh_block_t * blkn)
+{
+	rh_block_t *blk;
+	struct list_head *l;
+
+	/* Find the block immediately before the given one (if any) */
+	list_for_each(l, &info->taken_list) {
+		blk = list_entry(l, rh_block_t, list);
+		if (blk->start > blkn->start) {
+			list_add_tail(&blkn->list, &blk->list);
+			return;
+		}
+	}
+
+	list_add_tail(&blkn->list, &info->taken_list);
+}
+
+/*
+ * Create a remote heap dynamically.  Note that no memory for the blocks
+ * are allocated.  It will upon the first allocation
+ */
+rh_info_t *rh_create(unsigned int alignment)
+{
+	rh_info_t *info;
+
+	/* Alignment must be a power of two */
+	if ((alignment & (alignment - 1)) != 0)
+		return ERR_PTR(-EINVAL);
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (info == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	info->alignment = alignment;
+
+	/* Initially everything as empty */
+	info->block = NULL;
+	info->max_blocks = 0;
+	info->empty_slots = 0;
+	info->flags = 0;
+
+	INIT_LIST_HEAD(&info->empty_list);
+	INIT_LIST_HEAD(&info->free_list);
+	INIT_LIST_HEAD(&info->taken_list);
+
+	return info;
+}
+
+/*
+ * Destroy a dynamically created remote heap.  Deallocate only if the areas
+ * are not static
+ */
+void rh_destroy(rh_info_t * info)
+{
+	if ((info->flags & RHIF_STATIC_BLOCK) == 0 && info->block != NULL)
+		kfree(info->block);
+
+	if ((info->flags & RHIF_STATIC_INFO) == 0)
+		kfree(info);
+}
+
+/*
+ * Initialize in place a remote heap info block.  This is needed to support
+ * operation very early in the startup of the kernel, when it is not yet safe
+ * to call kmalloc.
+ */
+void rh_init(rh_info_t * info, unsigned int alignment, int max_blocks,
+	     rh_block_t * block)
+{
+	int i;
+	rh_block_t *blk;
+
+	/* Alignment must be a power of two */
+	if ((alignment & (alignment - 1)) != 0)
+		return;
+
+	info->alignment = alignment;
+
+	/* Initially everything as empty */
+	info->block = block;
+	info->max_blocks = max_blocks;
+	info->empty_slots = max_blocks;
+	info->flags = RHIF_STATIC_INFO | RHIF_STATIC_BLOCK;
+
+	INIT_LIST_HEAD(&info->empty_list);
+	INIT_LIST_HEAD(&info->free_list);
+	INIT_LIST_HEAD(&info->taken_list);
+
+	/* Add all new blocks to the free list */
+	for (i = 0, blk = block; i < max_blocks; i++, blk++)
+		list_add(&blk->list, &info->empty_list);
+}
+
+/* Attach a free memory region, coalesces regions if adjuscent */
+int rh_attach_region(rh_info_t * info, void *start, int size)
+{
+	rh_block_t *blk;
+	unsigned long s, e, m;
+	int r;
+
+	/* The region must be aligned */
+	s = (unsigned long)start;
+	e = s + size;
+	m = info->alignment - 1;
+
+	/* Round start up */
+	s = (s + m) & ~m;
+
+	/* Round end down */
+	e = e & ~m;
+
+	/* Take final values */
+	start = (void *)s;
+	size = (int)(e - s);
+
+	/* Grow the blocks, if needed */
+	r = assure_empty(info, 1);
+	if (r < 0)
+		return r;
+
+	blk = get_slot(info);
+	blk->start = start;
+	blk->size = size;
+	blk->owner = NULL;
+
+	attach_free_block(info, blk);
+
+	return 0;
+}
+
+/* Detatch given address range, splits free block if needed. */
+void *rh_detach_region(rh_info_t * info, void *start, int size)
+{
+	struct list_head *l;
+	rh_block_t *blk, *newblk;
+	unsigned long s, e, m, bs, be;
+
+	/* Validate size */
+	if (size <= 0)
+		return ERR_PTR(-EINVAL);
+
+	/* The region must be aligned */
+	s = (unsigned long)start;
+	e = s + size;
+	m = info->alignment - 1;
+
+	/* Round start up */
+	s = (s + m) & ~m;
+
+	/* Round end down */
