Adding upstream version 4.19.249.upstream/4.19.249

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

36 files changed, 13332 insertions, 0 deletions

diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
new file mode 100644
index 000000000..36f913084
--- /dev/null
+++ b/arch/powerpc/lib/Makefile
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for ppc-specific library files..
+#
+
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+
+ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
+
+CFLAGS_REMOVE_code-patching.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE)
+
+CFLAGS_code-patching.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+CFLAGS_feature-fixups.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+
+obj-y += string.o alloc.o code-patching.o feature-fixups.o
+
+obj-$(CONFIG_PPC32)	+= div64.o copy_32.o crtsavres.o strlen_32.o
+
+# See corresponding test in arch/powerpc/Makefile
+# 64-bit linker creates .sfpr on demand for final link (vmlinux),
+# so it is only needed for modules, and only for older linkers which
+# do not support --save-restore-funcs
+ifeq ($(call ld-ifversion, -lt, 225000000, y),y)
+extra-$(CONFIG_PPC64)	+= crtsavres.o
+endif
+
+obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
+			       memcpy_power7.o
+
+obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
+	   memcpy_64.o pmem.o
+
+obj64-$(CONFIG_SMP)	+= locks.o
+obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
+obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
+
+obj-y			+= checksum_$(BITS).o checksum_wrappers.o \
+			   string_$(BITS).o memcmp_$(BITS).o
+
+obj-y			+= sstep.o ldstfp.o quad.o
+obj64-y			+= quad.o
+
+obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
+
+obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o
+
+obj-$(CONFIG_ALTIVEC)	+= xor_vmx.o xor_vmx_glue.o
+CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec)
+
+obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
new file mode 100644
index 000000000..06796dec0
--- /dev/null
+++ b/arch/powerpc/lib/alloc.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/bootmem.h>
+#include <linux/string.h>
+#include <asm/setup.h>
+
+
+void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask)
+{
+	void *p;
+
+	if (slab_is_available())
+		p = kzalloc(size, mask);
+	else {
+		p = memblock_virt_alloc(size, 0);
+	}
+	return p;
+}
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
new file mode 100644
index 000000000..aa224069f
--- /dev/null
+++ b/arch/powerpc/lib/checksum_32.S
@@ -0,0 +1,337 @@
+/*
+ * 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/cache.h>
+#include <asm/errno.h>
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+
+	.text
+
+/*
+ * 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)
+	subi	r3,r3,4
+	srawi.	r6,r4,2		/* Divide len by 4 and also clear carry */
+	beq	3f		/* if we're doing < 4 bytes */
+	andi.	r0,r3,2		/* Align buffer to longword boundary */
+	beq+	1f
+	lhz	r0,4(r3)	/* do 2 bytes to get aligned */
+	subi	r4,r4,2
+	addi	r3,r3,2
+	srwi.	r6,r4,2		/* # words to do */
+	adde	r5,r5,r0
+	beq	3f
+1:	andi.	r6,r6,3		/* Prepare to handle words 4 by 4 */
+	beq	21f
+	mtctr	r6
+2:	lwzu	r0,4(r3)
+	adde	r5,r5,r0
+	bdnz	2b
+21:	srwi.	r6,r4,4		/* # blocks of 4 words to do */
+	beq	3f
+	lwz	r0,4(r3)
+	mtctr	r6
+	lwz	r6,8(r3)
+	adde	r5,r5,r0
+	lwz	r7,12(r3)
+	adde	r5,r5,r6
+	lwzu	r8,16(r3)
+	adde	r5,r5,r7
+	bdz	23f
+22:	lwz	r0,4(r3)
+	adde	r5,r5,r8
+	lwz	r6,8(r3)
+	adde	r5,r5,r0
+	lwz	r7,12(r3)
+	adde	r5,r5,r6
+	lwzu	r8,16(r3)
+	adde	r5,r5,r7
+	bdnz	22b
+23:	adde	r5,r5,r8
+3:	andi.	r0,r4,2
+	beq+	4f
+	lhz	r0,4(r3)
+	addi	r3,r3,2
+	adde	r5,r5,r0
+4:	andi.	r0,r4,1
+	beq+	5f
+	lbz	r0,4(r3)
+	slwi	r0,r0,8		/* Upper byte of word */
+	adde	r5,r5,r0
+5:	addze	r3,r5		/* add in final carry */
+	blr
+EXPORT_SYMBOL(__csum_partial)
+
+/*
+ * 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)
+ */
+#define CSUM_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);	\
+	adde	r12,r12,r7;	\
+8 ## n ## 5:			\
+	stw	r8,8(r6);	\
+	adde	r12,r12,r8;	\
+8 ## n ## 6:			\
+	stw	r9,12(r6);	\
+	adde	r12,r12,r9;	\
+8 ## n ## 7:			\
+	stwu	r10,16(r6);	\
+	adde	r12,r12,r10
+
+#define CSUM_COPY_16_BYTES_EXCODE(n)		\
+	EX_TABLE(8 ## n ## 0b, src_error);	\
+	EX_TABLE(8 ## n ## 1b, src_error);	\
+	EX_TABLE(8 ## n ## 2b, src_error);	\
+	EX_TABLE(8 ## n ## 3b, src_error);	\
+	EX_TABLE(8 ## n ## 4b, dst_error);	\
+	EX_TABLE(8 ## n ## 5b, dst_error);	\
+	EX_TABLE(8 ## n ## 6b, dst_error);	\
+	EX_TABLE(8 ## n ## 7b, dst_error);
+
+	.text
+	.stabs	"arch/powerpc/lib/",N_SO,0,0,0f
+	.stabs	"checksum_32.S",N_SO,0,0,0f
+0:
+
+CACHELINE_BYTES = L1_CACHE_BYTES
+LG_CACHELINE_BYTES = L1_CACHE_SHIFT
+CACHELINE_MASK = (L1_CACHE_BYTES-1)
+
+_GLOBAL(csum_partial_copy_generic)
+	stwu	r1,-16(r1)
+	stw	r7,12(r1)
+	stw	r8,8(r1)
+
+	addic	r12,r6,0
+	addi	r6,r4,-4
+	neg	r0,r4
+	addi	r4,r3,-4
+	andi.	r0,r0,CACHELINE_MASK	/* # bytes to start of cache line */
+	crset	4*cr7+eq
+	beq	58f
+
+	cmplw	0,r5,r0			/* is this more than total to do? */
+	blt	63f			/* if not much to do */
+	rlwinm	r7,r6,3,0x8
+	rlwnm	r12,r12,r7,0,31	/* odd destination address: rotate one byte */
+	cmplwi	cr7,r7,0	/* is destination address even ? */
+	andi.	r8,r0,3			/* get it word-aligned first */
+	mtctr	r8
+	beq+	61f
+	li	r3,0
+70:	lbz	r9,4(r4)		/* do some bytes */
+	addi	r4,r4,1
+	slwi	r3,r3,8
+	rlwimi	r3,r9,0,24,31
+71:	stb	r9,4(r6)
+	addi	r6,r6,1
+	bdnz	70b
+	adde	r12,r12,r3
+61:	subf	r5,r0,r5
+	srwi.	r0,r0,2
+	mtctr	r0
+	beq	58f
+72:	lwzu	r9,4(r4)		/* do some words */
+	adde	r12,r12,r9
+73:	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
+	beq	63f
+
+	/* 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
+/* the main body of the cacheline loop */
+	CSUM_COPY_16_BYTES_WITHEX(0)
+#if L1_CACHE_BYTES >= 32
+	CSUM_COPY_16_BYTES_WITHEX(1)
+#if L1_CACHE_BYTES >= 64
+	CSUM_COPY_16_BYTES_WITHEX(2)
+	CSUM_COPY_16_BYTES_WITHEX(3)
+#if L1_CACHE_BYTES >= 128
+	CSUM_COPY_16_BYTES_WITHEX(4)
+	CSUM_COPY_16_BYTES_WITHEX(5)
+	CSUM_COPY_16_BYTES_WITHEX(6)
+	CSUM_COPY_16_BYTES_WITHEX(7)
+#endif
+#endif
+#endif
+	bdnz	53b
+	cmpwi	r0,0
+	li	r3,4
+	li	r7,0
+	bne	114b
+
+63:	srwi.	r0,r5,2
+	mtctr	r0
+	beq	64f
+30:	lwzu	r0,4(r4)
+	adde	r12,r12,r0
+31:	stwu	r0,4(r6)
+	bdnz	30b
+
+64:	andi.	r0,r5,2
+	beq+	65f
+40:	lhz	r0,4(r4)
+	addi	r4,r4,2
+41:	sth	r0,4(r6)
+	adde	r12,r12,r0
+	addi	r6,r6,2
+65:	andi.	r0,r5,1
+	beq+	66f
+50:	lbz	r0,4(r4)
+51:	stb	r0,4(r6)
+	slwi	r0,r0,8
+	adde	r12,r12,r0
+66:	addze	r3,r12
+	addi	r1,r1,16
+	beqlr+	cr7
+	rlwinm	r3,r3,8,0,31	/* odd destination address: rotate one byte */
+	blr
+
+/* read fault */
+src_error:
+	lwz	r7,12(r1)
+	addi	r1,r1,16
+	cmpwi	cr0,r7,0
+	beqlr
+	li	r0,-EFAULT
+	stw	r0,0(r7)
+	blr
+/* write fault */
+dst_error:
+	lwz	r8,8(r1)
+	addi	r1,r1,16
+	cmpwi	cr0,r8,0
+	beqlr
+	li	r0,-EFAULT
+	stw	r0,0(r8)
+	blr
+
+	EX_TABLE(70b, src_error);
+	EX_TABLE(71b, dst_error);
+	EX_TABLE(72b, src_error);
+	EX_TABLE(73b, dst_error);
+	EX_TABLE(54b, dst_error);
+
+/*
+ * this stuff handles faults in the cacheline loop and branches to either
+ * src_error (if in read part) or dst_error (if in write part)
+ */
+	CSUM_COPY_16_BYTES_EXCODE(0)
+#if L1_CACHE_BYTES >= 32
+	CSUM_COPY_16_BYTES_EXCODE(1)
+#if L1_CACHE_BYTES >= 64
+	CSUM_COPY_16_BYTES_EXCODE(2)
+	CSUM_COPY_16_BYTES_EXCODE(3)
+#if L1_CACHE_BYTES >= 128
+	CSUM_COPY_16_BYTES_EXCODE(4)
+	CSUM_COPY_16_BYTES_EXCODE(5)
+	CSUM_COPY_16_BYTES_EXCODE(6)
+	CSUM_COPY_16_BYTES_EXCODE(7)
+#endif
+#endif
+#endif
+
+	EX_TABLE(30b, src_error);
+	EX_TABLE(31b, dst_error);
+	EX_TABLE(40b, src_error);
+	EX_TABLE(41b, dst_error);
+	EX_TABLE(50b, src_error);
+	EX_TABLE(51b, dst_error);
+
+EXPORT_SYMBOL(csum_partial_copy_generic)
+
+/*
+ * __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ *			   const struct in6_addr *daddr,
+ *			   __u32 len, __u8 proto, __wsum sum)
+ */
+
+_GLOBAL(csum_ipv6_magic)
+	lwz	r8, 0(r3)
+	lwz	r9, 4(r3)
+	addc	r0, r7, r8
+	lwz	r10, 8(r3)
+	adde	r0, r0, r9
+	lwz	r11, 12(r3)
+	adde	r0, r0, r10
+	lwz	r8, 0(r4)
+	adde	r0, r0, r11
+	lwz	r9, 4(r4)
+	adde	r0, r0, r8
+	lwz	r10, 8(r4)
+	adde	r0, r0, r9
+	lwz	r11, 12(r4)
+	adde	r0, r0, r10
+	add	r5, r5, r6	/* assumption: len + proto doesn't carry */
+	adde	r0, r0, r11
+	adde	r0, r0, r5
+	addze	r0, r0
+	rotlwi	r3, r0, 16
+	add	r3, r0, r3
+	not	r3, r3
+	rlwinm	r3, r3, 16, 16, 31
+	blr
+EXPORT_SYMBOL(csum_ipv6_magic)
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
new file mode 100644
index 000000000..d05c8af4a
--- /dev/null
+++ b/arch/powerpc/lib/checksum_64.S
@@ -0,0 +1,462 @@
+/*
+ * 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>
+#include <asm/export.h>
+
+/*
+ * Computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit).
+ *
+ * __csum_partial(r3=buff, r4=len, r5=sum)
+ */
+_GLOBAL(__csum_partial)
+	addic	r0,r5,0			/* clear carry */
+
+	srdi.	r6,r4,3			/* less than 8 bytes? */
+	beq	.Lcsum_tail_word
+
+	/*
+	 * If only halfword aligned, align to a double word. Since odd
+	 * aligned addresses should be rare and they would require more
+	 * work to calculate the correct checksum, we ignore that case
+	 * and take the potential slowdown of unaligned loads.
+	 */
+	rldicl. r6,r3,64-1,64-2		/* r6 = (r3 >> 1) & 0x3 */
+	beq	.Lcsum_aligned
+
+	li	r7,4
+	sub	r6,r7,r6
+	mtctr	r6
+
+1:
+	lhz	r6,0(r3)		/* align to doubleword */
+	subi	r4,r4,2
+	addi	r3,r3,2
+	adde	r0,r0,r6
+	bdnz	1b
+
+.Lcsum_aligned:
+	/*
+	 * We unroll the loop such that each iteration is 64 bytes with an
+	 * entry and exit limb of 64 bytes, meaning a minimum size of
+	 * 128 bytes.
+	 */
+	srdi.	r6,r4,7
+	beq	.Lcsum_tail_doublewords		/* len < 128 */
+
+	srdi	r6,r4,6
+	subi	r6,r6,1
+	mtctr	r6
+
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+
+	ld	r6,0(r3)
+	ld	r9,8(r3)
+
+	ld	r10,16(r3)
+	ld	r11,24(r3)
+
+	/*
+	 * On POWER6 and POWER7 back to back adde instructions take 2 cycles
+	 * because of the XER dependency. This means the fastest this loop can
+	 * go is 16 cycles per iteration. The scheduling of the loop below has
+	 * been shown to hit this on both POWER6 and POWER7.
+	 */
+	.align 5
+2:
+	adde	r0,r0,r6
+	ld	r12,32(r3)
+	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+	ld	r15,48(r3)
+	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+
+	adde	r0,r0,r11
+
+	adde	r0,r0,r12
+
+	adde	r0,r0,r14
+
+	adde	r0,r0,r15
+	ld	r6,0(r3)
+	ld	r9,8(r3)
+
+	adde	r0,r0,r16
+	ld	r10,16(r3)
+	ld	r11,24(r3)
+	bdnz	2b
+
+
+	adde	r0,r0,r6
+	ld	r12,32(r3)
+	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+	ld	r15,48(r3)
+	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+	adde	r0,r0,r11
+	adde	r0,r0,r12
+	adde	r0,r0,r14
+	adde	r0,r0,r15
+	adde	r0,r0,r16
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	andi.	r4,r4,63
+
+.Lcsum_tail_doublewords:		/* Up to 127 bytes to go */
+	srdi.	r6,r4,3
+	beq	.Lcsum_tail_word
+
+	mtctr	r6
+3:
+	ld	r6,0(r3)
+	addi	r3,r3,8
+	adde	r0,r0,r6
+	bdnz	3b
+
+	andi.	r4,r4,7
+
+.Lcsum_tail_word:			/* Up to 7 bytes to go */
+	srdi.	r6,r4,2
+	beq	.Lcsum_tail_halfword
+
+	lwz	r6,0(r3)
+	addi	r3,r3,4
+	adde	r0,r0,r6
+	subi	r4,r4,4
+
+.Lcsum_tail_halfword:			/* Up to 3 bytes to go */
+	srdi.	r6,r4,1
+	beq	.Lcsum_tail_byte
+
+	lhz	r6,0(r3)
+	addi	r3,r3,2
+	adde	r0,r0,r6
+	subi	r4,r4,2
+
+.Lcsum_tail_byte:			/* Up to 1 byte to go */
+	andi.	r6,r4,1
+	beq	.Lcsum_finish
+
+	lbz	r6,0(r3)
+#ifdef __BIG_ENDIAN__
+	sldi	r9,r6,8			/* Pad the byte out to 16 bits */
+	adde	r0,r0,r9
+#else
+	adde	r0,r0,r6
+#endif
+
+.Lcsum_finish:
+	addze	r0,r0			/* add in final carry */
+	rldicl	r4,r0,32,0		/* fold two 32 bit halves together */
+	add	r3,r4,r0
+	srdi	r3,r3,32
+	blr
+EXPORT_SYMBOL(__csum_partial)
+
+
+	.macro srcnr
+100:
+	EX_TABLE(100b,.Lsrc_error_nr)
+	.endm
+
+	.macro source
+150:
+	EX_TABLE(150b,.Lsrc_error)
+	.endm
+
+	.macro dstnr
+200:
+	EX_TABLE(200b,.Ldest_error_nr)
+	.endm
+
+	.macro dest
+250:
+	EX_TABLE(250b,.Ldest_error)
+	.endm
+
+/*
+ * 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. The caller must take any action
+ * required in this case (zeroing memory, recalculating partial checksum etc).
+ *
+ * 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			/* clear carry */
+
+	srdi.	r6,r5,3			/* less than 8 bytes? */
+	beq	.Lcopy_tail_word
+
+	/*
+	 * If only halfword aligned, align to a double word. Since odd
+	 * aligned addresses should be rare and they would require more
+	 * work to calculate the correct checksum, we ignore that case
+	 * and take the potential slowdown of unaligned loads.
+	 *
+	 * If the source and destination are relatively unaligned we only
+	 * align the source. This keeps things simple.
+	 */
+	rldicl. r6,r3,64-1,64-2		/* r6 = (r3 >> 1) & 0x3 */
+	beq	.Lcopy_aligned
+
+	li	r9,4
+	sub	r6,r9,r6
+	mtctr	r6
+
+1:
+srcnr;	lhz	r6,0(r3)		/* align to doubleword */
+	subi	r5,r5,2
+	addi	r3,r3,2
+	adde	r0,r0,r6
+dstnr;	sth	r6,0(r4)
+	addi	r4,r4,2
+	bdnz	1b
+
+.Lcopy_aligned:
+	/*
+	 * We unroll the loop such that each iteration is 64 bytes with an
+	 * entry and exit limb of 64 bytes, meaning a minimum size of
+	 * 128 bytes.
+	 */
+	srdi.	r6,r5,7
+	beq	.Lcopy_tail_doublewords		/* len < 128 */
+
+	srdi	r6,r5,6
+	subi	r6,r6,1
+	mtctr	r6
+
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+
+source;	ld	r6,0(r3)
+source;	ld	r9,8(r3)
+
+source;	ld	r10,16(r3)
+source;	ld	r11,24(r3)
+
+	/*
+	 * On POWER6 and POWER7 back to back adde instructions take 2 cycles
+	 * because of the XER dependency. This means the fastest this loop can
+	 * go is 16 cycles per iteration. The scheduling of the loop below has
+	 * been shown to hit this on both POWER6 and POWER7.
