powerpc: Merge enough to start building in arch/powerpc.

This creates the directory structure under arch/powerpc and a bunch
of Kconfig files.  It does a first-cut merge of arch/powerpc/mm,
arch/powerpc/lib and arch/powerpc/platforms/powermac.  This is enough
to build a 32-bit powermac kernel with ARCH=powerpc.

For now we are getting some unmerged files from arch/ppc/kernel and
arch/ppc/syslib, or arch/ppc64/kernel.  This makes some minor changes
to files in those directories and files outside arch/powerpc.

The boot directory is still not merged.  That's going to be interesting.

Signed-off-by: Paul Mackerras <paulus@samba.org>

14 files changed, 3142 insertions, 0 deletions

diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
new file mode 100644
index 00000000000..347f9798e43
--- /dev/null
+++ b/arch/powerpc/lib/Makefile
@@ -0,0 +1,9 @@
+#
+# Makefile for ppc-specific library files..
+#
+
+obj-y			:= strcase.o string.o
+obj-$(CONFIG_PPC32)	+= div64.o copy32.o checksum.o
+obj-$(CONFIG_PPC64)	+= copypage.o copyuser.o memcpy.o usercopy.o \
+			   sstep.o checksum64.o
+obj-$(CONFIG_PPC_ISERIES) += e2a.o
diff --git a/arch/powerpc/lib/checksum.S b/arch/powerpc/lib/checksum.S
new file mode 100644
index 00000000000..7874e8a8045
--- /dev/null
+++ b/arch/powerpc/lib/checksum.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/checksum64.S b/arch/powerpc/lib/checksum64.S
new file mode 100644
index 00000000000..ef96c6c58ef
--- /dev/null
+++ b/arch/powerpc/lib/checksum64.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/copy32.S b/arch/powerpc/lib/copy32.S
new file mode 100644
index 00000000000..420a912198a
--- /dev/null
+++ b/arch/powerpc/lib/copy32.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_LINE_SIZE
+LG_CACHELINE_BYTES = LG_L1_CACHE_LINE_SIZE
+CACHELINE_MASK = (L1_CACHE_LINE_SIZE-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_LINE_SIZE >= 32
+	COPY_16_BYTES
+#if L1_CACHE_LINE_SIZE >= 64
+	COPY_16_BYTES
+	COPY_16_BYTES
+#if L1_CACHE_LINE_SIZE >= 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_LINE_SIZE >= 32
+	COPY_16_BYTES_WITHEX(1)
+#if L1_CACHE_LINE_SIZE >= 64
+	COPY_16_BYTES_WITHEX(2)
+	COPY_16_BYTES_WITHEX(3)
+#if L1_CACHE_LINE_SIZE >= 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_LINE_SIZE >= 32
+	COPY_16_BYTES_EXCODE(1)
+#if L1_CACHE_LINE_SIZE >= 64
+	COPY_16_BYTES_EXCODE(2)
+	COPY_16_BYTES_EXCODE(3)
+#if L1_CACHE_LINE_SIZE >= 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.S b/arch/powerpc/lib/copypage.S
new file mode 100644
index 00000000000..733d61618bb
--- /dev/null
+++ b/arch/powerpc/lib/copypage.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.S b/arch/powerpc/lib/copyuser.S
new file mode 100644
index 00000000000..a0b3fbbd6fb
--- /dev/null
+++ b/arch/powerpc/lib/copyuser.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_co