+	e = e & ~m;
+
+	if (assure_empty(info, 1) < 0)
+		return ERR_PTR(-ENOMEM);
+
+	blk = NULL;
+	list_for_each(l, &info->free_list) {
+		blk = list_entry(l, rh_block_t, list);
+		/* The range must lie entirely inside one free block */
+		bs = (unsigned long)blk->start;
+		be = (unsigned long)blk->start + blk->size;
+		if (s >= bs && e <= be)
+			break;
+		blk = NULL;
+	}
+
+	if (blk == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	/* Perfect fit */
+	if (bs == s && be == e) {
+		/* Delete from free list, release slot */
+		list_del(&blk->list);
+		release_slot(info, blk);
+		return (void *)s;
+	}
+
+	/* blk still in free list, with updated start and/or size */
+	if (bs == s || be == e) {
+		if (bs == s)
+			blk->start = (int8_t *)blk->start + size;
+		blk->size -= size;
+
+	} else {
+		/* The front free fragment */
+		blk->size = s - bs;
+
+		/* the back free fragment */
+		newblk = get_slot(info);
+		newblk->start = (void *)e;
+		newblk->size = be - e;
+
+		list_add(&newblk->list, &blk->list);
+	}
+
+	return (void *)s;
+}
+
+void *rh_alloc(rh_info_t * info, int size, const char *owner)
+{
+	struct list_head *l;
+	rh_block_t *blk;
+	rh_block_t *newblk;
+	void *start;
+
+	/* Validate size */
+	if (size <= 0)
+		return ERR_PTR(-EINVAL);
+
+	/* Align to configured alignment */
+	size = (size + (info->alignment - 1)) & ~(info->alignment - 1);
+
+	if (assure_empty(info, 1) < 0)
+		return ERR_PTR(-ENOMEM);
+
+	blk = NULL;
+	list_for_each(l, &info->free_list) {
+		blk = list_entry(l, rh_block_t, list);
+		if (size <= blk->size)
+			break;
+		blk = NULL;
+	}
+
+	if (blk == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	/* Just fits */
+	if (blk->size == size) {
+		/* Move from free list to taken list */
+		list_del(&blk->list);
+		blk->owner = owner;
+		start = blk->start;
+
+		attach_taken_block(info, blk);
+
+		return start;
+	}
+
+	newblk = get_slot(info);
+	newblk->start = blk->start;
+	newblk->size = size;
+	newblk->owner = owner;
+
+	/* blk still in free list, with updated start, size */
+	blk->start = (int8_t *)blk->start + size;
+	blk->size -= size;
+
+	start = newblk->start;
+
+	attach_taken_block(info, newblk);
+
+	return start;
+}
+
+/* allocate at precisely the given address */
+void *rh_alloc_fixed(rh_info_t * info, void *start, int size, const char *owner)
+{
+	struct list_head *l;
+	rh_block_t *blk, *newblk1, *newblk2;
+	unsigned long s, e, m, bs, be;
+
+	/* Validate size */
+	if (size <= 0)
+		return ERR_PTR(-EINVAL);
+
+	/* The region must be aligned */
+	s = (unsigned long)start;
+	e = s + size;
+	m = info->alignment - 1;
+
+	/* Round start up */
+	s = (s + m) & ~m;
+
+	/* Round end down */
+	e = e & ~m;
+
+	if (assure_empty(info, 2) < 0)
+		return ERR_PTR(-ENOMEM);
+
+	blk = NULL;
+	list_for_each(l, &info->free_list) {
+		blk = list_entry(l, rh_block_t, list);
+		/* The range must lie entirely inside one free block */
+		bs = (unsigned long)blk->start;
+		be = (unsigned long)blk->start + blk->size;
+		if (s >= bs && e <= be)
+			break;
+	}
+
+	if (blk == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	/* Perfect fit */
+	if (bs == s && be == e) {
+		/* Move from free list to taken list */
+		list_del(&blk->list);
+		blk->owner = owner;
+
+		start = blk->start;
+		attach_taken_block(info, blk);
+
+		return start;
+
+	}
+
+	/* blk still in free list, with updated start and/or size */
+	if (bs == s || be == e) {
+		if (bs == s)
+			blk->start = (int8_t *)blk->start + size;