+	 */
+	.align 5
+2:
+	adde	r0,r0,r6
+source;	ld	r12,32(r3)
+source;	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+source;	ld	r15,48(r3)
+source;	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+dest;	std	r6,0(r4)
+dest;	std	r9,8(r4)
+
+	adde	r0,r0,r11
+dest;	std	r10,16(r4)
+dest;	std	r11,24(r4)
+
+	adde	r0,r0,r12
+dest;	std	r12,32(r4)
+dest;	std	r14,40(r4)
+
+	adde	r0,r0,r14
+dest;	std	r15,48(r4)
+dest;	std	r16,56(r4)
+	addi	r4,r4,64
+
+	adde	r0,r0,r15
+source;	ld	r6,0(r3)
+source;	ld	r9,8(r3)
+
+	adde	r0,r0,r16
+source;	ld	r10,16(r3)
+source;	ld	r11,24(r3)
+	bdnz	2b
+
+
+	adde	r0,r0,r6
+source;	ld	r12,32(r3)
+source;	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+source;	ld	r15,48(r3)
+source;	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+dest;	std	r6,0(r4)
+dest;	std	r9,8(r4)
+
+	adde	r0,r0,r11
+dest;	std	r10,16(r4)
+dest;	std	r11,24(r4)
+
+	adde	r0,r0,r12
+dest;	std	r12,32(r4)
+dest;	std	r14,40(r4)
+
+	adde	r0,r0,r14
+dest;	std	r15,48(r4)
+dest;	std	r16,56(r4)
+	addi	r4,r4,64
+
+	adde	r0,r0,r15
+	adde	r0,r0,r16
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	andi.	r5,r5,63
+
+.Lcopy_tail_doublewords:		/* Up to 127 bytes to go */
+	srdi.	r6,r5,3
+	beq	.Lcopy_tail_word
+
+	mtctr	r6
+3:
+srcnr;	ld	r6,0(r3)
+	addi	r3,r3,8
+	adde	r0,r0,r6
+dstnr;	std	r6,0(r4)
+	addi	r4,r4,8
+	bdnz	3b
+
+	andi.	r5,r5,7
+
+.Lcopy_tail_word:			/* Up to 7 bytes to go */
+	srdi.	r6,r5,2
+	beq	.Lcopy_tail_halfword
+
+srcnr;	lwz	r6,0(r3)
+	addi	r3,r3,4
+	adde	r0,r0,r6
+dstnr;	stw	r6,0(r4)
+	addi	r4,r4,4
+	subi	r5,r5,4
+
+.Lcopy_tail_halfword:			/* Up to 3 bytes to go */
+	srdi.	r6,r5,1
+	beq	.Lcopy_tail_byte
+
+srcnr;	lhz	r6,0(r3)
+	addi	r3,r3,2
+	adde	r0,r0,r6
+dstnr;	sth	r6,0(r4)
+	addi	r4,r4,2
+	subi	r5,r5,2
+
+.Lcopy_tail_byte:			/* Up to 1 byte to go */
+	andi.	r6,r5,1
+	beq	.Lcopy_finish
+
+srcnr;	lbz	r6,0(r3)
+#ifdef __BIG_ENDIAN__
+	sldi	r9,r6,8			/* Pad the byte out to 16 bits */
+	adde	r0,r0,r9
+#else
+	adde	r0,r0,r6
+#endif
+dstnr;	stb	r6,0(r4)
+
+.Lcopy_finish:
+	addze	r0,r0			/* add in final carry */
+	rldicl	r4,r0,32,0		/* fold two 32 bit halves together */
+	add	r3,r4,r0
+	srdi	r3,r3,32
+	blr
+
+.Lsrc_error:
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Lsrc_error_nr:
+	cmpdi	0,r7,0
+	beqlr
+	li	r6,-EFAULT
+	stw	r6,0(r7)
+	blr
+
+.Ldest_error:
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Ldest_error_nr:
+	cmpdi	0,r8,0
+	beqlr
+	li	r6,-EFAULT
+	stw	r6,0(r8)
+	blr
+EXPORT_SYMBOL(csum_partial_copy_generic)
+
+/*
+ * __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ *			   const struct in6_addr *daddr,
+ *			   __u32 len, __u8 proto, __wsum sum)
+ */
+
+_GLOBAL(csum_ipv6_magic)
+	ld	r8, 0(r3)
+	ld	r9, 8(r3)
+	add	r5, r5, r6
+	addc	r0, r8, r9
+	ld	r10, 0(r4)
+	ld	r11, 8(r4)
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+	rotldi	r5, r5, 8
+#endif
+	adde	r0, r0, r10
+	add	r5, r5, r7
+	adde	r0, r0, r11
+	adde	r0, r0, r5
+	addze	r0, r0
+	rotldi  r3, r0, 32		/* fold two 32 bit halves together */
+	add	r3, r0, r3
+	srdi	r0, r3, 32
+	rotlwi	r3, r0, 16		/* fold two 16 bit halves together */
+	add	r3, r0, r3
+	not	r3, r3
+	rlwinm	r3, r3, 16, 16, 31
+	blr
+EXPORT_SYMBOL(csum_ipv6_magic)
diff --git a/arch/powerpc/lib/checksum_wrappers.c b/arch/powerpc/lib/checksum_wrappers.c
new file mode 100644
index 000000000..8d83c39be
--- /dev/null
+++ b/arch/powerpc/lib/checksum_wrappers.c
@@ -0,0 +1,106 @@
+/*
+ * 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.
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2010
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <linux/export.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/checksum.h>
+#include <linux/uaccess.h>
+
+__wsum csum_and_copy_from_user(const void __user *src, void *dst,
+			       int len, __wsum sum, int *err_ptr)
+{
+	unsigned int csum;
+
+	might_sleep();
+	allow_read_from_user(src, len);
+
+	*err_ptr = 0;
+
+	if (!len) {
+		csum = 0;
+		goto out;
+	}
+
+	if (unlikely((len < 0) || !access_ok(VERIFY_READ, src, len))) {
+		*err_ptr = -EFAULT;
+		csum = (__force unsigned int)sum;
+		goto out;
+	}
+
+	csum = csum_partial_copy_generic((void __force *)src, dst,
+					 len, sum, err_ptr, NULL);
+
+	if (unlikely(*err_ptr)) {
+		int missing = __copy_from_user(dst, src, len);
+
+		if (missing) {
+			memset(dst + len - missing, 0, missing);
+			*err_ptr = -EFAULT;
+		} else {
+			*err_ptr = 0;
+		}
+
+		csum = csum_partial(dst, len, sum);
+	}
+
+out:
+	prevent_read_from_user(src, len);
+	return (__force __wsum)csum;
+}
+EXPORT_SYMBOL(csum_and_copy_from_user);
+
+__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
+			     __wsum sum, int *err_ptr)
+{
+	unsigned int csum;
+
+	might_sleep();
+	allow_write_to_user(dst, len);
+
+	*err_ptr = 0;
+
+	if (!len) {
+		csum = 0;
+		goto out;
+	}
+
+	if (unlikely((len < 0) || !access_ok(VERIFY_WRITE, dst, len))) {
+		*err_ptr = -EFAULT;
+		csum = -1; /* invalid checksum */
+		goto out;
+	}
+
+	csum = csum_partial_copy_generic(src, (void __force *)dst,
+					 len, sum, NULL, err_ptr);
+
+	if (unlikely(*err_ptr)) {
+		csum = csum_partial(src, len, sum);
+
+		if (copy_to_user(dst, src, len)) {
+			*err_ptr = -EFAULT;
+			csum = -1; /* invalid checksum */
+		}
+	}
+
+out:
+	prevent_write_to_user(dst, len);
+	return (__force __wsum)csum;
+}
+EXPORT_SYMBOL(csum_and_copy_to_user);
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
new file mode 100644
index 000000000..bb245dbf6
--- /dev/null
+++ b/arch/powerpc/lib/code-patching.c
@@ -0,0 +1,713 @@
+/*
+ *  Copyright 2008 Michael Ellerman, 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) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/cpuhotplug.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/page.h>
+#include <asm/code-patching.h>
+#include <asm/setup.h>
+
+static int __patch_instruction(unsigned int *exec_addr, unsigned int instr,
+			       unsigned int *patch_addr)
+{
+	int err;
+
+	__put_user_size(instr, patch_addr, 4, err);
+	if (err)
+		return err;
+
+	asm ("dcbst 0, %0; sync; icbi 0,%1; sync; isync" :: "r" (patch_addr),
+							    "r" (exec_addr));
+
+	return 0;
+}
+
+int raw_patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	return __patch_instruction(addr, instr, addr);
+}
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+static DEFINE_PER_CPU(struct vm_struct *, text_poke_area);
+
+static int text_area_cpu_up(unsigned int cpu)
+{
+	struct vm_struct *area;
+
+	area = get_vm_area(PAGE_SIZE, VM_ALLOC);
+	if (!area) {
+		WARN_ONCE(1, "Failed to create text area for cpu %d\n",
+			cpu);
+		return -1;
+	}
+	this_cpu_write(text_poke_area, area);
+
+	return 0;
+}
+
+static int text_area_cpu_down(unsigned int cpu)
+{
+	free_vm_area(this_cpu_read(text_poke_area));
+	return 0;
+}
+
+/*
+ * Run as a late init call. This allows all the boot time patching to be done
+ * simply by patching the code, and then we're called here prior to
+ * mark_rodata_ro(), which happens after all init calls are run. Although
+ * BUG_ON() is rude, in this case it should only happen if ENOMEM, and we judge
+ * it as being preferable to a kernel that will crash later when someone tries
+ * to use patch_instruction().
+ */
+static int __init setup_text_poke_area(void)
+{
+	BUG_ON(!cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+		"powerpc/text_poke:online", text_area_cpu_up,
+		text_area_cpu_down));
+
+	return 0;
+}
+late_initcall(setup_text_poke_area);
+
+/*
+ * This can be called for kernel text or a module.
+ */
+static int map_patch_area(void *addr, unsigned long text_poke_addr)
+{
+	unsigned long pfn;
+	int err;
+
+	if (is_vmalloc_addr(addr))
+		pfn = vmalloc_to_pfn(addr);
+	else
+		pfn = __pa_symbol(addr) >> PAGE_SHIFT;
+
+	err = map_kernel_page(text_poke_addr, (pfn << PAGE_SHIFT),
+				pgprot_val(PAGE_KERNEL));
+
+	pr_devel("Mapped addr %lx with pfn %lx:%d\n", text_poke_addr, pfn, err);
+	if (err)
+		return -1;
+
+	return 0;
+}
+
+static inline int unmap_patch_area(unsigned long addr)
+{
+	pte_t *ptep;
+	pmd_t *pmdp;
+	pud_t *pudp;
+	pgd_t *pgdp;
+
+	pgdp = pgd_offset_k(addr);
+	if (unlikely(!pgdp))
+		return -EINVAL;
+
+	pudp = pud_offset(pgdp, addr);
+	if (unlikely(!pudp))
+		return -EINVAL;
+
+	pmdp = pmd_offset(pudp, addr);
+	if (unlikely(!pmdp))
+		return -EINVAL;
+
+	ptep = pte_offset_kernel(pmdp, addr);
+	if (unlikely(!ptep))
+		return -EINVAL;
+
+	pr_devel("clearing mm %p, pte %p, addr %lx\n", &init_mm, ptep, addr);
+
+	/*
+	 * In hash, pte_clear flushes the tlb, in radix, we have to
+	 */
+	pte_clear(&init_mm, addr, ptep);
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+	return 0;
+}
+
+static int do_patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	int err;
+	unsigned int *patch_addr = NULL;
+	unsigned long flags;
+	unsigned long text_poke_addr;
+	unsigned long kaddr = (unsigned long)addr;
+
+	/*
+	 * During early early boot patch_instruction is called
+	 * when text_poke_area is not ready, but we still need
+	 * to allow patching. We just do the plain old patching
+	 */
+	if (!this_cpu_read(text_poke_area))
+		return raw_patch_instruction(addr, instr);
+
+	local_irq_save(flags);
+
+	text_poke_addr = (unsigned long)__this_cpu_read(text_poke_area)->addr;
+	if (map_patch_area(addr, text_poke_addr)) {
+		err = -1;
+		goto out;
+	}
+
+	patch_addr = (unsigned int *)(text_poke_addr) +
+			((kaddr & ~PAGE_MASK) / sizeof(unsigned int));
+
+	__patch_instruction(addr, instr, patch_addr);
+
+	err = unmap_patch_area(text_poke_addr);
+	if (err)
+		pr_warn("failed to unmap %lx\n", text_poke_addr);
+
+out:
+	local_irq_restore(flags);
+
+	return err;
+}
+#else /* !CONFIG_STRICT_KERNEL_RWX */
+
+static int do_patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	return raw_patch_instruction(addr, instr);
+}
+
+#endif /* CONFIG_STRICT_KERNEL_RWX */
+
+int patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	/* Make sure we aren't patching a freed init section */
+	if (init_mem_is_free && init_section_contains(addr, 4)) {
+		pr_debug("Skipping init section patching addr: 0x%px\n", addr);
+		return 0;
+	}
+	return do_patch_instruction(addr, instr);
+}
+NOKPROBE_SYMBOL(patch_instruction);
+
+int patch_branch(unsigned int *addr, unsigned long target, int flags)
+{
+	return patch_instruction(addr, create_branch(addr, target, flags));
+}
+
+int patch_branch_site(s32 *site, unsigned long target, int flags)
+{
+	unsigned int *addr;
+
+	addr = (unsigned int *)((unsigned long)site + *site);
+	return patch_instruction(addr, create_branch(addr, target, flags));
+}
+
+int patch_instruction_site(s32 *site, unsigned int instr)
+{
+	unsigned int *addr;
+
+	addr = (unsigned int *)((unsigned long)site + *site);
+	return patch_instruction(addr, instr);
+}
+
+bool is_offset_in_branch_range(long offset)
+{
+	/*
+	 * Powerpc branch instruction is :
+	 *
+	 *  0         6                 30   31
+	 *  +---------+----------------+---+---+
+	 *  | opcode  |     LI         |AA |LK |
+	 *  +---------+----------------+---+---+
+	 *  Where AA = 0 and LK = 0
+	 *
+	 * LI is a signed 24 bits integer. The real branch offset is computed
+	 * by: imm32 = SignExtend(LI:'0b00', 32);
+	 *
+	 * So the maximum forward branch should be:
+	 *   (0x007fffff << 2) = 0x01fffffc =  0x1fffffc
+	 * The maximum backward branch should be:
+	 *   (0xff800000 << 2) = 0xfe000000 = -0x2000000
+	 */
+	return (offset >= -0x2000000 && offset <= 0x1fffffc && !(offset & 0x3));
+}
+
+bool is_offset_in_cond_branch_range(long offset)
+{
+	return offset >= -0x8000 && offset <= 0x7fff && !(offset & 0x3);
+}
+
+/*
+ * Helper to check if a given instruction is a conditional branch
+ * Derived from the conditional checks in analyse_instr()
+ */
+bool is_conditional_branch(unsigned int instr)
+{
+	unsigned int opcode = instr >> 26;
+
+	if (opcode == 16)       /* bc, bca, bcl, bcla */
+		return true;
+	if (opcode == 19) {
+		switch ((instr >> 1) & 0x3ff) {
+		case 16:        /* bclr, bclrl */
+		case 528:       /* bcctr, bcctrl */
+		case 560:       /* bctar, bctarl */
+			return true;
+		}
+	}
+	return false;
+}
+NOKPROBE_SYMBOL(is_conditional_branch);
+
+unsigned int create_branch(const unsigned int *addr,
+			   unsigned long target, int flags)
+{
+	unsigned int instruction;
+	long offset;
+
+	offset = target;
+	if (! (flags & BRANCH_ABSOLUTE))
+		offset = offset - (unsigned long)addr;
+
+	/* Check we can represent the target in the instruction format */
+	if (!is_offset_in_branch_range(offset))
+		return 0;
+
+	/* Mask out the flags and target, so they don't step on each other. */
+	instruction = 0x48000000 | (flags & 0x3) | (offset & 0x03FFFFFC);
+
+	return instruction;
+}
+
+unsigned int create_cond_branch(const unsigned int *addr,
+				unsigned long target, int flags)
+{
+	unsigned int instruction;
+	long offset;
+
+	offset = target;
+	if (! (flags & BRANCH_ABSOLUTE))
+		offset = offset - (unsigned long)addr;
+
+	/* Check we can represent the target in the instruction format */
+	if (!is_offset_in_cond_branch_range(offset))
+		return 0;
+
+	/* Mask out the flags and target, so they don't step on each other. */
+	instruction = 0x40000000 | (flags & 0x3FF0003) | (offset & 0xFFFC);
+
+	return instruction;
+}
+
+static unsigned int branch_opcode(unsigned int instr)
+{
+	return (instr >> 26) & 0x3F;
+}
+
+static int instr_is_branch_iform(unsigned int instr)
+{
+	return branch_opcode(instr) == 18;
+}
+
+static int instr_is_branch_bform(unsigned int instr)
+{
+	return branch_opcode(instr) == 16;
+}
+
+int instr_is_relative_branch(unsigned int instr)
+{
+	if (instr & BRANCH_ABSOLUTE)
+		return 0;
+
+	return instr_is_branch_iform(instr) || instr_is_branch_bform(instr);
+}
+
+int instr_is_relative_link_branch(unsigned int instr)
+{
+	return instr_is_relative_branch(instr) && (instr & BRANCH_SET_LINK);
+}
+
+static unsigned long branch_iform_target(const unsigned int *instr)
+{
+	signed long imm;
+
+	imm = *instr & 0x3FFFFFC;
+
+	/* If the top bit of the immediate value is set this is negative */
+	if (imm & 0x2000000)
+		imm -= 0x4000000;
+
+	if ((*instr & BRANCH_ABSOLUTE) == 0)
+		imm += (unsigned long)instr;
+
+	return (unsigned long)imm;
+}
+
+static unsigned long branch_bform_target(const unsigned int *instr)
+{
+	signed long imm;
+
+	imm = *instr & 0xFFFC;
+
+	/* If the top bit of the immediate value is set this is negative */
+	if (imm & 0x8000)
+		imm -= 0x10000;
+
+	if ((*instr & BRANCH_ABSOLUTE) == 0)
+		imm += (unsigned long)instr;
+
+	return (unsigned long)imm;
+}
+
+unsigned long branch_target(const unsigned int *instr)
+{
+	if (instr_is_branch_iform(*instr))
+		return branch_iform_target(instr);
+	else if (instr_is_branch_bform(*instr))
+		return branch_bform_target(instr);
+
+	return 0;
+}
+
+int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr)
+{
+	if (instr_is_branch_iform(*instr) || instr_is_branch_bform(*instr))
+		return branch_target(instr) == addr;
+
+	return 0;
+}
+
+unsigned int translate_branch(const unsigned int *dest, const unsigned int *src)
+{
+	unsigned long target;
+
+	target = branch_target(src);
+
+	if (instr_is_branch_iform(*src))
+		return create_branch(dest, target, *src);
+	else if (instr_is_branch_bform(*src))
+		return create_cond_branch(dest, target, *src);
+
+	return 0;
+}
+
+#ifdef CONFIG_PPC_BOOK3E_64
+void __patch_exception(int exc, unsigned long addr)
+{
+	extern unsigned int interrupt_base_book3e;
+	unsigned int *ibase = &interrupt_base_book3e;
+
+	/* Our exceptions vectors start with a NOP and -then- a branch
+	 * to deal with single stepping from userspace which stops on
+	 * the second instruction. Thus we need to patch the second
+	 * instruction of the exception, not the first one
+	 */
+
+	patch_branch(ibase + (exc / 4) + 1, addr, 0);
+}
+#endif
+
+#ifdef CONFIG_CODE_PATCHING_SELFTEST
+
+static void __init test_trampoline(void)
+{