+		blk->size -= size;
+
+	} else {
+		/* The front free fragment */
+		blk->size = s - bs;
+
+		/* The back free fragment */
+		newblk2 = get_slot(info);
+		newblk2->start = (void *)e;
+		newblk2->size = be - e;
+
+		list_add(&newblk2->list, &blk->list);
+	}
+
+	newblk1 = get_slot(info);
+	newblk1->start = (void *)s;
+	newblk1->size = e - s;
+	newblk1->owner = owner;
+
+	start = newblk1->start;
+	attach_taken_block(info, newblk1);
+
+	return start;
+}
+
+int rh_free(rh_info_t * info, void *start)
+{
+	rh_block_t *blk, *blk2;
+	struct list_head *l;
+	int size;
+
+	/* Linear search for block */
+	blk = NULL;
+	list_for_each(l, &info->taken_list) {
+		blk2 = list_entry(l, rh_block_t, list);
+		if (start < blk2->start)
+			break;
+		blk = blk2;
+	}
+
+	if (blk == NULL || start > (blk->start + blk->size))
+		return -EINVAL;
+
+	/* Remove from taken list */
+	list_del(&blk->list);
+
+	/* Get size of freed block */
+	size = blk->size;
+	attach_free_block(info, blk);
+
+	return size;
+}
+
+int rh_get_stats(rh_info_t * info, int what, int max_stats, rh_stats_t * stats)
+{
+	rh_block_t *blk;
+	struct list_head *l;
+	struct list_head *h;
+	int nr;
+
+	switch (what) {
+
+	case RHGS_FREE:
+		h = &info->free_list;
+		break;
+
+	case RHGS_TAKEN:
+		h = &info->taken_list;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	/* Linear search for block */
+	nr = 0;
+	list_for_each(l, h) {
+		blk = list_entry(l, rh_block_t, list);
+		if (stats != NULL && nr < max_stats) {
+			stats->start = blk->start;
+			stats->size = blk->size;
+			stats->owner = blk->owner;
+			stats++;
+		}
+		nr++;
+	}
+
+	return nr;
+}
+
+int rh_set_owner(rh_info_t * info, void *start, const char *owner)
+{
+	rh_block_t *blk, *blk2;
+	struct list_head *l;
+	int size;
+
+	/* Linear search for block */
+	blk = NULL;
+	list_for_each(l, &info->taken_list) {
+		blk2 = list_entry(l, rh_block_t, list);
+		if (start < blk2->start)
+			break;
+		blk = blk2;
+	}
+
+	if (blk == NULL || start > (blk->start + blk->size))
+		return -EINVAL;
+
+	blk->owner = owner;
+	size = blk->size;
+
+	return size;
+}
+
+void rh_dump(rh_info_t * info)
+{
+	static rh_stats_t st[32];	/* XXX maximum 32 blocks */
+	int maxnr;
+	int i, nr;
+
+	maxnr = sizeof(st) / sizeof(st[0]);
+
+	printk(KERN_INFO
+	       "info @0x%p (%d slots empty / %d max)\n",
+	       info, info->empty_slots, info->max_blocks);
+
+	printk(KERN_INFO "  Free:\n");
+	nr = rh_get_stats(info, RHGS_FREE, maxnr, st);
+	if (nr > maxnr)
+		nr = maxnr;
+	for (i = 0; i < nr; i++)
+		printk(KERN_INFO
+		       "    0x%p-0x%p (%u)\n",
+		       st[i].start, (int8_t *) st[i].start + st[i].size,
+		       st[i].size);
+	printk(KERN_INFO "\n");
+
+	printk(KERN_INFO "  Taken:\n");
+	nr = rh_get_stats(info, RHGS_TAKEN, maxnr, st);
+	if (nr > maxnr)
+		nr = maxnr;
+	for (i = 0; i < nr; i++)
+		printk(KERN_INFO
+		       "    0x%p-0x%p (%u) %s\n",
+		       st[i].start, (int8_t *) st[i].start + st[i].size,
+		       st[i].size, st[i].owner != NULL ? st[i].owner : "");
+	printk(KERN_INFO "\n");
+}
+
+void rh_dump_blk(rh_info_t * info, rh_block_t * blk)
+{
+	printk(KERN_INFO
+	       "blk @0x%p: 0x%p-0x%p (%u)\n",
+	       blk, blk->start, (int8_t *) blk->start + blk->size, blk->size);
+}
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
new file mode 100644
index 000000000000..666c2aa55016
--- /dev/null
+++ b/arch/powerpc/lib/sstep.c
@@ -0,0 +1,158 @@
+/*
+ * Single-step support.
+ *
+ * Copyright (C) 2004 Paul Mackerras <paulus@au.ibm.com>, IBM
+ *
+ * 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/kernel.h>
+#include <linux/ptrace.h>
+#include <linux/config.h>
+#include <asm/sstep.h>
+#include <asm/processor.h>
+
+extern char system_call_common[];
+
+#ifdef CONFIG_PPC64
+/* Bits in SRR1 that are copied from MSR */
+#define MSR_MASK	0xffffffff87c0ffff
+#else
+#define MSR_MASK	0x87c0ffff
+#endif
+
+/*
+ * Determine whether a conditional branch instruction would branch.
+ */
+static int branch_taken(unsigned int instr, struct pt_regs *regs)
+{
+	unsigned int bo = (instr >> 21) & 0x1f;
+	unsigned int bi;
+
+	if ((bo & 4) == 0) {
+		/* decrement counter */
+		--regs->ctr;
+		if (((bo >> 1) & 1) ^ (regs->ctr == 0))
+			return 0;
+	}
+	if ((bo & 0x10) == 0) {
+		/* check bit from CR */
+		bi = (instr >> 16) & 0x1f;
+		if (((regs->ccr >> (31 - bi)) & 1) != ((bo >> 3) & 1))
+			return 0;
+	}
+	return 1;
+}
+
+/*
+ * Emulate instructions that cause a transfer of control.
+ * Returns 1 if the step was emulated, 0 if not,
+ * or -1 if the instruction is one that should not be stepped,
+ * such as an rfid, or a mtmsrd that would clear MSR_RI.
+ */
+int emulate_step(struct pt_regs *regs, unsigned int instr)
+{
+	unsigned int opcode, rd;
+	unsigned long int imm;
+
+	opcode = instr >> 26;
+	switch (opcode) {
+	case 16:	/* bc */
+		imm = (signed short)(instr & 0xfffc);
+		if ((instr & 2) == 0)
+			imm += regs->nip;
+		regs->nip += 4;
+		if ((regs->msr & MSR_SF) == 0)
+			regs->nip &= 0xffffffffUL;
+		if (instr & 1)
+			regs->link = regs->nip;
+		if (branch_taken(instr, regs))
+			regs->nip = imm;
+		return 1;
+#ifdef CONFIG_PPC64
+	case 17:	/* sc */
+		/*
+		 * N.B. this uses knowledge about how the syscall
+		 * entry code works.  If that is changed, this will
+		 * need to be changed also.
+		 */
+		regs->gpr[9] = regs->gpr[13];
+		regs->gpr[11] = regs->nip + 4;
+		regs->gpr[12] = regs->msr & MSR_MASK;
+		regs->gpr[13] = (unsigned long) get_paca();
+		regs->nip = (unsigned long) &system_call_common;
+		regs->msr = MSR_KERNEL;
+		return 1;
+#endif
+	case 18:	/* b */
+		imm = instr & 0x03fffffc;
+		if (imm & 0x02000000)
+			imm -= 0x04000000;
+		if ((instr & 2) == 0)
+			imm += regs->nip;
+		if (instr & 1) {
+			regs->link = regs->nip + 4;
+			if ((regs->msr & MSR_SF) == 0)
+				regs->link &= 0xffffffffUL;
+		}
+		if ((regs->msr & MSR_SF) == 0)
+			imm &= 0xffffffffUL;
+		regs->nip = imm;
+		return 1;
+	case 19:
+		switch (instr & 0x7fe) {
+		case 0x20:	/* bclr */
+		case 0x420:	/* bcctr */
+			imm = (instr & 0x400)? regs->ctr: regs->link;
+			regs->nip += 4;
+			if ((regs->msr & MSR_SF) == 0) {
+				regs->nip &= 0xffffffffUL;
+				imm &= 0xffffffffUL;
+			}
+			if (instr & 1)
+				regs->link = regs->nip;
+			if (branch_taken(instr, regs))
+				regs->nip = imm;
+			return 1;
+		case 0x24:	/* rfid, scary */
+			return -1;
+		}
+	case 31:
+		rd = (instr >> 21) & 0x1f;
+		switch (instr & 0x7fe) {
+		case 0xa6:	/* mfmsr */
+			regs->gpr[rd] = regs->msr & MSR_MASK;