+	asm ("nop;\n");
+}
+
+#define check(x)	\
+	if (!(x)) printk("code-patching: test failed at line %d\n", __LINE__);
+
+static void __init test_branch_iform(void)
+{
+	unsigned int instr;
+	unsigned long addr;
+
+	addr = (unsigned long)&instr;
+
+	/* The simplest case, branch to self, no flags */
+	check(instr_is_branch_iform(0x48000000));
+	/* All bits of target set, and flags */
+	check(instr_is_branch_iform(0x4bffffff));
+	/* High bit of opcode set, which is wrong */
+	check(!instr_is_branch_iform(0xcbffffff));
+	/* Middle bits of opcode set, which is wrong */
+	check(!instr_is_branch_iform(0x7bffffff));
+
+	/* Simplest case, branch to self with link */
+	check(instr_is_branch_iform(0x48000001));
+	/* All bits of targets set */
+	check(instr_is_branch_iform(0x4bfffffd));
+	/* Some bits of targets set */
+	check(instr_is_branch_iform(0x4bff00fd));
+	/* Must be a valid branch to start with */
+	check(!instr_is_branch_iform(0x7bfffffd));
+
+	/* Absolute branch to 0x100 */
+	instr = 0x48000103;
+	check(instr_is_branch_to_addr(&instr, 0x100));
+	/* Absolute branch to 0x420fc */
+	instr = 0x480420ff;
+	check(instr_is_branch_to_addr(&instr, 0x420fc));
+	/* Maximum positive relative branch, + 20MB - 4B */
+	instr = 0x49fffffc;
+	check(instr_is_branch_to_addr(&instr, addr + 0x1FFFFFC));
+	/* Smallest negative relative branch, - 4B */
+	instr = 0x4bfffffc;
+	check(instr_is_branch_to_addr(&instr, addr - 4));
+	/* Largest negative relative branch, - 32 MB */
+	instr = 0x4a000000;
+	check(instr_is_branch_to_addr(&instr, addr - 0x2000000));
+
+	/* Branch to self, with link */
+	instr = create_branch(&instr, addr, BRANCH_SET_LINK);
+	check(instr_is_branch_to_addr(&instr, addr));
+
+	/* Branch to self - 0x100, with link */
+	instr = create_branch(&instr, addr - 0x100, BRANCH_SET_LINK);
+	check(instr_is_branch_to_addr(&instr, addr - 0x100));
+
+	/* Branch to self + 0x100, no link */
+	instr = create_branch(&instr, addr + 0x100, 0);
+	check(instr_is_branch_to_addr(&instr, addr + 0x100));
+
+	/* Maximum relative negative offset, - 32 MB */
+	instr = create_branch(&instr, addr - 0x2000000, BRANCH_SET_LINK);
+	check(instr_is_branch_to_addr(&instr, addr - 0x2000000));
+
+	/* Out of range relative negative offset, - 32 MB + 4*/
+	instr = create_branch(&instr, addr - 0x2000004, BRANCH_SET_LINK);
+	check(instr == 0);
+
+	/* Out of range relative positive offset, + 32 MB */
+	instr = create_branch(&instr, addr + 0x2000000, BRANCH_SET_LINK);
+	check(instr == 0);
+
+	/* Unaligned target */
+	instr = create_branch(&instr, addr + 3, BRANCH_SET_LINK);
+	check(instr == 0);
+
+	/* Check flags are masked correctly */
+	instr = create_branch(&instr, addr, 0xFFFFFFFC);
+	check(instr_is_branch_to_addr(&instr, addr));
+	check(instr == 0x48000000);
+}
+
+static void __init test_create_function_call(void)
+{
+	unsigned int *iptr;
+	unsigned long dest;
+
+	/* Check we can create a function call */
+	iptr = (unsigned int *)ppc_function_entry(test_trampoline);
+	dest = ppc_function_entry(test_create_function_call);
+	patch_instruction(iptr, create_branch(iptr, dest, BRANCH_SET_LINK));
+	check(instr_is_branch_to_addr(iptr, dest));
+}
+
+static void __init test_branch_bform(void)
+{
+	unsigned long addr;
+	unsigned int *iptr, instr, flags;
+
+	iptr = &instr;
+	addr = (unsigned long)iptr;
+
+	/* The simplest case, branch to self, no flags */
+	check(instr_is_branch_bform(0x40000000));
+	/* All bits of target set, and flags */
+	check(instr_is_branch_bform(0x43ffffff));
+	/* High bit of opcode set, which is wrong */
+	check(!instr_is_branch_bform(0xc3ffffff));
+	/* Middle bits of opcode set, which is wrong */
+	check(!instr_is_branch_bform(0x7bffffff));
+
+	/* Absolute conditional branch to 0x100 */
+	instr = 0x43ff0103;
+	check(instr_is_branch_to_addr(&instr, 0x100));
+	/* Absolute conditional branch to 0x20fc */
+	instr = 0x43ff20ff;
+	check(instr_is_branch_to_addr(&instr, 0x20fc));
+	/* Maximum positive relative conditional branch, + 32 KB - 4B */
+	instr = 0x43ff7ffc;
+	check(instr_is_branch_to_addr(&instr, addr + 0x7FFC));
+	/* Smallest negative relative conditional branch, - 4B */
+	instr = 0x43fffffc;
+	check(instr_is_branch_to_addr(&instr, addr - 4));
+	/* Largest negative relative conditional branch, - 32 KB */
+	instr = 0x43ff8000;
+	check(instr_is_branch_to_addr(&instr, addr - 0x8000));
+
+	/* All condition code bits set & link */
+	flags = 0x3ff000 | BRANCH_SET_LINK;
+
+	/* Branch to self */
+	instr = create_cond_branch(iptr, addr, flags);
+	check(instr_is_branch_to_addr(&instr, addr));
+
+	/* Branch to self - 0x100 */
+	instr = create_cond_branch(iptr, addr - 0x100, flags);
+	check(instr_is_branch_to_addr(&instr, addr - 0x100));
+
+	/* Branch to self + 0x100 */
+	instr = create_cond_branch(iptr, addr + 0x100, flags);
+	check(instr_is_branch_to_addr(&instr, addr + 0x100));
+
+	/* Maximum relative negative offset, - 32 KB */
+	instr = create_cond_branch(iptr, addr - 0x8000, flags);
+	check(instr_is_branch_to_addr(&instr, addr - 0x8000));
+
+	/* Out of range relative negative offset, - 32 KB + 4*/
+	instr = create_cond_branch(iptr, addr - 0x8004, flags);
+	check(instr == 0);
+
+	/* Out of range relative positive offset, + 32 KB */
+	instr = create_cond_branch(iptr, addr + 0x8000, flags);
+	check(instr == 0);
+
+	/* Unaligned target */
+	instr = create_cond_branch(iptr, addr + 3, flags);
+	check(instr == 0);
+
+	/* Check flags are masked correctly */
+	instr = create_cond_branch(iptr, addr, 0xFFFFFFFC);
+	check(instr_is_branch_to_addr(&instr, addr));
+	check(instr == 0x43FF0000);
+}
+
+static void __init test_translate_branch(void)
+{
+	unsigned long addr;
+	unsigned int *p, *q;
+	void *buf;
+
+	buf = vmalloc(PAGE_ALIGN(0x2000000 + 1));
+	check(buf);
+	if (!buf)
+		return;
+
+	/* Simple case, branch to self moved a little */
+	p = buf;
+	addr = (unsigned long)p;
+	patch_branch(p, addr, 0);
+	check(instr_is_branch_to_addr(p, addr));
+	q = p + 1;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(q, addr));
+
+	/* Maximum negative case, move b . to addr + 32 MB */
+	p = buf;
+	addr = (unsigned long)p;
+	patch_branch(p, addr, 0);
+	q = buf + 0x2000000;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(p, addr));
+	check(instr_is_branch_to_addr(q, addr));
+	check(*q == 0x4a000000);
+
+	/* Maximum positive case, move x to x - 32 MB + 4 */
+	p = buf + 0x2000000;
+	addr = (unsigned long)p;
+	patch_branch(p, addr, 0);
+	q = buf + 4;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(p, addr));
+	check(instr_is_branch_to_addr(q, addr));
+	check(*q == 0x49fffffc);
+
+	/* Jump to x + 16 MB moved to x + 20 MB */
+	p = buf;
+	addr = 0x1000000 + (unsigned long)buf;
+	patch_branch(p, addr, BRANCH_SET_LINK);
+	q = buf + 0x1400000;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(p, addr));
+	check(instr_is_branch_to_addr(q, addr));
+
+	/* Jump to x + 16 MB moved to x - 16 MB + 4 */
+	p = buf + 0x1000000;
+	addr = 0x2000000 + (unsigned long)buf;
+	patch_branch(p, addr, 0);
+	q = buf + 4;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(p, addr));
+	check(instr_is_branch_to_addr(q, addr));
+
+
+	/* Conditional branch tests */
+
+	/* Simple case, branch to self moved a little */
+	p = buf;
+	addr = (unsigned long)p;
+	patch_instruction(p, create_cond_branch(p, addr, 0));
+	check(instr_is_branch_to_addr(p, addr));
+	q = p + 1;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(q, addr));
+
+	/* Maximum negative case, move b . to addr + 32 KB */
+	p = buf;
+	addr = (unsigned long)p;
+	patch_instruction(p, create_cond_branch(p, addr, 0xFFFFFFFC));
+	q = buf + 0x8000;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(p, addr));
+	check(instr_is_branch_to_addr(q, addr));
+	check(*q == 0x43ff8000);
+
+	/* Maximum positive case, move x to x - 32 KB + 4 */
+	p = buf + 0x8000;
+	addr = (unsigned long)p;
+	patch_instruction(p, create_cond_branch(p, addr, 0xFFFFFFFC));
+	q = buf + 4;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(p, addr));
+	check(instr_is_branch_to_addr(q, addr));
+	check(*q == 0x43ff7ffc);
+
+	/* Jump to x + 12 KB moved to x + 20 KB */
+	p = buf;
+	addr = 0x3000 + (unsigned long)buf;
+	patch_instruction(p, create_cond_branch(p, addr, BRANCH_SET_LINK));
+	q = buf + 0x5000;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(p, addr));
+	check(instr_is_branch_to_addr(q, addr));
+
+	/* Jump to x + 8 KB moved to x - 8 KB + 4 */
+	p = buf + 0x2000;
+	addr = 0x4000 + (unsigned long)buf;
+	patch_instruction(p, create_cond_branch(p, addr, 0));
+	q = buf + 4;
+	patch_instruction(q, translate_branch(q, p));
+	check(instr_is_branch_to_addr(p, addr));
+	check(instr_is_branch_to_addr(q, addr));
+
+	/* Free the buffer we were using */
+	vfree(buf);
+}
+
+static int __init test_code_patching(void)
+{
+	printk(KERN_DEBUG "Running code patching self-tests ...\n");
+
+	test_branch_iform();
+	test_branch_bform();
+	test_create_function_call();
+	test_translate_branch();
+
+	return 0;
+}
+late_initcall(test_code_patching);
+
+#endif /* CONFIG_CODE_PATCHING_SELFTEST */
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
new file mode 100644
index 000000000..ba66846fe
--- /dev/null
+++ b/arch/powerpc/lib/copy_32.S
@@ -0,0 +1,516 @@
+/*
+ * 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 <asm/processor.h>
+#include <asm/cache.h>
+#include <asm/errno.h>
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/code-patching-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;				\
+	EX_TABLE(8 ## n ## 0b,9 ## n ## 0b);	\
+	EX_TABLE(8 ## n ## 1b,9 ## n ## 0b);	\
+	EX_TABLE(8 ## n ## 2b,9 ## n ## 0b);	\
+	EX_TABLE(8 ## n ## 3b,9 ## n ## 0b);	\
+	EX_TABLE(8 ## n ## 4b,9 ## n ## 1b);	\
+	EX_TABLE(8 ## n ## 5b,9 ## n ## 1b);	\
+	EX_TABLE(8 ## n ## 6b,9 ## n ## 1b);	\
+	EX_TABLE(8 ## n ## 7b,9 ## n ## 1b)
+
+	.text
+	.stabs	"arch/powerpc/lib/",N_SO,0,0,0f
+	.stabs	"copy_32.S",N_SO,0,0,0f
+0:
+
+CACHELINE_BYTES = L1_CACHE_BYTES
+LG_CACHELINE_BYTES = L1_CACHE_SHIFT
+CACHELINE_MASK = (L1_CACHE_BYTES-1)
+
+_GLOBAL(memset16)
+	rlwinm.	r0 ,r5, 31, 1, 31
+	addi	r6, r3, -4
+	beq-	2f
+	rlwimi	r4 ,r4 ,16 ,0 ,15
+	mtctr	r0
+1:	stwu	r4, 4(r6)
+	bdnz	1b
+2:	andi.	r0, r5, 1
+	beqlr
+	sth	r4, 4(r6)
+	blr
+EXPORT_SYMBOL(memset16)
+
+/*
+ * Use dcbz on the complete cache lines in the destination
+ * to set them to zero.  This requires that the destination
+ * area is cacheable.  -- paulus
+ *
+ * During early init, cache might not be active yet, so dcbz cannot be used.
+ * We therefore skip the optimised bloc that uses dcbz. This jump is
+ * replaced by a nop once cache is active. This is done in machine_init()
+ */
+_GLOBAL(memset)
+	cmplwi	0,r5,4
+	blt	7f
+
+	rlwimi	r4,r4,8,16,23
+	rlwimi	r4,r4,16,0,15
+
+	stw	r4,0(r3)
+	beqlr
+	andi.	r0,r3,3
+	add	r5,r0,r5
+	subf	r6,r0,r3
+	cmplwi	0,r4,0
+	/*
+	 * Skip optimised bloc until cache is enabled. Will be replaced
+	 * by 'bne' during boot to use normal procedure if r4 is not zero
+	 */
+5:	b	2f
+	patch_site	5b, patch__memset_nocache
+
+	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
+10:	dcbz	r7,r6
+	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
+	beqlr
+	mtctr	r5
+	addi	r6,r6,3
+8:	stbu	r4,1(r6)
+	bdnz	8b
+	blr
+
+7:	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+	addi	r6,r3,-1
+9:	stbu	r4,1(r6)
+	bdnz	9b
+	blr
+EXPORT_SYMBOL(memset)
+
+/*
+ * 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.
+ *
+ * During early init, cache might not be active yet, so dcbz cannot be used.
+ * We therefore jump to generic_memcpy which doesn't use dcbz. This jump is
+ * replaced by a nop once cache is active. This is done in machine_init()
+ */
+_GLOBAL(memmove)
+	cmplw	0,r3,r4
+	bgt	backwards_memcpy
+	/* fall through */
+
+_GLOBAL(memcpy)
+1:	b	generic_memcpy
+	patch_site	1b, patch__memcpy_nocache
+
+	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	generic_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 */
+	addi	r4,r4,1
+	addi	r6,r6,1
+	stb	r9,3(r6)
+	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:
+	dcbz	r11,r6
+	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
+	addi	r4,r4,3
+	addi	r6,r6,3
+40:	lbzu	r0,1(r4)
+	stbu	r0,1(r6)
+	bdnz	40b
+65:	blr
+EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL(memmove)
+
+generic_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
+
+	EX_TABLE(70b,100f)
+	EX_TABLE(71b,101f)
+	EX_TABLE(72b,102f)
+	EX_TABLE(73b,103f)
+
+58:	srwi.	r0,r5,LG_CACHELINE_BYTES /* # complete cachelines */
+	clrlwi	r5,r5,32-LG_CACHELINE_BYTES
+	li	r11,4
+	beq	63f
+
+	/* 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
+	EX_TABLE(54b,105f)
+/* 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
+
+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
+120:	blr
+
+	EX_TABLE(30b,108b)
+	EX_TABLE(31b,109b)
+	EX_TABLE(40b,110b)
+	EX_TABLE(41b,111b)
+	EX_TABLE(130b,132b)
+	EX_TABLE(131b,120b)
+
+EXPORT_SYMBOL(__copy_tofrom_user)
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
new file mode 100644
index 000000000..694390357
--- /dev/null
+++ b/arch/powerpc/lib/copypage_64.S
@@ -0,0 +1,117 @@
+/*
+ * Copyright (C) 2008 Mark Nelson, 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/page.h>
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/export.h>
+#include <asm/feature-fixups.h>
+
+        .section        ".toc","aw"
+PPC64_CACHES:
+        .tc             ppc64_caches[TC],ppc64_caches
+        .section        ".text"
+
+_GLOBAL_TOC(copy_page)
+BEGIN_FTR_SECTION
+	lis	r5,PAGE_SIZE@h
+FTR_SECTION_ELSE
+#ifdef CONFIG_PPC_BOOK3S_64
+	b	copypage_power7
+#endif
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
+	ori	r5,r5,PAGE_SIZE@l
+BEGIN_FTR_SECTION
+	ld      r10,PPC64_CACHES@toc(r2)
+	lwz	r11,DCACHEL1LOGBLOCKSIZE(r10)	/* log2 of cache block size */
+	lwz     r12,DCACHEL1BLOCKSIZE(r10)	/* get cache block size */
+	li	r9,0
+	srd	r8,r5,r11
+
+	mtctr	r8
+.Lsetup:
+	dcbt	r9,r4
+	dcbz	r9,r3
+	add	r9,r9,r12
+	bdnz	.Lsetup
+END_FTR_SECTION_IFSET(CPU_FTR_CP_USE_DCBTZ)
+	addi	r3,r3,-8
+	srdi    r8,r5,7		/* page is copied in 128 byte strides */
+	addi	r8,r8,-1	/* one stride copied outside loop */
+
+	mtctr	r8
+
+	ld	r5,0(r4)
+	ld	r6,8(r4)
+	ld	r7,16(r4)
+	ldu	r8,24(r4)
+1:	std	r5,8(r3)
+	std	r6,16(r3)
+	ld	r9,8(r4)
+	ld	r10,16(r4)
+	std	r7,24(r3)
+	std	r8,32(r3)
+	ld	r11,24(r4)
+	ld	r12,32(r4)
+	std	r9,40(r3)
+	std	r10,48(r3)
+	ld	r5,40(r4)
+	ld	r6,48(r4)
+	std	r11,56(r3)
+	std	r12,64(r3)
+	ld	r7,56(r4)
+	ld	r8,64(r4)
+	std	r5,72(r3)
+	std	r6,80(r3)
+	ld	r9,72(r4)
+	ld	r10,80(r4)
+	std	r7,88(r3)
+	std	r8,96(r3)
+	ld	r11,88(r4)
+	ld	r12,96(r4)
+	std	r9,104(r3)
+	std	r10,112(r3)
+	ld	r5,104(r4)
+	ld	r6,112(r4)
+	std	r11,120(r3)
+	stdu	r12,128(r3)
+	ld	r7,120(r4)
+	ldu	r8,128(r4)
+	bdnz	1b
+
+	std	r5,8(r3)
+	std	r6,16(r3)
+	ld	r9,8(r4)
+	ld	r10,16(r4)
+	std	r7,24(r3)
+	std	r8,32(r3)
+	ld	r11,24(r4)
+	ld	r12,32(r4)
+	std	r9,40(r3)
+	std	r10,48(r3)
+	ld	r5,40(r4)
+	ld	r6,48(r4)
+	std	r11,56(r3)
+	std	r12,64(r3)
+	ld	r7,56(r4)
+	ld	r8,64(r4)
+	std	r5,72(r3)
+	std	r6,80(r3)
+	ld	r9,72(r4)
+	ld	r10,80(r4)
+	std	r7,88(r3)
+	std	r8,96(r3)
+	ld	r11,88(r4)
+	ld	r12,96(r4)
+	std	r9,104(r3)
+	std	r10,112(r3)
+	std	r11,120(r3)
+	std	r12,128(r3)
+	blr
+EXPORT_SYMBOL(copy_page)
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
new file mode 100644
index 000000000..e38f956f7
--- /dev/null
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -0,0 +1,165 @@
+/*
+ * 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.
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/page.h>
+#include <asm/ppc_asm.h>
+
+_GLOBAL(copypage_power7)
+	/*
+	 * We prefetch both the source and destination using enhanced touch
+	 * instructions. We use a stream ID of 0 for the load side and
+	 * 1 for the store side. Since source and destination are page
+	 * aligned we don't need to clear the bottom 7 bits of either
+	 * address.