+			regs->nip += 4;
+			if ((regs->msr & MSR_SF) == 0)
+				regs->nip &= 0xffffffffUL;
+			return 1;
+		case 0x124:	/* mtmsr */
+			imm = regs->gpr[rd];
+			if ((imm & MSR_RI) == 0)
+				/* can't step mtmsr that would clear MSR_RI */
+				return -1;
+			regs->msr = imm;
+			regs->nip += 4;
+			return 1;
+#ifdef CONFIG_PPC64
+		case 0x164:	/* mtmsrd */
+			/* only MSR_EE and MSR_RI get changed if bit 15 set */
+			/* mtmsrd doesn't change MSR_HV and MSR_ME */
+			imm = (instr & 0x10000)? 0x8002: 0xefffffffffffefffUL;
+			imm = (regs->msr & MSR_MASK & ~imm)
+				| (regs->gpr[rd] & imm);
+			if ((imm & MSR_RI) == 0)
+				/* can't step mtmsrd that would clear MSR_RI */
+				return -1;
+			regs->msr = imm;
+			regs->nip += 4;
+			if ((imm & MSR_SF) == 0)
+				regs->nip &= 0xffffffffUL;
+			return 1;
+#endif
+		}
+	}
+	return 0;
+}
diff --git a/arch/powerpc/lib/strcase.c b/arch/powerpc/lib/strcase.c
new file mode 100644
index 000000000000..36b521091bbc
--- /dev/null
+++ b/arch/powerpc/lib/strcase.c
@@ -0,0 +1,23 @@
+#include <linux/ctype.h>
+
+int strcasecmp(const char *s1, const char *s2)
+{
+	int c1, c2;
+
+	do {
+		c1 = tolower(*s1++);
+		c2 = tolower(*s2++);
+	} while (c1 == c2 && c1 != 0);
+	return c1 - c2;
+}
+
+int strncasecmp(const char *s1, const char *s2, int n)
+{
+	int c1, c2;
+
+	do {
+		c1 = tolower(*s1++);
+		c2 = tolower(*s2++);
+	} while ((--n > 0) && c1 == c2 && c1 != 0);
+	return c1 - c2;
+}
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
new file mode 100644
index 000000000000..b9ca84ed8927
--- /dev/null
+++ b/arch/powerpc/lib/string.S
@@ -0,0 +1,198 @@
+/*
+ * String handling functions for PowerPC.
+ *
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ * 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/processor.h>
+#include <asm/errno.h>
+#include <asm/ppc_asm.h>
+
+	.section __ex_table,"a"
+#ifdef CONFIG_PPC64
+	.align	3
+#define EXTBL	.llong
+#else
+	.align	2
+#define EXTBL	.long
+#endif
+	.text
+	
+_GLOBAL(strcpy)
+	addi	r5,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r0,1(r4)
+	cmpwi	0,r0,0
+	stbu	r0,1(r5)
+	bne	1b
+	blr
+
+/* This clears out any unused part of the destination buffer,
+   just as the libc version does.  -- paulus */
+_GLOBAL(strncpy)
+	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+	addi	r6,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r0,1(r4)
+	cmpwi	0,r0,0
+	stbu	r0,1(r6)
+	bdnzf	2,1b		/* dec ctr, branch if ctr != 0 && !cr0.eq */
+	bnelr			/* if we didn't hit a null char, we're done */
+	mfctr	r5
+	cmpwi	0,r5,0		/* any space left in destination buffer? */
+	beqlr			/* we know r0 == 0 here */
+2:	stbu	r0,1(r6)	/* clear it out if so */
+	bdnz	2b
+	blr
+
+_GLOBAL(strcat)
+	addi	r5,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r0,1(r5)
+	cmpwi	0,r0,0
+	bne	1b
+	addi	r5,r5,-1
+1:	lbzu	r0,1(r4)
+	cmpwi	0,r0,0
+	stbu	r0,1(r5)
+	bne	1b
+	blr
+
+_GLOBAL(strcmp)
+	addi	r5,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r3,1(r5)
+	cmpwi	1,r3,0
+	lbzu	r0,1(r4)
+	subf.	r3,r0,r3
+	beqlr	1
+	beq	1b
+	blr
+