+	 */
+	ori	r9,r3,1		/* stream=1 => to */
+
+#ifdef CONFIG_PPC_64K_PAGES
+	lis	r7,0x0E01	/* depth=7
+				 * units/cachelines=512 */
+#else
+	lis	r7,0x0E00	/* depth=7 */
+	ori	r7,r7,0x1000	/* units/cachelines=32 */
+#endif
+	ori	r10,r7,1	/* stream=1 */
+
+	lis	r8,0x8000	/* GO=1 */
+	clrldi	r8,r8,32
+
+	/* setup read stream 0  */
+	dcbt	0,r4,0b01000  	/* addr from */
+	dcbt	0,r7,0b01010   /* length and depth from */
+	/* setup write stream 1 */
+	dcbtst	0,r9,0b01000   /* addr to */
+	dcbtst	0,r10,0b01010  /* length and depth to */
+	eieio
+	dcbt	0,r8,0b01010	/* all streams GO */
+
+#ifdef CONFIG_ALTIVEC
+	mflr	r0
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r0,16(r1)
+	stdu	r1,-STACKFRAMESIZE(r1)
+	bl	enter_vmx_ops
+	cmpwi	r3,0
+	ld	r0,STACKFRAMESIZE+16(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
+	mtlr	r0
+
+	li	r0,(PAGE_SIZE/128)
+	mtctr	r0
+
+	beq	.Lnonvmx_copy
+
+	addi	r1,r1,STACKFRAMESIZE
+
+	li	r6,16
+	li	r7,32
+	li	r8,48
+	li	r9,64
+	li	r10,80
+	li	r11,96
+	li	r12,112
+
+	.align	5
+1:	lvx	v7,0,r4
+	lvx	v6,r4,r6
+	lvx	v5,r4,r7
+	lvx	v4,r4,r8
+	lvx	v3,r4,r9
+	lvx	v2,r4,r10
+	lvx	v1,r4,r11
+	lvx	v0,r4,r12
+	addi	r4,r4,128
+	stvx	v7,0,r3
+	stvx	v6,r3,r6
+	stvx	v5,r3,r7
+	stvx	v4,r3,r8
+	stvx	v3,r3,r9
+	stvx	v2,r3,r10
+	stvx	v1,r3,r11
+	stvx	v0,r3,r12
+	addi	r3,r3,128
+	bdnz	1b
+
+	b	exit_vmx_ops		/* tail call optimise */
+
+#else
+	li	r0,(PAGE_SIZE/128)
+	mtctr	r0
+
+	stdu	r1,-STACKFRAMESIZE(r1)
+#endif
+
+.Lnonvmx_copy:
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+
+1:	ld	r0,0(r4)
+	ld	r5,8(r4)
+	ld	r6,16(r4)
+	ld	r7,24(r4)
+	ld	r8,32(r4)
+	ld	r9,40(r4)
+	ld	r10,48(r4)
+	ld	r11,56(r4)
+	ld	r12,64(r4)
+	ld	r14,72(r4)
+	ld	r15,80(r4)
+	ld	r16,88(r4)
+	ld	r17,96(r4)
+	ld	r18,104(r4)
+	ld	r19,112(r4)
+	ld	r20,120(r4)
+	addi	r4,r4,128
+	std	r0,0(r3)
+	std	r5,8(r3)
+	std	r6,16(r3)
+	std	r7,24(r3)
+	std	r8,32(r3)
+	std	r9,40(r3)
+	std	r10,48(r3)
+	std	r11,56(r3)
+	std	r12,64(r3)
+	std	r14,72(r3)
+	std	r15,80(r3)
+	std	r16,88(r3)
+	std	r17,96(r3)
+	std	r18,104(r3)
+	std	r19,112(r3)
+	std	r20,120(r3)
+	addi	r3,r3,128
+	bdnz	1b
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+	blr
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
new file mode 100644
index 000000000..96c514bee
--- /dev/null
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -0,0 +1,568 @@
+/*
+ * 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>
+#include <asm/export.h>
+#include <asm/asm-compat.h>
+#include <asm/feature-fixups.h>
+
+#ifndef SELFTEST_CASE
+/* 0 == most CPUs, 1 == POWER6, 2 == Cell */
+#define SELFTEST_CASE	0
+#endif
+
+#ifdef __BIG_ENDIAN__
+#define sLd sld		/* Shift towards low-numbered address. */
+#define sHd srd		/* Shift towards high-numbered address. */
+#else
+#define sLd srd		/* Shift towards low-numbered address. */
+#define sHd sld		/* Shift towards high-numbered address. */
+#endif
+
+/*
+ * These macros are used to generate exception table entries.
+ * The exception handlers below use the original arguments
+ * (stored on the stack) and the point where we're up to in
+ * the destination buffer, i.e. the address of the first
+ * unmodified byte.  Generally r3 points into the destination
+ * buffer, but the first unmodified byte is at a variable
+ * offset from r3.  In the code below, the symbol r3_offset
+ * is set to indicate the current offset at each point in
+ * the code.  This offset is then used as a negative offset
+ * from the exception handler code, and those instructions
+ * before the exception handlers are addi instructions that
+ * adjust r3 to point to the correct place.
+ */
+	.macro	lex		/* exception handler for load */
+100:	EX_TABLE(100b, .Lld_exc - r3_offset)
+	.endm
+
+	.macro	stex		/* exception handler for store */
+100:	EX_TABLE(100b, .Lst_exc - r3_offset)
+	.endm
+
+	.align	7
+_GLOBAL_TOC(__copy_tofrom_user)
+#ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FTR_SECTION
+	nop
+FTR_SECTION_ELSE
+	b	__copy_tofrom_user_power7
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
+#endif
+_GLOBAL(__copy_tofrom_user_base)
+	/* first check for a 4kB copy on a 4kB 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_4K
+	andi.	r6,r6,7
+	PPC_MTOCRF(0x01,r5)
+	blt	cr1,.Lshort_copy
+/* Below we want to nop out the bne if we're on a CPU that has the
+ * CPU_FTR_UNALIGNED_LD_STD bit set and the CPU_FTR_CP_USE_DCBTZ bit
+ * cleared.
+ * At the time of writing the only CPU that has this combination of bits
+ * set is Power6.
+ */
+test_feature = (SELFTEST_CASE == 1)
+BEGIN_FTR_SECTION
+	nop
+FTR_SECTION_ELSE
+	bne	.Ldst_unaligned
+ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
+		    CPU_FTR_UNALIGNED_LD_STD)
+.Ldst_aligned:
+	addi	r3,r3,-16
+r3_offset = 16
+test_feature = (SELFTEST_CASE == 0)
+BEGIN_FTR_SECTION
+	andi.	r0,r4,7
+	bne	.Lsrc_unaligned
+END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
+	blt	cr1,.Ldo_tail		/* if < 16 bytes to copy */
+	srdi	r0,r5,5
+	cmpdi	cr1,r0,0
+lex;	ld	r7,0(r4)
+lex;	ld	r6,8(r4)
+	addi	r4,r4,16
+	mtctr	r0
+	andi.	r0,r5,0x10
+	beq	22f
+	addi	r3,r3,16
+r3_offset = 0
+	addi	r4,r4,-16
+	mr	r9,r7
+	mr	r8,r6
+	beq	cr1,72f
+21:
+lex;	ld	r7,16(r4)
+lex;	ld	r6,24(r4)
+	addi	r4,r4,32
+stex;	std	r9,0(r3)
+r3_offset = 8
+stex;	std	r8,8(r3)
+r3_offset = 16
+22:
+lex;	ld	r9,0(r4)
+lex;	ld	r8,8(r4)
+stex;	std	r7,16(r3)
+r3_offset = 24
+stex;	std	r6,24(r3)
+	addi	r3,r3,32
+r3_offset = 0
+	bdnz	21b
+72:
+stex;	std	r9,0(r3)
+r3_offset = 8
+stex;	std	r8,8(r3)
+r3_offset = 16
+	andi.	r5,r5,0xf
+	beq+	3f
+	addi	r4,r4,16
+.Ldo_tail:
+	addi	r3,r3,16
+r3_offset = 0
+	bf	cr7*4+0,246f
+lex;	ld	r9,0(r4)
+	addi	r4,r4,8
+stex;	std	r9,0(r3)
+	addi	r3,r3,8
+246:	bf	cr7*4+1,1f
+lex;	lwz	r9,0(r4)
+	addi	r4,r4,4
+stex;	stw	r9,0(r3)
+	addi	r3,r3,4
+1:	bf	cr7*4+2,2f
+lex;	lhz	r9,0(r4)
+	addi	r4,r4,2
+stex;	sth	r9,0(r3)
+	addi	r3,r3,2
+2:	bf	cr7*4+3,3f
+lex;	lbz	r9,0(r4)
+stex;	stb	r9,0(r3)
+3:	li	r3,0
+	blr
+
+.Lsrc_unaligned:
+r3_offset = 16
+	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
+
+lex;	ld	r9,0(r4)	/* 3+2n loads, 2+2n stores */
+lex;	ld	r0,8(r4)
+	sLd	r6,r9,r10
+lex;	ldu	r9,16(r4)
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
+	or	r7,r7,r6
+	blt	cr6,79f
+lex;	ld	r0,8(r4)
+	b	2f
+
+28:
+lex;	ld	r0,0(r4)	/* 4+2n loads, 3+2n stores */
+lex;	ldu	r9,8(r4)
+	sLd	r8,r0,r10
+	addi	r3,r3,-8
+r3_offset = 24
+	blt	cr6,5f
+lex;	ld	r0,8(r4)
+	sHd	r12,r9,r11
+	sLd	r6,r9,r10
+lex;	ldu	r9,16(r4)
+	or	r12,r8,r12
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
+	addi	r3,r3,16
+r3_offset = 8
+	beq	cr6,78f
+
+1:	or	r7,r7,r6
+lex;	ld	r0,8(r4)
+stex;	std	r12,8(r3)
+r3_offset = 16
+2:	sHd	r12,r9,r11
+	sLd	r6,r9,r10
+lex;	ldu	r9,16(r4)
+	or	r12,r8,r12
+stex;	stdu	r7,16(r3)
+r3_offset = 8
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
+	bdnz	1b
+
+78:
+stex;	std	r12,8(r3)
+r3_offset = 16
+	or	r7,r7,r6
+79:
+stex;	std	r7,16(r3)
+r3_offset = 24
+5:	sHd	r12,r9,r11
+	or	r12,r8,r12
+stex;	std	r12,24(r3)
+r3_offset = 32
+	bne	6f
+	li	r3,0
+	blr
+6:	cmpwi	cr1,r5,8
+	addi	r3,r3,32
+r3_offset = 0
+	sLd	r9,r9,r10
+	ble	cr1,7f
+lex;	ld	r0,8(r4)
+	sHd	r7,r0,r11
+	or	r9,r7,r9
+7:
+	bf	cr7*4+1,1f
+#ifdef __BIG_ENDIAN__
+	rotldi	r9,r9,32
+#endif
+stex;	stw	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,32
+#endif
+	addi	r3,r3,4
+1:	bf	cr7*4+2,2f
+#ifdef __BIG_ENDIAN__
+	rotldi	r9,r9,16
+#endif
+stex;	sth	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,16
+#endif
+	addi	r3,r3,2
+2:	bf	cr7*4+3,3f
+#ifdef __BIG_ENDIAN__
+	rotldi	r9,r9,8
+#endif
+stex;	stb	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,8
+#endif
+3:	li	r3,0
+	blr
+
+.Ldst_unaligned:
+r3_offset = 0
+	PPC_MTOCRF(0x01,r6)		/* put #bytes to 8B bdry into cr7 */
+	subf	r5,r6,r5
+	li	r7,0
+	cmpldi	cr1,r5,16
+	bf	cr7*4+3,1f
+100:	EX_TABLE(100b, .Lld_exc_r7)
+	lbz	r0,0(r4)
+100:	EX_TABLE(100b, .Lst_exc_r7)
+	stb	r0,0(r3)
+	addi	r7,r7,1
+1:	bf	cr7*4+2,2f
+100:	EX_TABLE(100b, .Lld_exc_r7)
+	lhzx	r0,r7,r4
+100:	EX_TABLE(100b, .Lst_exc_r7)
+	sthx	r0,r7,r3
+	addi	r7,r7,2
+2:	bf	cr7*4+1,3f
+100:	EX_TABLE(100b, .Lld_exc_r7)
+	lwzx	r0,r7,r4
+100:	EX_TABLE(100b, .Lst_exc_r7)
+	stwx	r0,r7,r3
+3:	PPC_MTOCRF(0x01,r5)
+	add	r4,r6,r4
+	add	r3,r6,r3
+	b	.Ldst_aligned
+
+.Lshort_copy:
+r3_offset = 0
+	bf	cr7*4+0,1f
+lex;	lwz	r0,0(r4)
+lex;	lwz	r9,4(r4)
+	addi	r4,r4,8
+stex;	stw	r0,0(r3)
+stex;	stw	r9,4(r3)
+	addi	r3,r3,8
+1:	bf	cr7*4+1,2f
+lex;	lwz	r0,0(r4)
+	addi	r4,r4,4
+stex;	stw	r0,0(r3)
+	addi	r3,r3,4
+2:	bf	cr7*4+2,3f
+lex;	lhz	r0,0(r4)
+	addi	r4,r4,2
+stex;	sth	r0,0(r3)
+	addi	r3,r3,2
+3:	bf	cr7*4+3,4f
+lex;	lbz	r0,0(r4)
+stex;	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
+ * Note that the number of bytes of instructions for adjusting r3 needs
+ * to equal the amount of the adjustment, due to the trick of using
+ * .Lld_exc - r3_offset as the handler address.
+ */
+
+.Lld_exc_r7:
+	add	r3,r3,r7
+	b	.Lld_exc
+
+	/* adjust by 24 */
+	addi	r3,r3,8
+	nop
+	/* adjust by 16 */
+	addi	r3,r3,8
+	nop
+	/* adjust by 8 */
+	addi	r3,r3,8
+	nop
+
+/*
+ * Here we have had a fault on a load and r3 points to the first
+ * unmodified byte of the destination.  We use the original arguments
+ * and r3 to work out how much wasn't copied.  Since we load some
+ * distance ahead of the stores, we continue copying byte-by-byte until
+ * we hit the load fault again in order to copy as much as possible.
+ */
+.Lld_exc:
+	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
+r3_offset = 0
+100:	EX_TABLE(100b, .Ldone)
+43:	lbz	r0,0(r4)
+	addi	r4,r4,1
+stex;	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, amount remaining is in ctr.
+ */
+.Ldone:
+	mfctr	r3
+	blr
+
+/*
+ * exception handlers for stores: we need to work out how many bytes
+ * weren't copied, and we may need to copy some more.
+ * Note that the number of bytes of instructions for adjusting r3 needs
+ * to equal the amount of the adjustment, due to the trick of using
+ * .Lst_exc - r3_offset as the handler address.
+ */
+.Lst_exc_r7:
+	add	r3,r3,r7
+	b	.Lst_exc
+
+	/* adjust by 24 */
+	addi	r3,r3,8
+	nop
+	/* adjust by 16 */
+	addi	r3,r3,8
+	nop
+	/* adjust by 8 */
+	addi	r3,r3,4
+	/* adjust by 4 */
+	addi	r3,r3,4
+.Lst_exc:
+	ld	r6,-24(r1)	/* original destination pointer */
+	ld	r4,-16(r1)	/* original source pointer */
+	ld	r5,-8(r1)	/* original number of bytes */
+	add	r7,r6,r5
+	/*
+	 * If the destination pointer isn't 8-byte aligned,
+	 * we may have got the exception as a result of a
+	 * store that overlapped a page boundary, so we may be
+	 * able to copy a few more bytes.
+	 */
+17:	andi.	r0,r3,7
+	beq	19f
+	subf	r8,r6,r3	/* #bytes copied */
+100:	EX_TABLE(100b,19f)
+	lbzx	r0,r8,r4
+100:	EX_TABLE(100b,19f)
+	stb	r0,0(r3)
+	addi	r3,r3,1
+	cmpld	r3,r7
+	blt	17b
+19:	subf	r3,r3,r7	/* #bytes not copied in r3 */
+	blr
+
+/*
+ * 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).
+ */
+	.macro	exc
+100:	EX_TABLE(100b, .Labort)
+	.endm
+.Lcopy_page_4K:
+	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
+exc;	ld	r22,640(4)
+exc;	ld	r21,512(4)
+exc;	ld	r20,384(4)
+exc;	ld	r11,256(4)
+exc;	ld	r9,128(4)
+exc;	ld	r7,0(4)
+exc;	ld	r25,648(4)
+exc;	ld	r24,520(4)
+exc;	ld	r23,392(4)
+exc;	ld	r10,264(4)
+exc;	ld	r8,136(4)
+exc;	ldu	r6,8(4)
+	cmpwi	r5,24
+1:
+exc;	std	r22,648(3)
+exc;	std	r21,520(3)
+exc;	std	r20,392(3)
+exc;	std	r11,264(3)
+exc;	std	r9,136(3)
+exc;	std	r7,8(3)
+exc;	ld	r28,648(4)
+exc;	ld	r27,520(4)
+exc;	ld	r26,392(4)
+exc;	ld	r31,264(4)
+exc;	ld	r30,136(4)
+exc;	ld	r29,8(4)
+exc;	std	r25,656(3)
+exc;	std	r24,528(3)
+exc;	std	r23,400(3)
+exc;	std	r10,272(3)
+exc;	std	r8,144(3)
+exc;	std	r6,16(3)
+exc;	ld	r22,656(4)
+exc;	ld	r21,528(4)
+exc;	ld	r20,400(4)
+exc;	ld	r11,272(4)
+exc;	ld	r9,144(4)
+exc;	ld	r7,16(4)
+exc;	std	r28,664(3)
+exc;	std	r27,536(3)
+exc;	std	r26,408(3)
+exc;	std	r31,280(3)
+exc;	std	r30,152(3)
+exc;	stdu	r29,24(3)
+exc;	ld	r25,664(4)
+exc;	ld	r24,536(4)
+exc;	ld	r23,408(4)
+exc;	ld	r10,280(4)
+exc;	ld	r8,152(4)
+exc;	ldu	r6,24(4)
+	bdnz	1b
+exc;	std	r22,648(3)
+exc;	std	r21,520(3)
+exc;	std	r20,392(3)
+exc;	std	r11,264(3)
+exc;	std	r9,136(3)
+exc;	std	r7,8(3)
+	addi	r4,r4,640
+	addi	r3,r3,648
+	bge	0b
+	mtctr	r5
+exc;	ld	r7,0(4)
+exc;	ld	r8,8(4)
+exc;	ldu	r9,16(4)
+3:
+exc;	ld	r10,8(4)
+exc;	std	r7,8(3)
+exc;	ld	r7,16(4)
+exc;	std	r8,16(3)
+exc;	ld	r8,24(4)
+exc;	std	r9,24(3)
+exc;	ldu	r9,32(4)
+exc;	stdu	r10,32(3)
+	bdnz	3b
+4:
+exc;	ld	r10,8(4)
+exc;	std	r7,8(3)
+exc;	std	r8,16(3)
+exc;	std	r9,24(3)
+exc;	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
+ */
+.Labort:
+	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
+EXPORT_SYMBOL(__copy_tofrom_user)
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
new file mode 100644
index 000000000..1a1fe180a
--- /dev/null
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -0,0 +1,707 @@
+/*
+ * 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.
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2011
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/ppc_asm.h>
+
+#ifndef SELFTEST_CASE
+/* 0 == don't use VMX, 1 == use VMX */
+#define SELFTEST_CASE	0
+#endif
+
+#ifdef __BIG_ENDIAN__
+#define LVS(VRT,RA,RB)		lvsl	VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRA,VRB,VRC
+#else
+#define LVS(VRT,RA,RB)		lvsr	VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRB,VRA,VRC
+#endif
+
+	.macro err1
+100:
+	EX_TABLE(100b,.Ldo_err1)
+	.endm
+
+	.macro err2
+200:
+	EX_TABLE(200b,.Ldo_err2)
+	.endm
+
+#ifdef CONFIG_ALTIVEC
+	.macro err3
+300:
+	EX_TABLE(300b,.Ldo_err3)
+	.endm
+
+	.macro err4
+400:
+	EX_TABLE(400b,.Ldo_err4)
+	.endm
+
+
+.Ldo_err4:
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
+.Ldo_err3:
+	bl	exit_vmx_usercopy
+	ld	r0,STACKFRAMESIZE+16(r1)
+	mtlr	r0
+	b	.Lexit
+#endif /* CONFIG_ALTIVEC */
+
+.Ldo_err2:
+	ld	r22,STK_REG(R22)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
+.Lexit:
+	addi	r1,r1,STACKFRAMESIZE
+.Ldo_err1:
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	ld	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	ld	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
+	b	__copy_tofrom_user_base
+
+
+_GLOBAL(__copy_tofrom_user_power7)
+	cmpldi	r5,16
+	cmpldi	cr1,r5,3328
+
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
+
+	blt	.Lshort_copy
+
+#ifdef CONFIG_ALTIVEC
+test_feature = SELFTEST_CASE
+BEGIN_FTR_SECTION
+	bgt	cr1,.Lvmx_copy
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+
+.Lnonvmx_copy:
+	/* Get the source 8B aligned */
+	neg	r6,r4
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	bf	cr7*4+3,1f
+err1;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err1;	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	sub	r5,r5,r6
+	cmpldi	r5,128
+	blt	5f
+
+	mflr	r0
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
+	std	r0,STACKFRAMESIZE+16(r1)
+
+	srdi	r6,r5,7
+	mtctr	r6
+
+	/* Now do cacheline (128B) sized loads and stores. */
+	.align	5
+4:
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r7,16(r4)
+err2;	ld	r8,24(r4)
+err2;	ld	r9,32(r4)
+err2;	ld	r10,40(r4)
+err2;	ld	r11,48(r4)
+err2;	ld	r12,56(r4)
+err2;	ld	r14,64(r4)
+err2;	ld	r15,72(r4)
+err2;	ld	r16,80(r4)
+err2;	ld	r17,88(r4)
+err2;	ld	r18,96(r4)
+err2;	ld	r19,104(r4)
+err2;	ld	r20,112(r4)
+err2;	ld	r21,120(r4)
+	addi	r4,r4,128
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r7,16(r3)
+err2;	std	r8,24(r3)
+err2;	std	r9,32(r3)
+err2;	std	r10,40(r3)
+err2;	std	r11,48(r3)
+err2;	std	r12,56(r3)
+err2;	std	r14,64(r3)
+err2;	std	r15,72(r3)
+err2;	std	r16,80(r3)
+err2;	std	r17,88(r3)
+err2;	std	r18,96(r3)
+err2;	std	r19,104(r3)
+err2;	std	r20,112(r3)
+err2;	std	r21,120(r3)
+	addi	r3,r3,128
+	bdnz	4b
+
+	clrldi	r5,r5,(64-7)
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	/* Up to 127B to go */
+5:	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+6:	bf	cr7*4+1,7f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+err1;	ld	r7,16(r4)
+err1;	ld	r8,24(r4)
+err1;	ld	r9,32(r4)
+err1;	ld	r10,40(r4)
+err1;	ld	r11,48(r4)
+err1;	ld	r12,56(r4)
+	addi	r4,r4,64
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+err1;	std	r7,16(r3)
+err1;	std	r8,24(r3)
+err1;	std	r9,32(r3)
+err1;	std	r10,40(r3)
+err1;	std	r11,48(r3)
+err1;	std	r12,56(r3)
+	addi	r3,r3,64
+
+	/* Up to 63B to go */
+7:	bf	cr7*4+2,8f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+err1;	ld	r7,16(r4)
+err1;	ld	r8,24(r4)
+	addi	r4,r4,32
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+err1;	std	r7,16(r3)
+err1;	std	r8,24(r3)
+	addi	r3,r3,32
+
+	/* Up to 31B to go */
+8:	bf	cr7*4+3,9f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+	addi	r4,r4,16
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+	addi	r3,r3,16
+
+9:	clrldi	r5,r5,(64-4)
+
+	/* Up to 15B to go */
+.Lshort_copy:
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+err1;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+err1;	lwz	r6,4(r4)
+	addi	r4,r4,8
+err1;	stw	r0,0(r3)
+err1;	stw	r6,4(r3)
+	addi	r3,r3,8
+
+12:	bf	cr7*4+1,13f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+13:	bf	cr7*4+2,14f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+14:	bf	cr7*4+3,15f
+err1;	lbz	r0,0(r4)
+err1;	stb	r0,0(r3)
+
+15:	li	r3,0
+	blr
+
+.Lunwind_stack_nonvmx_copy:
+	addi	r1,r1,STACKFRAMESIZE
+	b	.Lnonvmx_copy
+
+.Lvmx_copy:
+#ifdef CONFIG_ALTIVEC
+	mflr	r0
+	std	r0,16(r1)
+	stdu	r1,-STACKFRAMESIZE(r1)
+	bl	enter_vmx_usercopy
+	cmpwi	cr1,r3,0
+	ld	r0,STACKFRAMESIZE+16(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
+	ld	r5,STK_REG(R29)(r1)
+	mtlr	r0
+
+	/*
+	 * We prefetch both the source and destination using enhanced touch
+	 * instructions. We use a stream ID of 0 for the load side and
+	 * 1 for the store side.
+	 */
+	clrrdi	r6,r4,7
+	clrrdi	r9,r3,7
+	ori	r9,r9,1		/* stream=1 */
+
+	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
+	cmpldi	r7,0x3FF
+	ble	1f
+	li	r7,0x3FF
+1:	lis	r0,0x0E00	/* depth=7 */
+	sldi	r7,r7,7
+	or	r7,r7,r0
+	ori	r10,r7,1	/* stream=1 */
+
+	lis	r8,0x8000	/* GO=1 */
+	clrldi	r8,r8,32
+
+	/* setup read stream 0 */
+	dcbt	0,r6,0b01000   /* addr from */
+	dcbt	0,r7,0b01010   /* length and depth from */
+	/* setup write stream 1 */
+	dcbtst	0,r9,0b01000   /* addr to */
+	dcbtst	0,r10,0b01010  /* length and depth to */
+	eieio
+	dcbt	0,r8,0b01010	/* all streams GO */
+
+	beq	cr1,.Lunwind_stack_nonvmx_copy
+
+	/*
+	 * If source and destination are not relatively aligned we use a
+	 * slower permute loop.
+	 */
+	xor	r6,r4,r3
+	rldicl.	r6,r6,0,(64-4)
+	bne	.Lvmx_unaligned_copy
+
+	/* Get the destination 16B aligned */
+	neg	r6,r3
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-4)
+
+	bf	cr7*4+3,1f
+err3;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err3;	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+err3;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err3;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+err3;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err3;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	bf	cr7*4+0,4f
+err3;	ld	r0,0(r4)
+	addi	r4,r4,8
+err3;	std	r0,0(r3)
+	addi	r3,r3,8
+
+4:	sub	r5,r5,r6
+
+	/* Get the desination 128B aligned */
+	neg	r6,r3
+	srdi	r7,r6,4
+	mtocrf	0x01,r7
+	clrldi	r6,r6,(64-7)
+
+	li	r9,16
+	li	r10,32
+	li	r11,48
+
+	bf	cr7*4+3,5f
+err3;	lvx	v1,0,r4
+	addi	r4,r4,16
+err3;	stvx	v1,0,r3
+	addi	r3,r3,16
+
+5:	bf	cr7*4+2,6f
+err3;	lvx	v1,0,r4
+err3;	lvx	v0,r4,r9
+	addi	r4,r4,32
+err3;	stvx	v1,0,r3
+err3;	stvx	v0,r3,r9
+	addi	r3,r3,32
+
+6:	bf	cr7*4+1,7f
+err3;	lvx	v3,0,r4
+err3;	lvx	v2,r4,r9
+err3;	lvx	v1,r4,r10
+err3;	lvx	v0,r4,r11
+	addi	r4,r4,64
+err3;	stvx	v3,0,r3
+err3;	stvx	v2,r3,r9
+err3;	stvx	v1,r3,r10
+err3;	stvx	v0,r3,r11
+	addi	r3,r3,64
+
+7:	sub	r5,r5,r6
+	srdi	r6,r5,7
+
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+
+	li	r12,64
+	li	r14,80
+	li	r15,96
+	li	r16,112
+
+	mtctr	r6
+
+	/*
+	 * Now do cacheline sized loads and stores. By this stage the
+	 * cacheline stores are also cacheline aligned.
+	 */
+	.align	5
+8:
+err4;	lvx	v7,0,r4
+err4;	lvx	v6,r4,r9
+err4;	lvx	v5,r4,r10
+err4;	lvx	v4,r4,r11
+err4;	lvx	v3,r4,r12
+err4;	lvx	v2,r4,r14
+err4;	lvx	v1,r4,r15
+err4;	lvx	v0,r4,r16
+	addi	r4,r4,128
+err4;	stvx	v7,0,r3
+err4;	stvx	v6,r3,r9
+err4;	stvx	v5,r3,r10
+err4;	stvx	v4,r3,r11
+err4;	stvx	v3,r3,r12
+err4;	stvx	v2,r3,r14
+err4;	stvx	v1,r3,r15
+err4;	stvx	v0,r3,r16
+	addi	r3,r3,128
+	bdnz	8b
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+
+	/* Up to 127B to go */
+	clrldi	r5,r5,(64-7)
+	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+	bf	cr7*4+1,9f
+err3;	lvx	v3,0,r4
+err3;	lvx	v2,r4,r9
+err3;	lvx	v1,r4,r10
+err3;	lvx	v0,r4,r11
+	addi	r4,r4,64
+err3;	stvx	v3,0,r3
+err3;	stvx	v2,r3,r9
+err3;	stvx	v1,r3,r10
+err3;	stvx	v0,r3,r11
+	addi	r3,r3,64
+
+9:	bf	cr7*4+2,10f
+err3;	lvx	v1,0,r4
+err3;	lvx	v0,r4,r9
+	addi	r4,r4,32
+err3;	stvx	v1,0,r3
+err3;	stvx	v0,r3,r9
+	addi	r3,r3,32
+
+10:	bf	cr7*4+3,11f
+err3;	lvx	v1,0,r4
+	addi	r4,r4,16
+err3;	stvx	v1,0,r3
+	addi	r3,r3,16
+
+	/* Up to 15B to go */
+11:	clrldi	r5,r5,(64-4)
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+err3;	ld	r0,0(r4)
+	addi	r4,r4,8
+err3;	std	r0,0(r3)
+	addi	r3,r3,8
+
+12:	bf	cr7*4+1,13f
+err3;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err3;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+13:	bf	cr7*4+2,14f
+err3;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err3;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+14:	bf	cr7*4+3,15f
+err3;	lbz	r0,0(r4)
+err3;	stb	r0,0(r3)
+
+15:	addi	r1,r1,STACKFRAMESIZE
+	b	exit_vmx_usercopy	/* tail call optimise */
+
+.Lvmx_unaligned_copy:
+	/* Get the destination 16B aligned */
+	neg	r6,r3
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-4)
+
+	bf	cr7*4+3,1f
+err3;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err3;	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+err3;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err3;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+err3;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err3;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	bf	cr7*4+0,4f
+err3;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+err3;	lwz	r7,4(r4)
+	addi	r4,r4,8
+err3;	stw	r0,0(r3)
+err3;	stw	r7,4(r3)
+	addi	r3,r3,8
+
+4:	sub	r5,r5,r6
+
+	/* Get the desination 128B aligned */
+	neg	r6,r3
+	srdi	r7,r6,4
+	mtocrf	0x01,r7
+	clrldi	r6,r6,(64-7)
+
+	li	r9,16
+	li	r10,32
+	li	r11,48
+
+	LVS(v16,0,r4)		/* Setup permute control vector */
+err3;	lvx	v0,0,r4
+	addi	r4,r4,16
+
+	bf	cr7*4+3,5f
+err3;	lvx	v1,0,r4
+	VPERM(v8,v0,v1,v16)
+	addi	r4,r4,16
+err3;	stvx	v8,0,r3
+	addi	r3,r3,16
+	vor	v0,v1,v1
+
+5:	bf	cr7*4+2,6f
+err3;	lvx	v1,0,r4
+	VPERM(v8,v0,v1,v16)
+err3;	lvx	v0,r4,r9
+	VPERM(v9,v1,v0,v16)
+	addi	r4,r4,32
+err3;	stvx	v8,0,r3
+err3;	stvx	v9,r3,r9
+	addi	r3,r3,32
+
+6:	bf	cr7*4+1,7f
+err3;	lvx	v3,0,r4
+	VPERM(v8,v0,v3,v16)
+err3;	lvx	v2,r4,r9
+	VPERM(v9,v3,v2,v16)
+err3;	lvx	v1,r4,r10
+	VPERM(v10,v2,v1,v16)
+err3;	lvx	v0,r4,r11
+	VPERM(v11,v1,v0,v16)
+	addi	r4,r4,64
+err3;	stvx	v8,0,r3
+err3;	stvx	v9,r3,r9
+err3;	stvx	v10,r3,r10
+err3;	stvx	v11,r3,r11
+	addi	r3,r3,64
+
+7:	sub	r5,r5,r6
+	srdi	r6,r5,7
+
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+
+	li	r12,64
+	li	r14,80
+	li	r15,96
+	li	r16,112
+
+	mtctr	r6
+
+	/*
+	 * Now do cacheline sized loads and stores. By this stage the
+	 * cacheline stores are also cacheline aligned.
+	 */
+	.align	5
+8:
+err4;	lvx	v7,0,r4
+	VPERM(v8,v0,v7,v16)
+err4;	lvx	v6,r4,r9
+	VPERM(v9,v7,v6,v16)
+err4;	lvx	v5,r4,r10
+	VPERM(v10,v6,v5,v16)
+err4;	lvx	v4,r4,r11
+	VPERM(v11,v5,v4,v16)
+err4;	lvx	v3,r4,r12
+	VPERM(v12,v4,v3,v16)
+err4;	lvx	v2,r4,r14
+	VPERM(v13,v3,v2,v16)
+err4;	lvx	v1,r4,r15
+	VPERM(v14,v2,v1,v16)
+err4;	lvx	v0,r4,r16
+	VPERM(v15,v1,v0,v16)
+	addi	r4,r4,128
+err4;	stvx	v8,0,r3
+err4;	stvx	v9,r3,r9
+err4;	stvx	v10,r3,r10
+err4;	stvx	v11,r3,r11
+err4;	stvx	v12,r3,r12
+err4;	stvx	v13,r3,r14
+err4;	stvx	v14,r3,r15
+err4;	stvx	v15,r3,r16
+	addi	r3,r3,128
+	bdnz	8b
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+
+	/* Up to 127B to go */
+	clrldi	r5,r5,(64-7)
+	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+	bf	cr7*4+1,9f
+err3;	lvx	v3,0,r4
+	VPERM(v8,v0,v3,v16)
+err3;	lvx	v2,r4,r9
+	VPERM(v9,v3,v2,v16)
+err3;	lvx	v1,r4,r10
+	VPERM(v10,v2,v1,v16)
+err3;	lvx	v0,r4,r11
+	VPERM(v11,v1,v0,v16)
+	addi	r4,r4,64
+err3;	stvx	v8,0,r3
+err3;	stvx	v9,r3,r9
+err3;	stvx	v10,r3,r10
+err3;	stvx	v11,r3,r11
+	addi	r3,r3,64
+
+9:	bf	cr7*4+2,10f
+err3;	lvx	v1,0,r4
+	VPERM(v8,v0,v1,v16)
+err3;	lvx	v0,r4,r9
+	VPERM(v9,v1,v0,v16)
+	addi	r4,r4,32
+err3;	stvx	v8,0,r3
+err3;	stvx	v9,r3,r9
+	addi	r3,r3,32
+
+10:	bf	cr7*4+3,11f
+err3;	lvx	v1,0,r4
+	VPERM(v8,v0,v1,v16)
+	addi	r4,r4,16
+err3;	stvx	v8,0,r3
+	addi	r3,r3,16
+
+	/* Up to 15B to go */
+11:	clrldi	r5,r5,(64-4)
+	addi	r4,r4,-16	/* Unwind the +16 load offset */
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+err3;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+err3;	lwz	r6,4(r4)
+	addi	r4,r4,8
+err3;	stw	r0,0(r3)
+err3;	stw	r6,4(r3)
+	addi	r3,r3,8
+
+12:	bf	cr7*4+1,13f
+err3;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err3;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+13:	bf	cr7*4+2,14f
+err3;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err3;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+14:	bf	cr7*4+3,15f
+err3;	lbz	r0,0(r4)
+err3;	stb	r0,0(r3)
+
+15:	addi	r1,r1,STACKFRAMESIZE
+	b	exit_vmx_usercopy	/* tail call optimise */
+#endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S
new file mode 100644
index 000000000..7e5e1c28e
--- /dev/null
+++ b/arch/powerpc/lib/crtsavres.S
@@ -0,0 +1,545 @@
+/*
+ * Special support for eabi and SVR4
+ *
+ *   Copyright (C) 1995, 1996, 1998, 2000, 2001 Free Software Foundation, Inc.
+ *   Copyright 2008 Freescale Semiconductor, Inc.
+ *   Written By Michael Meissner
+ *
+ * Based on gcc/config/rs6000/crtsavres.asm from gcc
+ * 64 bit additions from reading the PPC elf64abi document.
+ *
+ * This file is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * In addition to the permissions in the GNU General Public License, the
+ * Free Software Foundation gives you unlimited permission to link the
+ * compiled version of this file with other programs, and to distribute
+ * those programs without any restriction coming from the use of this
+ * file.  (The General Public License restrictions do apply in other
+ * respects; for example, they cover modification of the file, and
+ * distribution when not linked into another program.)
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+ * Boston, MA 02110-1301, USA.
+ *
+ *    As a special exception, if you link this library with files
+ *    compiled with GCC to produce an executable, this does not cause
+ *    the resulting executable to be covered by the GNU General Public License.
+ *    This exception does not however invalidate any other reasons why
+ *    the executable file might be covered by the GNU General Public License.