+_GLOBAL(strlen)
+	addi	r4,r3,-1
+1:	lbzu	r0,1(r4)
+	cmpwi	0,r0,0
+	bne	1b
+	subf	r3,r3,r4
+	blr
+
+_GLOBAL(memcmp)
+	cmpwi	0,r5,0
+	ble-	2f
+	mtctr	r5
+	addi	r6,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r3,1(r6)
+	lbzu	r0,1(r4)
+	subf.	r3,r0,r3
+	bdnzt	2,1b
+	blr
+2:	li	r3,0
+	blr
+
+_GLOBAL(memchr)
+	cmpwi	0,r5,0
+	ble-	2f
+	mtctr	r5
+	addi	r3,r3,-1
+1:	lbzu	r0,1(r3)
+	cmpw	0,r0,r4
+	bdnzf	2,1b
+	beqlr
+2:	li	r3,0
+	blr
+
+_GLOBAL(__clear_user)
+	addi	r6,r3,-4
+	li	r3,0
+	li	r5,0
+	cmplwi	0,r4,4
+	blt	7f
+	/* clear a single word */
+11:	stwu	r5,4(r6)
+	beqlr
+	/* clear word sized chunks */
+	andi.	r0,r6,3
+	add	r4,r0,r4
+	subf	r6,r0,r6
+	srwi	r0,r4,2
+	andi.	r4,r4,3
+	mtctr	r0
+	bdz	7f
+1:	stwu	r5,4(r6)
+	bdnz	1b
+	/* clear byte sized chunks */
+7:	cmpwi	0,r4,0
+	beqlr
+	mtctr	r4
+	addi	r6,r6,3
+8:	stbu	r5,1(r6)
+	bdnz	8b
+	blr
+90:	mr	r3,r4
+	blr
+91:	mfctr	r3
+	slwi	r3,r3,2
+	add	r3,r3,r4
+	blr
+92:	mfctr	r3
+	blr
+
+	.section __ex_table,"a"
+	EXTBL	11b,90b
+	EXTBL	1b,91b
+	EXTBL	8b,92b
+	.text
+
+_GLOBAL(__strncpy_from_user)
+	addi	r6,r3,-1
+	addi	r4,r4,-1
+	cmpwi	0,r5,0
+	beq	2f
+	mtctr	r5
+1:	lbzu	r0,1(r4)
+	cmpwi	0,r0,0
+	stbu	r0,1(r6)
+	bdnzf	2,1b		/* dec ctr, branch if ctr != 0 && !cr0.eq */
+	beq	3f
+2:	addi	r6,r6,1
+3:	subf	r3,r3,r6
+	blr
+99:	li	r3,-EFAULT
+	blr
+
+	.section __ex_table,"a"
+	EXTBL	1b,99b
+	.text
+
+/* r3 = str, r4 = len (> 0), r5 = top (highest addr) */
+_GLOBAL(__strnlen_user)
+	addi	r7,r3,-1
+	subf	r6,r7,r5	/* top+1 - str */
+	cmplw	0,r4,r6
+	bge	0f
+	mr	r6,r4
+0:	mtctr	r6		/* ctr = min(len, top - str) */
+1:	lbzu	r0,1(r7)	/* get next byte */
+	cmpwi	0,r0,0
+	bdnzf	2,1b		/* loop if --ctr != 0 && byte != 0 */
+	addi	r7,r7,1
+	subf	r3,r3,r7	/* number of bytes we have looked at */
+	beqlr			/* return if we found a 0 byte */
+	cmpw	0,r3,r4		/* did we look at all len bytes? */
+	blt	99f		/* if not, must have hit top */
+	addi	r3,r4,1		/* return len + 1 to indicate no null found */
+	blr
+99:	li	r3,0		/* bad address, return 0 */
+	blr
+
+	.section __ex_table,"a"
+	EXTBL	1b,99b
diff --git a/arch/powerpc/lib/usercopy_64.c b/arch/powerpc/lib/usercopy_64.c
new file mode 100644
index 000000000000..5eea6f3c1e03
--- /dev/null
+++ b/arch/powerpc/lib/usercopy_64.c
@@ -0,0 +1,41 @@
+/*
+ * Functions which are too large to be inlined.
+ *
+ * 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/module.h>
+#include <asm/uaccess.h>
+
+unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		n = __copy_from_user(to, from, n);
+	else
+		memset(to, 0, n);
+	return n;
+}
+
+unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (likely(access_ok(VERIFY_WRITE, to, n)))
+		n = __copy_to_user(to, from, n);
+	return n;
+}
+
+unsigned long copy_in_user(void __user *to, const void __user *from,
+			   unsigned long n)
+{
+	might_sleep();
+	if (likely(access_ok(VERIFY_READ, from, n) &&
+	    access_ok(VERIFY_WRITE, to, n)))
+		n =__copy_tofrom_user(to, from, n);
+	return n;
+}
+
+EXPORT_SYMBOL(copy_from_user);
+EXPORT_SYMBOL(copy_to_user);
+EXPORT_SYMBOL(copy_in_user);
+