+ */
+
+#include <asm/ppc_asm.h>
+
+	.file	"crtsavres.S"
+
+#ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
+
+	.section ".text"
+
+#ifndef CONFIG_PPC64
+
+/* Routines for saving integer registers, called by the compiler.  */
+/* Called with r11 pointing to the stack header word of the caller of the */
+/* function, just beyond the end of the integer save area.  */
+
+_GLOBAL(_savegpr_14)
+_GLOBAL(_save32gpr_14)
+	stw	14,-72(11)	/* save gp registers */
+_GLOBAL(_savegpr_15)
+_GLOBAL(_save32gpr_15)
+	stw	15,-68(11)
+_GLOBAL(_savegpr_16)
+_GLOBAL(_save32gpr_16)
+	stw	16,-64(11)
+_GLOBAL(_savegpr_17)
+_GLOBAL(_save32gpr_17)
+	stw	17,-60(11)
+_GLOBAL(_savegpr_18)
+_GLOBAL(_save32gpr_18)
+	stw	18,-56(11)
+_GLOBAL(_savegpr_19)
+_GLOBAL(_save32gpr_19)
+	stw	19,-52(11)
+_GLOBAL(_savegpr_20)
+_GLOBAL(_save32gpr_20)
+	stw	20,-48(11)
+_GLOBAL(_savegpr_21)
+_GLOBAL(_save32gpr_21)
+	stw	21,-44(11)
+_GLOBAL(_savegpr_22)
+_GLOBAL(_save32gpr_22)
+	stw	22,-40(11)
+_GLOBAL(_savegpr_23)
+_GLOBAL(_save32gpr_23)
+	stw	23,-36(11)
+_GLOBAL(_savegpr_24)
+_GLOBAL(_save32gpr_24)
+	stw	24,-32(11)
+_GLOBAL(_savegpr_25)
+_GLOBAL(_save32gpr_25)
+	stw	25,-28(11)
+_GLOBAL(_savegpr_26)
+_GLOBAL(_save32gpr_26)
+	stw	26,-24(11)
+_GLOBAL(_savegpr_27)
+_GLOBAL(_save32gpr_27)
+	stw	27,-20(11)
+_GLOBAL(_savegpr_28)
+_GLOBAL(_save32gpr_28)
+	stw	28,-16(11)
+_GLOBAL(_savegpr_29)
+_GLOBAL(_save32gpr_29)
+	stw	29,-12(11)
+_GLOBAL(_savegpr_30)
+_GLOBAL(_save32gpr_30)
+	stw	30,-8(11)
+_GLOBAL(_savegpr_31)
+_GLOBAL(_save32gpr_31)
+	stw	31,-4(11)
+	blr
+
+/* Routines for restoring integer registers, called by the compiler.  */
+/* Called with r11 pointing to the stack header word of the caller of the */
+/* function, just beyond the end of the integer restore area.  */
+
+_GLOBAL(_restgpr_14)
+_GLOBAL(_rest32gpr_14)
+	lwz	14,-72(11)	/* restore gp registers */
+_GLOBAL(_restgpr_15)
+_GLOBAL(_rest32gpr_15)
+	lwz	15,-68(11)
+_GLOBAL(_restgpr_16)
+_GLOBAL(_rest32gpr_16)
+	lwz	16,-64(11)
+_GLOBAL(_restgpr_17)
+_GLOBAL(_rest32gpr_17)
+	lwz	17,-60(11)
+_GLOBAL(_restgpr_18)
+_GLOBAL(_rest32gpr_18)
+	lwz	18,-56(11)
+_GLOBAL(_restgpr_19)
+_GLOBAL(_rest32gpr_19)
+	lwz	19,-52(11)
+_GLOBAL(_restgpr_20)
+_GLOBAL(_rest32gpr_20)
+	lwz	20,-48(11)
+_GLOBAL(_restgpr_21)
+_GLOBAL(_rest32gpr_21)
+	lwz	21,-44(11)
+_GLOBAL(_restgpr_22)
+_GLOBAL(_rest32gpr_22)
+	lwz	22,-40(11)
+_GLOBAL(_restgpr_23)
+_GLOBAL(_rest32gpr_23)
+	lwz	23,-36(11)
+_GLOBAL(_restgpr_24)
+_GLOBAL(_rest32gpr_24)
+	lwz	24,-32(11)
+_GLOBAL(_restgpr_25)
+_GLOBAL(_rest32gpr_25)
+	lwz	25,-28(11)
+_GLOBAL(_restgpr_26)
+_GLOBAL(_rest32gpr_26)
+	lwz	26,-24(11)
+_GLOBAL(_restgpr_27)
+_GLOBAL(_rest32gpr_27)
+	lwz	27,-20(11)
+_GLOBAL(_restgpr_28)
+_GLOBAL(_rest32gpr_28)
+	lwz	28,-16(11)
+_GLOBAL(_restgpr_29)
+_GLOBAL(_rest32gpr_29)
+	lwz	29,-12(11)
+_GLOBAL(_restgpr_30)
+_GLOBAL(_rest32gpr_30)
+	lwz	30,-8(11)
+_GLOBAL(_restgpr_31)
+_GLOBAL(_rest32gpr_31)
+	lwz	31,-4(11)
+	blr
+
+/* Routines for restoring integer registers, called by the compiler.  */
+/* Called with r11 pointing to the stack header word of the caller of the */
+/* function, just beyond the end of the integer restore area.  */
+
+_GLOBAL(_restgpr_14_x)
+_GLOBAL(_rest32gpr_14_x)
+	lwz	14,-72(11)	/* restore gp registers */
+_GLOBAL(_restgpr_15_x)
+_GLOBAL(_rest32gpr_15_x)
+	lwz	15,-68(11)
+_GLOBAL(_restgpr_16_x)
+_GLOBAL(_rest32gpr_16_x)
+	lwz	16,-64(11)
+_GLOBAL(_restgpr_17_x)
+_GLOBAL(_rest32gpr_17_x)
+	lwz	17,-60(11)
+_GLOBAL(_restgpr_18_x)
+_GLOBAL(_rest32gpr_18_x)
+	lwz	18,-56(11)
+_GLOBAL(_restgpr_19_x)
+_GLOBAL(_rest32gpr_19_x)
+	lwz	19,-52(11)
+_GLOBAL(_restgpr_20_x)
+_GLOBAL(_rest32gpr_20_x)
+	lwz	20,-48(11)
+_GLOBAL(_restgpr_21_x)
+_GLOBAL(_rest32gpr_21_x)
+	lwz	21,-44(11)
+_GLOBAL(_restgpr_22_x)
+_GLOBAL(_rest32gpr_22_x)
+	lwz	22,-40(11)
+_GLOBAL(_restgpr_23_x)
+_GLOBAL(_rest32gpr_23_x)
+	lwz	23,-36(11)
+_GLOBAL(_restgpr_24_x)
+_GLOBAL(_rest32gpr_24_x)
+	lwz	24,-32(11)
+_GLOBAL(_restgpr_25_x)
+_GLOBAL(_rest32gpr_25_x)
+	lwz	25,-28(11)
+_GLOBAL(_restgpr_26_x)
+_GLOBAL(_rest32gpr_26_x)
+	lwz	26,-24(11)
+_GLOBAL(_restgpr_27_x)
+_GLOBAL(_rest32gpr_27_x)
+	lwz	27,-20(11)
+_GLOBAL(_restgpr_28_x)
+_GLOBAL(_rest32gpr_28_x)
+	lwz	28,-16(11)
+_GLOBAL(_restgpr_29_x)
+_GLOBAL(_rest32gpr_29_x)
+	lwz	29,-12(11)
+_GLOBAL(_restgpr_30_x)
+_GLOBAL(_rest32gpr_30_x)
+	lwz	30,-8(11)
+_GLOBAL(_restgpr_31_x)
+_GLOBAL(_rest32gpr_31_x)
+	lwz	0,4(11)
+	lwz	31,-4(11)
+	mtlr	0
+	mr	1,11
+	blr
+
+#ifdef CONFIG_ALTIVEC
+/* Called with r0 pointing just beyond the end of the vector save area.  */
+
+_GLOBAL(_savevr_20)
+	li	r11,-192
+	stvx	v20,r11,r0
+_GLOBAL(_savevr_21)
+	li	r11,-176
+	stvx	v21,r11,r0
+_GLOBAL(_savevr_22)
+	li	r11,-160
+	stvx	v22,r11,r0
+_GLOBAL(_savevr_23)
+	li	r11,-144
+	stvx	v23,r11,r0
+_GLOBAL(_savevr_24)
+	li	r11,-128
+	stvx	v24,r11,r0
+_GLOBAL(_savevr_25)
+	li	r11,-112
+	stvx	v25,r11,r0
+_GLOBAL(_savevr_26)
+	li	r11,-96
+	stvx	v26,r11,r0
+_GLOBAL(_savevr_27)
+	li	r11,-80
+	stvx	v27,r11,r0
+_GLOBAL(_savevr_28)
+	li	r11,-64
+	stvx	v28,r11,r0
+_GLOBAL(_savevr_29)
+	li	r11,-48
+	stvx	v29,r11,r0
+_GLOBAL(_savevr_30)
+	li	r11,-32
+	stvx	v30,r11,r0
+_GLOBAL(_savevr_31)
+	li	r11,-16
+	stvx	v31,r11,r0
+	blr
+
+_GLOBAL(_restvr_20)
+	li	r11,-192
+	lvx	v20,r11,r0
+_GLOBAL(_restvr_21)
+	li	r11,-176
+	lvx	v21,r11,r0
+_GLOBAL(_restvr_22)
+	li	r11,-160
+	lvx	v22,r11,r0
+_GLOBAL(_restvr_23)
+	li	r11,-144
+	lvx	v23,r11,r0
+_GLOBAL(_restvr_24)
+	li	r11,-128
+	lvx	v24,r11,r0
+_GLOBAL(_restvr_25)
+	li	r11,-112
+	lvx	v25,r11,r0
+_GLOBAL(_restvr_26)
+	li	r11,-96
+	lvx	v26,r11,r0
+_GLOBAL(_restvr_27)
+	li	r11,-80
+	lvx	v27,r11,r0
+_GLOBAL(_restvr_28)
+	li	r11,-64
+	lvx	v28,r11,r0
+_GLOBAL(_restvr_29)
+	li	r11,-48
+	lvx	v29,r11,r0
+_GLOBAL(_restvr_30)
+	li	r11,-32
+	lvx	v30,r11,r0
+_GLOBAL(_restvr_31)
+	li	r11,-16
+	lvx	v31,r11,r0
+	blr
+
+#endif /* CONFIG_ALTIVEC */
+
+#else /* CONFIG_PPC64 */
+
+.globl	_savegpr0_14
+_savegpr0_14:
+	std	r14,-144(r1)
+.globl	_savegpr0_15
+_savegpr0_15:
+	std	r15,-136(r1)
+.globl	_savegpr0_16
+_savegpr0_16:
+	std	r16,-128(r1)
+.globl	_savegpr0_17
+_savegpr0_17:
+	std	r17,-120(r1)
+.globl	_savegpr0_18
+_savegpr0_18:
+	std	r18,-112(r1)
+.globl	_savegpr0_19
+_savegpr0_19:
+	std	r19,-104(r1)
+.globl	_savegpr0_20
+_savegpr0_20:
+	std	r20,-96(r1)
+.globl	_savegpr0_21
+_savegpr0_21:
+	std	r21,-88(r1)
+.globl	_savegpr0_22
+_savegpr0_22:
+	std	r22,-80(r1)
+.globl	_savegpr0_23
+_savegpr0_23:
+	std	r23,-72(r1)
+.globl	_savegpr0_24
+_savegpr0_24:
+	std	r24,-64(r1)
+.globl	_savegpr0_25
+_savegpr0_25:
+	std	r25,-56(r1)
+.globl	_savegpr0_26
+_savegpr0_26:
+	std	r26,-48(r1)
+.globl	_savegpr0_27
+_savegpr0_27:
+	std	r27,-40(r1)
+.globl	_savegpr0_28
+_savegpr0_28:
+	std	r28,-32(r1)
+.globl	_savegpr0_29
+_savegpr0_29:
+	std	r29,-24(r1)
+.globl	_savegpr0_30
+_savegpr0_30:
+	std	r30,-16(r1)
+.globl	_savegpr0_31
+_savegpr0_31:
+	std	r31,-8(r1)
+	std	r0,16(r1)
+	blr
+
+.globl	_restgpr0_14
+_restgpr0_14:
+	ld	r14,-144(r1)
+.globl	_restgpr0_15
+_restgpr0_15:
+	ld	r15,-136(r1)
+.globl	_restgpr0_16
+_restgpr0_16:
+	ld	r16,-128(r1)
+.globl	_restgpr0_17
+_restgpr0_17:
+	ld	r17,-120(r1)
+.globl	_restgpr0_18
+_restgpr0_18:
+	ld	r18,-112(r1)
+.globl	_restgpr0_19
+_restgpr0_19:
+	ld	r19,-104(r1)
+.globl	_restgpr0_20
+_restgpr0_20:
+	ld	r20,-96(r1)
+.globl	_restgpr0_21
+_restgpr0_21:
+	ld	r21,-88(r1)
+.globl	_restgpr0_22
+_restgpr0_22:
+	ld	r22,-80(r1)
+.globl	_restgpr0_23
+_restgpr0_23:
+	ld	r23,-72(r1)
+.globl	_restgpr0_24
+_restgpr0_24:
+	ld	r24,-64(r1)
+.globl	_restgpr0_25
+_restgpr0_25:
+	ld	r25,-56(r1)
+.globl	_restgpr0_26
+_restgpr0_26:
+	ld	r26,-48(r1)
+.globl	_restgpr0_27
+_restgpr0_27:
+	ld	r27,-40(r1)
+.globl	_restgpr0_28
+_restgpr0_28:
+	ld	r28,-32(r1)
+.globl	_restgpr0_29
+_restgpr0_29:
+	ld	r0,16(r1)
+	ld	r29,-24(r1)
+	mtlr	r0
+	ld	r30,-16(r1)
+	ld	r31,-8(r1)
+	blr
+
+.globl	_restgpr0_30
+_restgpr0_30:
+	ld	r30,-16(r1)
+.globl	_restgpr0_31
+_restgpr0_31:
+	ld	r0,16(r1)
+	ld	r31,-8(r1)
+	mtlr	r0
+	blr
+
+#ifdef CONFIG_ALTIVEC
+/* Called with r0 pointing just beyond the end of the vector save area.  */
+
+.globl	_savevr_20
+_savevr_20:
+	li	r12,-192
+	stvx	v20,r12,r0
+.globl	_savevr_21
+_savevr_21:
+	li	r12,-176
+	stvx	v21,r12,r0
+.globl	_savevr_22
+_savevr_22:
+	li	r12,-160
+	stvx	v22,r12,r0
+.globl	_savevr_23
+_savevr_23:
+	li	r12,-144
+	stvx	v23,r12,r0
+.globl	_savevr_24
+_savevr_24:
+	li	r12,-128
+	stvx	v24,r12,r0
+.globl	_savevr_25
+_savevr_25:
+	li	r12,-112
+	stvx	v25,r12,r0
+.globl	_savevr_26
+_savevr_26:
+	li	r12,-96
+	stvx	v26,r12,r0
+.globl	_savevr_27
+_savevr_27:
+	li	r12,-80
+	stvx	v27,r12,r0
+.globl	_savevr_28
+_savevr_28:
+	li	r12,-64
+	stvx	v28,r12,r0
+.globl	_savevr_29
+_savevr_29:
+	li	r12,-48
+	stvx	v29,r12,r0
+.globl	_savevr_30
+_savevr_30:
+	li	r12,-32
+	stvx	v30,r12,r0
+.globl	_savevr_31
+_savevr_31:
+	li	r12,-16
+	stvx	v31,r12,r0
+	blr
+
+.globl	_restvr_20
+_restvr_20:
+	li	r12,-192
+	lvx	v20,r12,r0
+.globl	_restvr_21
+_restvr_21:
+	li	r12,-176
+	lvx	v21,r12,r0
+.globl	_restvr_22
+_restvr_22:
+	li	r12,-160
+	lvx	v22,r12,r0
+.globl	_restvr_23
+_restvr_23:
+	li	r12,-144
+	lvx	v23,r12,r0
+.globl	_restvr_24
+_restvr_24:
+	li	r12,-128
+	lvx	v24,r12,r0
+.globl	_restvr_25
+_restvr_25:
+	li	r12,-112
+	lvx	v25,r12,r0
+.globl	_restvr_26
+_restvr_26:
+	li	r12,-96
+	lvx	v26,r12,r0
+.globl	_restvr_27
+_restvr_27:
+	li	r12,-80
+	lvx	v27,r12,r0
+.globl	_restvr_28
+_restvr_28:
+	li	r12,-64
+	lvx	v28,r12,r0
+.globl	_restvr_29
+_restvr_29:
+	li	r12,-48
+	lvx	v29,r12,r0
+.globl	_restvr_30
+_restvr_30:
+	li	r12,-32
+	lvx	v30,r12,r0
+.globl	_restvr_31
+_restvr_31:
+	li	r12,-16
+	lvx	v31,r12,r0
+	blr
+
+#endif /* CONFIG_ALTIVEC */
+
+#endif /* CONFIG_PPC64 */
+
+#endif
diff --git a/arch/powerpc/lib/div64.S b/arch/powerpc/lib/div64.S
new file mode 100644
index 000000000..83d9832fd
--- /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/feature-fixups-test.S b/arch/powerpc/lib/feature-fixups-test.S
new file mode 100644
index 000000000..ee7c5fd5f
--- /dev/null
+++ b/arch/powerpc/lib/feature-fixups-test.S
@@ -0,0 +1,798 @@
+/*
+ * Copyright 2008 Michael Ellerman, 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) any later version.
+ */
+
+#include <asm/feature-fixups.h>
+#include <asm/ppc_asm.h>
+#include <asm/synch.h>
+#include <asm/asm-compat.h>
+
+	.text
+
+#define globl(x)		\
+	.globl x;	\
+x:
+
+globl(ftr_fixup_test1)
+	or	1,1,1
+	or	2,2,2	/* fixup will nop out this instruction */
+	or	3,3,3
+
+globl(end_ftr_fixup_test1)
+
+globl(ftr_fixup_test1_orig)
+	or	1,1,1
+	or	2,2,2
+	or	3,3,3
+
+globl(ftr_fixup_test1_expected)
+	or	1,1,1
+	nop
+	or	3,3,3
+
+globl(ftr_fixup_test2)
+	or	1,1,1
+	or	2,2,2	/* fixup will replace this with ftr_fixup_test2_alt */
+	or	3,3,3
+
+globl(end_ftr_fixup_test2)
+
+globl(ftr_fixup_test2_orig)
+	or	1,1,1
+	or	2,2,2
+	or	3,3,3
+
+globl(ftr_fixup_test2_alt)
+	or	31,31,31
+
+globl(ftr_fixup_test2_expected)
+	or	1,1,1
+	or	31,31,31
+	or	3,3,3
+
+globl(ftr_fixup_test3)
+	or	1,1,1
+	or	2,2,2	/* fixup will fail to replace this */
+	or	3,3,3
+
+globl(end_ftr_fixup_test3)
+
+globl(ftr_fixup_test3_orig)
+	or	1,1,1
+	or	2,2,2
+	or	3,3,3
+
+globl(ftr_fixup_test3_alt)
+	or	31,31,31
+	or	31,31,31
+
+globl(ftr_fixup_test4)
+	or	1,1,1
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	3,3,3
+
+globl(end_ftr_fixup_test4)
+
+globl(ftr_fixup_test4_expected)
+	or	1,1,1
+	or	31,31,31
+	or	31,31,31
+	nop
+	nop
+	or	3,3,3
+
+globl(ftr_fixup_test4_orig)
+	or	1,1,1
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	3,3,3
+
+globl(ftr_fixup_test4_alt)
+	or	31,31,31
+	or	31,31,31
+
+
+globl(ftr_fixup_test5)
+	or	1,1,1
+BEGIN_FTR_SECTION
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+FTR_SECTION_ELSE
+2:	b	3f
+3:	or	5,5,5
+	beq	3b
+	b	1f
+	or	6,6,6
+	b	2b
+1:	bdnz	3b
+ALT_FTR_SECTION_END(0, 1)
+	or	1,1,1
+
+globl(end_ftr_fixup_test5)
+
+globl(ftr_fixup_test5_expected)
+	or	1,1,1
+2:	b	3f
+3:	or	5,5,5
+	beq	3b
+	b	1f
+	or	6,6,6
+	b	2b
+1:	bdnz	3b
+	or	1,1,1
+
+globl(ftr_fixup_test6)
+1:	or	1,1,1
+BEGIN_FTR_SECTION
+	or	5,5,5
+2:	PPC_LCMPI	r3,0
+	beq	4f
+	blt	2b
+	b	1b
+	b	4f
+FTR_SECTION_ELSE
+2:	or	2,2,2
+	PPC_LCMPI	r3,1
+	beq	3f
+	blt	2b
+	b	3f
+	b	1b
+ALT_FTR_SECTION_END(0, 1)
+3:	or	1,1,1
+	or	2,2,2
+4:	or	3,3,3
+
+globl(end_ftr_fixup_test6)
+
+globl(ftr_fixup_test6_expected)
+1:	or	1,1,1
+2:	or	2,2,2
+	PPC_LCMPI	r3,1
+	beq	3f
+	blt	2b
+	b	3f
+	b	1b
+3:	or	1,1,1
+	or	2,2,2
+	or	3,3,3
+
+globl(ftr_fixup_test7)
+	or	1,1,1
+BEGIN_FTR_SECTION
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+FTR_SECTION_ELSE
+2:	b	3f
+3:	or	5,5,5
+	beq	3b
+	b	1f
+	or	6,6,6
+	b	2b
+	bdnz	3b
+1:
+ALT_FTR_SECTION_END(0, 1)
+	or	1,1,1
+	or	1,1,1
+
+globl(end_ftr_fixup_test7)
+	nop
+
+globl(ftr_fixup_test7_expected)
+	or	1,1,1
+2:	b	3f
+3:	or	5,5,5
+	beq	3b
+	b	1f
+	or	6,6,6
+	b	2b
+	bdnz	3b
+1:	or	1,1,1
+
+#if 0
+/* Test that if we have a larger else case the assembler spots it and
+ * reports an error. #if 0'ed so as not to break the build normally.
+ */
+ftr_fixup_test_too_big:
+	or	1,1,1
+BEGIN_FTR_SECTION
+	or	2,2,2
+	or	2,2,2
+	or	2,2,2
+FTR_SECTION_ELSE
+	or	3,3,3
+	or	3,3,3
+	or	3,3,3
+	or	3,3,3
+ALT_FTR_SECTION_END(0, 1)
+	or	1,1,1
+#endif
+
+#define	MAKE_MACRO_TEST(TYPE)						\
+globl(ftr_fixup_test_ ##TYPE##_macros)					\
+	or	1,1,1;							\
+	/* Basic test, this section should all be nop'ed */		\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+END_##TYPE##_SECTION(0, 1)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Basic test, this section should NOT be nop'ed */		\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+END_##TYPE##_SECTION(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nesting test, inner section should be nop'ed */		\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(80)					\
+	or	3,3,3;							\
+	or	3,3,3;							\
+END_##TYPE##_SECTION_NESTED(0, 1, 80)					\
+	or	2,2,2;							\
+	or	2,2,2;							\
+END_##TYPE##_SECTION(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nesting test, whole section should be nop'ed */		\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(80)					\
+	or	3,3,3;							\
+	or	3,3,3;							\
+END_##TYPE##_SECTION_NESTED(0, 0, 80)					\
+	or	2,2,2;							\
+	or	2,2,2;							\
+END_##TYPE##_SECTION(0, 1)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nesting test, none should be nop'ed */			\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(80)					\
+	or	3,3,3;							\
+	or	3,3,3;							\
+END_##TYPE##_SECTION_NESTED(0, 0, 80)					\
+	or	2,2,2;							\
+	or	2,2,2;							\
+END_##TYPE##_SECTION(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Basic alt section test, default case should be taken */	\
+BEGIN_##TYPE##_SECTION							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+##TYPE##_SECTION_ELSE							\
+	or	5,5,5;							\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Basic alt section test, else case should be taken */		\
+BEGIN_##TYPE##_SECTION							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+##TYPE##_SECTION_ELSE							\
+	or	31,31,31;						\
+	or	31,31,31;						\
+	or	31,31,31;						\
+ALT_##TYPE##_SECTION_END(0, 1)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Alt with smaller else case, should be padded with nops */	\
+BEGIN_##TYPE##_SECTION							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+##TYPE##_SECTION_ELSE							\
+	or	31,31,31;						\
+ALT_##TYPE##_SECTION_END(0, 1)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Alt section with nested section in default case */		\
+	/* Default case should be taken, with nop'ed inner section */	\
+BEGIN_##TYPE##_SECTION							\
+	or	3,3,3;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	3,3,3;							\
+	or	3,3,3;							\
+END_##TYPE##_SECTION_NESTED(0, 1, 95)					\
+	or	3,3,3;							\
+##TYPE##_SECTION_ELSE							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+ALT_##TYPE##_SECTION_END(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Alt section with nested section in else, default taken */	\
+BEGIN_##TYPE##_SECTION							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+##TYPE##_SECTION_ELSE							\
+	or	5,5,5;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	3,3,3;							\
+END_##TYPE##_SECTION_NESTED(0, 1, 95)					\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Alt section with nested section in else, else taken & nop */	\
+BEGIN_##TYPE##_SECTION							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+##TYPE##_SECTION_ELSE							\
+	or	5,5,5;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	3,3,3;							\
+END_##TYPE##_SECTION_NESTED(0, 1, 95)					\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END(0, 1)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Feature section with nested alt section, default taken */	\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	1,1,1;							\
+##TYPE##_SECTION_ELSE_NESTED(95)					\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 0, 95)				\
+	or	2,2,2;							\
+END_##TYPE##_SECTION(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Feature section with nested alt section, else taken */	\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	1,1,1;							\
+##TYPE##_SECTION_ELSE_NESTED(95)					\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 1, 95)				\
+	or	2,2,2;							\
+END_##TYPE##_SECTION(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Feature section with nested alt section, all nop'ed */	\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	1,1,1;							\
+##TYPE##_SECTION_ELSE_NESTED(95)					\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 0, 95)				\
+	or	2,2,2;							\
+END_##TYPE##_SECTION(0, 1)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, default with inner default taken */	\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	1,1,1;							\
+##TYPE##_SECTION_ELSE_NESTED(95)					\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 0, 95)				\
+	or	2,2,2;							\
+##TYPE##_SECTION_ELSE							\
+	or	31,31,31;						\
+BEGIN_##TYPE##_SECTION_NESTED(94)					\
+	or	5,5,5;							\
+##TYPE##_SECTION_ELSE_NESTED(94)					\
+	or	1,1,1;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 0, 94)				\
+	or	31,31,31;						\
+ALT_##TYPE##_SECTION_END(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, default with inner else taken */	\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	1,1,1;							\
+##TYPE##_SECTION_ELSE_NESTED(95)					\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 1, 95)				\
+	or	2,2,2;							\
+##TYPE##_SECTION_ELSE							\
+	or	31,31,31;						\
+BEGIN_##TYPE##_SECTION_NESTED(94)					\
+	or	5,5,5;							\
+##TYPE##_SECTION_ELSE_NESTED(94)					\
+	or	1,1,1;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 0, 94)				\
+	or	31,31,31;						\
+ALT_##TYPE##_SECTION_END(0, 0)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, else with inner default taken */	\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	1,1,1;							\
+##TYPE##_SECTION_ELSE_NESTED(95)					\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 1, 95)				\
+	or	2,2,2;							\
+##TYPE##_SECTION_ELSE							\
+	or	31,31,31;						\
+BEGIN_##TYPE##_SECTION_NESTED(94)					\
+	or	5,5,5;							\
+##TYPE##_SECTION_ELSE_NESTED(94)					\
+	or	1,1,1;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 0, 94)				\
+	or	31,31,31;						\
+ALT_##TYPE##_SECTION_END(0, 1)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, else with inner else taken */		\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+BEGIN_##TYPE##_SECTION_NESTED(95)					\
+	or	1,1,1;							\
+##TYPE##_SECTION_ELSE_NESTED(95)					\
+	or	5,5,5;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 1, 95)				\
+	or	2,2,2;							\
+##TYPE##_SECTION_ELSE							\
+	or	31,31,31;						\
+BEGIN_##TYPE##_SECTION_NESTED(94)					\
+	or	5,5,5;							\
+##TYPE##_SECTION_ELSE_NESTED(94)					\
+	or	1,1,1;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 1, 94)				\
+	or	31,31,31;						\
+ALT_##TYPE##_SECTION_END(0, 1)						\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, else can have large else case */	\
+BEGIN_##TYPE##_SECTION							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+##TYPE##_SECTION_ELSE 							\
+BEGIN_##TYPE##_SECTION_NESTED(94) 					\
+	or	5,5,5;							\
+	or	5,5,5;							\
+	or	5,5,5;							\
+	or	5,5,5;							\
+##TYPE##_SECTION_ELSE_NESTED(94) 					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	or	1,1,1;							\
+ALT_##TYPE##_SECTION_END_NESTED(0, 1, 94)				\
+ALT_##TYPE##_SECTION_END(0, 1)						\
+	or	1,1,1;							\
+	or	1,1,1;
+
+#define	MAKE_MACRO_TEST_EXPECTED(TYPE)					\
+globl(ftr_fixup_test_ ##TYPE##_macros_expected)				\
+	or	1,1,1;							\
+	/* Basic test, this section should all be nop'ed */		\
+/* BEGIN_##TYPE##_SECTION */						\
+	nop;								\
+	nop;								\
+	nop;								\
+/* END_##TYPE##_SECTION(0, 1) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Basic test, this section should NOT be nop'ed */		\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	2,2,2;							\
+	or	2,2,2;							\
+	or	2,2,2;							\
+/* END_##TYPE##_SECTION(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nesting test, inner section should be nop'ed */		\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	2,2,2;							\
+	or	2,2,2;							\
+/* BEGIN_##TYPE##_SECTION_NESTED(80) */					\
+	nop;								\
+	nop;								\
+/* END_##TYPE##_SECTION_NESTED(0, 1, 80) */				\
+	or	2,2,2;							\
+	or	2,2,2;							\
+/* END_##TYPE##_SECTION(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nesting test, whole section should be nop'ed */		\
+	/* NB. inner section is not nop'ed, but then entire outer is */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	nop;								\
+	nop;								\
+/* BEGIN_##TYPE##_SECTION_NESTED(80) */					\
+	nop;								\
+	nop;								\
+/* END_##TYPE##_SECTION_NESTED(0, 0, 80) */				\
+	nop;								\
+	nop;								\
+/* END_##TYPE##_SECTION(0, 1) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nesting test, none should be nop'ed */			\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	2,2,2;							\
+	or	2,2,2;							\
+/* BEGIN_##TYPE##_SECTION_NESTED(80) */					\
+	or	3,3,3;							\
+	or	3,3,3;							\
+/* END_##TYPE##_SECTION_NESTED(0, 0, 80) */				\
+	or	2,2,2;							\
+	or	2,2,2;							\
+/* END_##TYPE##_SECTION(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Basic alt section test, default case should be taken */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	3,3,3;							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+/* ##TYPE##_SECTION_ELSE */						\
+	/* or	5,5,5; */						\
+	/* or	5,5,5; */						\
+/* ALT_##TYPE##_SECTION_END(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Basic alt section test, else case should be taken */		\
+/* BEGIN_##TYPE##_SECTION */						\
+	/* or	3,3,3; */						\
+	/* or	3,3,3; */						\
+	/* or	3,3,3; */						\
+/* ##TYPE##_SECTION_ELSE */						\
+	or	31,31,31;						\
+	or	31,31,31;						\
+	or	31,31,31;						\
+/* ALT_##TYPE##_SECTION_END(0, 1) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Alt with smaller else case, should be padded with nops */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	/* or	3,3,3; */						\
+	/* or	3,3,3; */						\
+	/* or	3,3,3; */						\
+/* ##TYPE##_SECTION_ELSE */						\
+	or	31,31,31;						\
+	nop;								\
+	nop;								\
+/* ALT_##TYPE##_SECTION_END(0, 1) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Alt section with nested section in default case */		\
+	/* Default case should be taken, with nop'ed inner section */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	3,3,3;							\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	nop;								\
+	nop;								\
+/* END_##TYPE##_SECTION_NESTED(0, 1, 95) */				\
+	or	3,3,3;							\
+/* ##TYPE##_SECTION_ELSE */						\
+	/* or	2,2,2; */						\
+	/* or	2,2,2; */						\
+/* ALT_##TYPE##_SECTION_END(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Alt section with nested section in else, default taken */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	3,3,3;							\
+	or	3,3,3;							\
+	or	3,3,3;							\
+/* ##TYPE##_SECTION_ELSE */						\
+	/* or	5,5,5; */						\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	/* or	3,3,3; */						\
+/* END_##TYPE##_SECTION_NESTED(0, 1, 95) */				\
+	/* or	5,5,5; */						\
+/* ALT_##TYPE##_SECTION_END(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Alt section with nested section in else, else taken & nop */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	/* or	3,3,3; */						\
+	/* or	3,3,3; */						\
+	/* or	3,3,3; */						\
+/* ##TYPE##_SECTION_ELSE */						\
+	or	5,5,5;							\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	nop;								\
+/* END_##TYPE##_SECTION_NESTED(0, 1, 95) */				\
+	or	5,5,5;							\
+/* ALT_##TYPE##_SECTION_END(0, 1) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Feature section with nested alt section, default taken */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	2,2,2;							\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	or	1,1,1;							\
+/* ##TYPE##_SECTION_ELSE_NESTED(95) */					\
+	/* or	5,5,5; */						\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 0, 95) */				\
+	or	2,2,2;							\
+/* END_##TYPE##_SECTION(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Feature section with nested alt section, else taken */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	2,2,2;							\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	/* or	1,1,1; */						\
+/* ##TYPE##_SECTION_ELSE_NESTED(95) */					\
+	or	5,5,5;							\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 1, 95) */				\
+	or	2,2,2;							\
+/* END_##TYPE##_SECTION(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Feature section with nested alt section, all nop'ed */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	nop;								\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	nop;								\
+/* ##TYPE##_SECTION_ELSE_NESTED(95) */					\
+	/* or	5,5,5; */						\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 0, 95) */				\
+	nop;								\
+/* END_##TYPE##_SECTION(0, 1) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, default with inner default taken */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	2,2,2;							\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	or	1,1,1;							\
+/* ##TYPE##_SECTION_ELSE_NESTED(95) */					\
+	/* or	5,5,5; */						\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 0, 95) */				\
+	or	2,2,2;							\
+/* ##TYPE##_SECTION_ELSE */						\
+	/* or	31,31,31; */						\
+/* BEGIN_##TYPE##_SECTION_NESTED(94) */					\
+	/* or	5,5,5; */						\
+/* ##TYPE##_SECTION_ELSE_NESTED(94) */					\
+	/* or	1,1,1; */						\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 0, 94) */				\
+	/* or	31,31,31; */						\
+/* ALT_##TYPE##_SECTION_END(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, default with inner else taken */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	or	2,2,2;							\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	/* or	1,1,1; */						\
+/* ##TYPE##_SECTION_ELSE_NESTED(95) */					\
+	or	5,5,5;							\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 1, 95) */				\
+	or	2,2,2;							\
+/* ##TYPE##_SECTION_ELSE */						\
+	/* or	31,31,31; */						\
+/* BEGIN_##TYPE##_SECTION_NESTED(94) */					\
+	/* or	5,5,5; */						\
+/* ##TYPE##_SECTION_ELSE_NESTED(94) */					\
+	/* or	1,1,1; */						\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 0, 94) */				\
+	/* or	31,31,31; */						\
+/* ALT_##TYPE##_SECTION_END(0, 0) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, else with inner default taken */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	/* or	2,2,2; */						\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	/* or	1,1,1; */						\
+/* ##TYPE##_SECTION_ELSE_NESTED(95) */					\
+	/* or	5,5,5; */						\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 1, 95) */				\
+	/* or	2,2,2; */						\
+/* ##TYPE##_SECTION_ELSE */						\
+	or	31,31,31;						\
+/* BEGIN_##TYPE##_SECTION_NESTED(94) */					\
+	or	5,5,5;							\
+/* ##TYPE##_SECTION_ELSE_NESTED(94) */					\
+	/* or	1,1,1; */						\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 0, 94) */				\
+	or	31,31,31;						\
+/* ALT_##TYPE##_SECTION_END(0, 1) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, else with inner else taken */		\
+/* BEGIN_##TYPE##_SECTION */						\
+	/* or	2,2,2; */						\
+/* BEGIN_##TYPE##_SECTION_NESTED(95) */					\
+	/* or	1,1,1; */						\
+/* ##TYPE##_SECTION_ELSE_NESTED(95) */					\
+	/* or	5,5,5; */						\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 1, 95) */				\
+	/* or	2,2,2; */						\
+/* ##TYPE##_SECTION_ELSE */						\
+	or	31,31,31;						\
+/* BEGIN_##TYPE##_SECTION_NESTED(94) */					\
+	/* or	5,5,5; */						\
+/* ##TYPE##_SECTION_ELSE_NESTED(94) */					\
+	or	1,1,1;							\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 1, 94) */				\
+	or	31,31,31;						\
+/* ALT_##TYPE##_SECTION_END(0, 1) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	/* Nested alt sections, else can have large else case */	\
+/* BEGIN_##TYPE##_SECTION */						\
+	/* or	2,2,2; */						\
+	/* or	2,2,2; */						\
+	/* or	2,2,2; */						\
+	/* or	2,2,2; */						\
+/* ##TYPE##_SECTION_ELSE */						\
+/* BEGIN_##TYPE##_SECTION_NESTED(94) */					\
+	/* or	5,5,5; */						\
+	/* or	5,5,5; */						\
+	/* or	5,5,5; */						\
+	/* or	5,5,5; */						\
+/* ##TYPE##_SECTION_ELSE_NESTED(94) */					\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	or	1,1,1;							\
+	or	1,1,1;							\
+/* ALT_##TYPE##_SECTION_END_NESTED(0, 1, 94) */				\
+/* ALT_##TYPE##_SECTION_END(0, 1) */					\
+	or	1,1,1;							\
+	or	1,1,1;
+
+MAKE_MACRO_TEST(FTR);
+MAKE_MACRO_TEST_EXPECTED(FTR);
+
+#ifdef CONFIG_PPC64
+MAKE_MACRO_TEST(FW_FTR);
+MAKE_MACRO_TEST_EXPECTED(FW_FTR);
+#endif
+
+globl(lwsync_fixup_test)
+1:	or	1,1,1
+	LWSYNC
+globl(end_lwsync_fixup_test)
+
+globl(lwsync_fixup_test_expected_LWSYNC)
+1:	or	1,1,1
+	lwsync
+
+globl(lwsync_fixup_test_expected_SYNC)
+1:	or	1,1,1
+	sync
+
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
new file mode 100644
index 000000000..1561094ea
--- /dev/null
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -0,0 +1,843 @@
+/*
+ *  Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ *  Modifications for ppc64:
+ *      Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ *
+ *  Copyright 2008 Michael Ellerman, 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) any later version.
+ */
+
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/sched/mm.h>
+#include <linux/stop_machine.h>
+#include <asm/cputable.h>
+#include <asm/code-patching.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/security_features.h>
+#include <asm/firmware.h>
+
+struct fixup_entry {
+	unsigned long	mask;
+	unsigned long	value;
+	long		start_off;
+	long		end_off;
+	long		alt_start_off;
+	long		alt_end_off;
+};
+
+static unsigned int *calc_addr(struct fixup_entry *fcur, long offset)
+{
+	/*
+	 * We store the offset to the code as a negative offset from
+	 * the start of the alt_entry, to support the VDSO. This
+	 * routine converts that back into an actual address.
+	 */
+	return (unsigned int *)((unsigned long)fcur + offset);
+}
+
+static int patch_alt_instruction(unsigned int *src, unsigned int *dest,
+				 unsigned int *alt_start, unsigned int *alt_end)
+{
+	unsigned int instr;
+
+	instr = *src;
+
+	if (instr_is_relative_branch(*src)) {
+		unsigned int *target = (unsigned int *)branch_target(src);
+
+		/* Branch within the section doesn't need translating */
+		if (target < alt_start || target > alt_end) {
+			instr = translate_branch(dest, src);
+			if (!instr)
+				return 1;
+		}
+	}
+
+	raw_patch_instruction(dest, instr);
+
+	return 0;
+}
+
+static int patch_feature_section(unsigned long value, struct fixup_entry *fcur)
+{
+	unsigned int *start, *end, *alt_start, *alt_end, *src, *dest;
+
+	start = calc_addr(fcur, fcur->start_off);
+	end = calc_addr(fcur, fcur->end_off);
+	alt_start = calc_addr(fcur, fcur->alt_start_off);
+	alt_end = calc_addr(fcur, fcur->alt_end_off);
+
+	if ((alt_end - alt_start) > (end - start))
+		return 1;
+
+	if ((value & fcur->mask) == fcur->value)
+		return 0;
+
+	src = alt_start;
+	dest = start;
+
+	for (; src < alt_end; src++, dest++) {
+		if (patch_alt_instruction(src, dest, alt_start, alt_end))
+			return 1;
+	}
+
+	for (; dest < end; dest++)
+		raw_patch_instruction(dest, PPC_INST_NOP);
+
+	return 0;
+}
+
+void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
+{
+	struct fixup_entry *fcur, *fend;
+
+	fcur = fixup_start;
+	fend = fixup_end;
+
+	for (; fcur < fend; fcur++) {
+		if (patch_feature_section(value, fcur)) {
+			WARN_ON(1);
+			printk("Unable to patch feature section at %p - %p" \
+				" with %p - %p\n",
+				calc_addr(fcur, fcur->start_off),
+				calc_addr(fcur, fcur->end_off),
+				calc_addr(fcur, fcur->alt_start_off),
+				calc_addr(fcur, fcur->alt_end_off));
+		}
+	}
+}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+void do_stf_entry_barrier_fixups(enum stf_barrier_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___stf_entry_barrier_fixup),
+	end = PTRRELOC(&__stop___stf_entry_barrier_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	i = 0;
+	if (types & STF_BARRIER_FALLBACK) {
+		instrs[i++] = 0x7d4802a6; /* mflr r10		*/
+		instrs[i++] = 0x60000000; /* branch patched below */
+		instrs[i++] = 0x7d4803a6; /* mtlr r10		*/
+	} else if (types & STF_BARRIER_EIEIO) {
+		instrs[i++] = 0x7e0006ac; /* eieio + bit 6 hint */
+	} else if (types & STF_BARRIER_SYNC_ORI) {
+		instrs[i++] = 0x7c0004ac; /* hwsync		*/
+		instrs[i++] = 0xe94d0000; /* ld r10,0(r13)	*/
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+
+		if (types & STF_BARRIER_FALLBACK)
+			patch_branch(dest + 1, (unsigned long)&stf_barrier_fallback,
+				     BRANCH_SET_LINK);
+		else
+			patch_instruction(dest + 1, instrs[1]);
+
+		patch_instruction(dest + 2, instrs[2]);
+	}
+
+	printk(KERN_DEBUG "stf-barrier: patched %d entry locations (%s barrier)\n", i,
+		(types == STF_BARRIER_NONE)                  ? "no" :
+		(types == STF_BARRIER_FALLBACK)              ? "fallback" :
+		(types == STF_BARRIER_EIEIO)                 ? "eieio" :
+		(types == (STF_BARRIER_SYNC_ORI))            ? "hwsync"
+		                                           : "unknown");
+}
+
+void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
+{
+	unsigned int instrs[6], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___stf_exit_barrier_fixup),
+	end = PTRRELOC(&__stop___stf_exit_barrier_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+	instrs[3] = 0x60000000; /* nop */
+	instrs[4] = 0x60000000; /* nop */
+	instrs[5] = 0x60000000; /* nop */
+
+	i = 0;
+	if (types & STF_BARRIER_FALLBACK || types & STF_BARRIER_SYNC_ORI) {
+		if (cpu_has_feature(CPU_FTR_HVMODE)) {
+			instrs[i++] = 0x7db14ba6; /* mtspr 0x131, r13 (HSPRG1) */
+			instrs[i++] = 0x7db04aa6; /* mfspr r13, 0x130 (HSPRG0) */
+		} else {
+			instrs[i++] = 0x7db243a6; /* mtsprg 2,r13	*/
+			instrs[i++] = 0x7db142a6; /* mfsprg r13,1    */
+	        }
+		instrs[i++] = 0x7c0004ac; /* hwsync		*/
+		instrs[i++] = 0xe9ad0000; /* ld r13,0(r13)	*/
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		if (cpu_has_feature(CPU_FTR_HVMODE)) {
+			instrs[i++] = 0x7db14aa6; /* mfspr r13, 0x131 (HSPRG1) */
+		} else {
+			instrs[i++] = 0x7db242a6; /* mfsprg r13,2 */
+		}
+	} else if (types & STF_BARRIER_EIEIO) {
+		instrs[i++] = 0x7e0006ac; /* eieio + bit 6 hint */
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+		patch_instruction(dest + 1, instrs[1]);
+		patch_instruction(dest + 2, instrs[2]);
+		patch_instruction(dest + 3, instrs[3]);
+		patch_instruction(dest + 4, instrs[4]);
+		patch_instruction(dest + 5, instrs[5]);
+	}
+	printk(KERN_DEBUG "stf-barrier: patched %d exit locations (%s barrier)\n", i,
+		(types == STF_BARRIER_NONE)                  ? "no" :
+		(types == STF_BARRIER_FALLBACK)              ? "fallback" :
+		(types == STF_BARRIER_EIEIO)                 ? "eieio" :
+		(types == (STF_BARRIER_SYNC_ORI))            ? "hwsync"
+		                                           : "unknown");
+}
+
+static int __do_stf_barrier_fixups(void *data)
+{
+	enum stf_barrier_type *types = data;
+
+	do_stf_entry_barrier_fixups(*types);
+	do_stf_exit_barrier_fixups(*types);
+
+	return 0;
+}
+
+void do_stf_barrier_fixups(enum stf_barrier_type types)
+{
+	/*
+	 * The call to the fallback entry flush, and the fallback/sync-ori exit
+	 * flush can not be safely patched in/out while other CPUs are executing
+	 * them. So call __do_stf_barrier_fixups() on one CPU while all other CPUs
+	 * spin in the stop machine core with interrupts hard disabled.
+	 */
+	stop_machine(__do_stf_barrier_fixups, &types, NULL);
+}
+
+void do_uaccess_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[4], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___uaccess_flush_fixup);
+	end = PTRRELOC(&__stop___uaccess_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+	instrs[3] = 0x4e800020; /* blr */
+
+	i = 0;
+	if (types == L1D_FLUSH_FALLBACK) {
+		instrs[3] = 0x60000000; /* nop */
+		/* fallthrough to fallback flush */
+	}
+
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+
+		patch_instruction((dest + 1), instrs[1]);
+		patch_instruction((dest + 2), instrs[2]);
+		patch_instruction((dest + 3), instrs[3]);
+	}
+
+	printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i,
+		(types == L1D_FLUSH_NONE)       ? "no" :
+		(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
+		(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
+							? "ori+mttrig type"
+							: "ori type" :
+		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
+						: "unknown");
+}
+
+static int __do_entry_flush_fixups(void *data)
+{
+	enum l1d_flush_type types = *(enum l1d_flush_type *)data;
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___entry_flush_fixup);
+	end = PTRRELOC(&__stop___entry_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	i = 0;
+	if (types == L1D_FLUSH_FALLBACK) {
+		instrs[i++] = 0x7d4802a6; /* mflr r10		*/
+		instrs[i++] = 0x60000000; /* branch patched below */
+		instrs[i++] = 0x7d4803a6; /* mtlr r10		*/
+	}
+
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+
+		if (types == L1D_FLUSH_FALLBACK)
+			patch_branch((dest + 1), (unsigned long)&entry_flush_fallback,
+				     BRANCH_SET_LINK);
+		else
+			patch_instruction((dest + 1), instrs[1]);
+
+		patch_instruction((dest + 2), instrs[2]);
+	}
+
+	printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i,
+		(types == L1D_FLUSH_NONE)       ? "no" :
+		(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
+		(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
+							? "ori+mttrig type"
+							: "ori type" :
+		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
+						: "unknown");
+
+	return 0;
+}
+
+void do_entry_flush_fixups(enum l1d_flush_type types)
+{
+	/*
+	 * The call to the fallback flush can not be safely patched in/out while
+	 * other CPUs are executing it. So call __do_entry_flush_fixups() on one
+	 * CPU while all other CPUs spin in the stop machine core with interrupts
+	 * hard disabled.
+	 */
+	stop_machine(__do_entry_flush_fixups, &types, NULL);
+}
+
+void do_rfi_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___rfi_flush_fixup),
+	end = PTRRELOC(&__stop___rfi_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	if (types & L1D_FLUSH_FALLBACK)
+		/* b .+16 to fallback flush */
+		instrs[0] = 0x48000010;
+
+	i = 0;
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+		patch_instruction(dest + 1, instrs[1]);
+		patch_instruction(dest + 2, instrs[2]);
+	}
+
+	printk(KERN_DEBUG "rfi-flush: patched %d locations (%s flush)\n", i,
+		(types == L1D_FLUSH_NONE)       ? "no" :
+		(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
+		(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
+							? "ori+mttrig type"
+							: "ori type" :
+		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
+						: "unknown");
+}
+
+void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end)
+{
+	unsigned int instr, *dest;
+	long *start, *end;
+	int i;
+
+	start = fixup_start;
+	end = fixup_end;
+
+	instr = 0x60000000; /* nop */
+
+	if (enable) {
+		pr_info("barrier-nospec: using ORI speculation barrier\n");
+		instr = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+		patch_instruction(dest, instr);
+	}
+
+	printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i);
+}
+
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+void do_barrier_nospec_fixups(bool enable)
+{
+	void *start, *end;
+
+	start = PTRRELOC(&__start___barrier_nospec_fixup),
+	end = PTRRELOC(&__stop___barrier_nospec_fixup);
+
+	do_barrier_nospec_fixups_range(enable, start, end);
+}
+#endif /* CONFIG_PPC_BARRIER_NOSPEC */
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_end)
+{
+	unsigned int instr[2], *dest;
+	long *start, *end;
+	int i;
+
+	start = fixup_start;
+	end = fixup_end;
+
+	instr[0] = PPC_INST_NOP;
+	instr[1] = PPC_INST_NOP;
+
+	if (enable) {
+		pr_info("barrier-nospec: using isync; sync as speculation barrier\n");
+		instr[0] = PPC_INST_ISYNC;
+		instr[1] = PPC_INST_SYNC;
+	}
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+		patch_instruction(dest, instr[0]);
+		patch_instruction(dest + 1, instr[1]);
+	}
+
+	printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i);
+}
+
+static void patch_btb_flush_section(long *curr)
+{
+	unsigned int *start, *end;
+
+	start = (void *)curr + *curr;
+	end = (void *)curr + *(curr + 1);
+	for (; start < end; start++) {
+		pr_devel("patching dest %lx\n", (unsigned long)start);
+		patch_instruction(start, PPC_INST_NOP);
+	}
+}
+
+void do_btb_flush_fixups(void)
+{
+	long *start, *end;
+
+	start = PTRRELOC(&__start__btb_flush_fixup);
+	end = PTRRELOC(&__stop__btb_flush_fixup);
+
+	for (; start < end; start += 2)
+		patch_btb_flush_section(start);
+}
+#endif /* CONFIG_PPC_FSL_BOOK3E */
+
+void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
+{
+	long *start, *end;
+	unsigned int *dest;
+
+	if (!(value & CPU_FTR_LWSYNC))
+		return ;
+
+	start = fixup_start;
+	end = fixup_end;
+
+	for (; start < end; start++) {
+		dest = (void *)start + *start;
+		raw_patch_instruction(dest, PPC_INST_LWSYNC);
+	}
+}
+
+static void do_final_fixups(void)
+{
+#if defined(CONFIG_PPC64) && defined(CONFIG_RELOCATABLE)
+	int *src, *dest;
+	unsigned long length;
+
+	if (PHYSICAL_START == 0)
+		return;
+
+	src = (int *)(KERNELBASE + PHYSICAL_START);
+	dest = (int *)KERNELBASE;
+	length = (__end_interrupts - _stext) / sizeof(int);
+
+	while (length--) {
+		raw_patch_instruction(dest, *src);
+		src++;
+		dest++;
+	}
+#endif
+}
+
+static unsigned long __initdata saved_cpu_features;
+static unsigned int __initdata saved_mmu_features;
+#ifdef CONFIG_PPC64
+static unsigned long __initdata saved_firmware_features;
+#endif
+
+void __init apply_feature_fixups(void)
+{
+	struct cpu_spec *spec = PTRRELOC(*PTRRELOC(&cur_cpu_spec));
+
+	*PTRRELOC(&saved_cpu_features) = spec->cpu_features;
+	*PTRRELOC(&saved_mmu_features) = spec->mmu_features;
+
+	/*
+	 * Apply the CPU-specific and firmware specific fixups to kernel text
+	 * (nop out sections not relevant to this CPU or this firmware).
+	 */
+	do_feature_fixups(spec->cpu_features,
+			  PTRRELOC(&__start___ftr_fixup),
+			  PTRRELOC(&__stop___ftr_fixup));
+
+	do_feature_fixups(spec->mmu_features,
+			  PTRRELOC(&__start___mmu_ftr_fixup),
+			  PTRRELOC(&__stop___mmu_ftr_fixup));
+
+	do_lwsync_fixups(spec->cpu_features,
+			 PTRRELOC(&__start___lwsync_fixup),
+			 PTRRELOC(&__stop___lwsync_fixup));
+
+#ifdef CONFIG_PPC64
+	saved_firmware_features = powerpc_firmware_features;
+	do_feature_fixups(powerpc_firmware_features,
+			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
+#endif
+	do_final_fixups();
+}
+
+void __init setup_feature_keys(void)
+{
+	/*
+	 * Initialise jump label. This causes all the cpu/mmu_has_feature()
+	 * checks to take on their correct polarity based on the current set of
+	 * CPU/MMU features.
+	 */
+	jump_label_init();
+	cpu_feature_keys_init();
+	mmu_feature_keys_init();
+}
+
+static int __init check_features(void)
+{
+	WARN(saved_cpu_features != cur_cpu_spec->cpu_features,
+	     "CPU features changed after feature patching!\n");
+	WARN(saved_mmu_features != cur_cpu_spec->mmu_features,
+	     "MMU features changed after feature patching!\n");
+#ifdef CONFIG_PPC64
+	WARN(saved_firmware_features != powerpc_firmware_features,
+	     "Firmware features changed after feature patching!\n");
+#endif
+
+	return 0;
+}
+late_initcall(check_features);
+
+#ifdef CONFIG_FTR_FIXUP_SELFTEST
+
+#define check(x)	\
+	if (!(x)) printk("feature-fixups: test failed at line %d\n", __LINE__);
+
+/* This must be after the text it fixes up, vmlinux.lds.S enforces that atm */
+static struct fixup_entry fixup;
+
+static long calc_offset(struct fixup_entry *entry, unsigned int *p)
+{
+	return (unsigned long)p - (unsigned long)entry;
+}
+
+static void test_basic_patching(void)
+{
+	extern unsigned int ftr_fixup_test1[];
+	extern unsigned int end_ftr_fixup_test1[];
+	extern unsigned int ftr_fixup_test1_orig[];
+	extern unsigned int ftr_fixup_test1_expected[];
+	int size = 4 * (end_ftr_fixup_test1 - ftr_fixup_test1);
+
+	fixup.value = fixup.mask = 8;
+	fixup.start_off = calc_offset(&fixup, ftr_fixup_test1 + 1);
+	fixup.end_off = calc_offset(&fixup, ftr_fixup_test1 + 2);
+	fixup.alt_start_off = fixup.alt_end_off = 0;
+
+	/* Sanity check */
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0);
+
+	/* Check we don't patch if the value matches */
+	patch_feature_section(8, &fixup);
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0);
+
+	/* Check we do patch if the value doesn't match */
+	patch_feature_section(0, &fixup);
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_expected, size) == 0);
+
+	/* Check we do patch if the mask doesn't match */
+	memcpy(ftr_fixup_test1, ftr_fixup_test1_orig, size);
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0);
+	patch_feature_section(~8, &fixup);
+	check(memcmp(ftr_fixup_test1, ftr_fixup_test1_expected, size) == 0);
+}
+
+static void test_alternative_patching(void)
+{
+	extern unsigned int ftr_fixup_test2[];
+	extern unsigned int end_ftr_fixup_test2[];
+	extern unsigned int ftr_fixup_test2_orig[];
+	extern unsigned int ftr_fixup_test2_alt[];
+	extern unsigned int ftr_fixup_test2_expected[];
+	int size = 4 * (end_ftr_fixup_test2 - ftr_fixup_test2);
+
+	fixup.value = fixup.mask = 0xF;
+	fixup.start_off = calc_offset(&fixup, ftr_fixup_test2 + 1);
+	fixup.end_off = calc_offset(&fixup, ftr_fixup_test2 + 2);
+	fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test2_alt);
+	fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test2_alt + 1);
+
+	/* Sanity check */
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0);
+
+	/* Check we don't patch if the value matches */
+	patch_feature_section(0xF, &fixup);
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0);
+
+	/* Check we do patch if the value doesn't match */
+	patch_feature_section(0, &fixup);
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_expected, size) == 0);
+
+	/* Check we do patch if the mask doesn't match */
+	memcpy(ftr_fixup_test2, ftr_fixup_test2_orig, size);
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0);
+	patch_feature_section(~0xF, &fixup);
+	check(memcmp(ftr_fixup_test2, ftr_fixup_test2_expected, size) == 0);
+}
+
+static void test_alternative_case_too_big(void)
+{
+	extern unsigned int ftr_fixup_test3[];
+	extern unsigned int end_ftr_fixup_test3[];
+	extern unsigned int ftr_fixup_test3_orig[];
+	extern unsigned int ftr_fixup_test3_alt[];
+	int size = 4 * (end_ftr_fixup_test3 - ftr_fixup_test3);
+
+	fixup.value = fixup.mask = 0xC;
+	fixup.start_off = calc_offset(&fixup, ftr_fixup_test3 + 1);
+	fixup.end_off = calc_offset(&fixup, ftr_fixup_test3 + 2);
+	fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test3_alt);
+	fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test3_alt + 2);
+
+	/* Sanity check */
+	check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0);
+
+	/* Expect nothing to be patched, and the error returned to us */
+	check(patch_feature_section(0xF, &fixup) == 1);
+	check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0);
+	check(patch_feature_section(0, &fixup) == 1);
+	check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0);
+	check(patch_feature_section(~0xF, &fixup) == 1);
+	check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0);
+}
+
+static void test_alternative_case_too_small(void)
+{
+	extern unsigned int ftr_fixup_test4[];
+	extern unsigned int end_ftr_fixup_test4[];
+	extern unsigned int ftr_fixup_test4_orig[];
+	extern unsigned int ftr_fixup_test4_alt[];
+	extern unsigned int ftr_fixup_test4_expected[];
+	int size = 4 * (end_ftr_fixup_test4 - ftr_fixup_test4);
+	unsigned long flag;
+
+	/* Check a high-bit flag */
+	flag = 1UL << ((sizeof(unsigned long) - 1) * 8);
+	fixup.value = fixup.mask = flag;
+	fixup.start_off = calc_offset(&fixup, ftr_fixup_test4 + 1);
+	fixup.end_off = calc_offset(&fixup, ftr_fixup_test4 + 5);
+	fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test4_alt);
+	fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test4_alt + 2);
+
+	/* Sanity check */
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0);
+
+	/* Check we don't patch if the value matches */
+	patch_feature_section(flag, &fixup);
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0);
+
+	/* Check we do patch if the value doesn't match */
+	patch_feature_section(0, &fixup);
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_expected, size) == 0);
+
+	/* Check we do patch if the mask doesn't match */
+	memcpy(ftr_fixup_test4, ftr_fixup_test4_orig, size);
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0);
+	patch_feature_section(~flag, &fixup);
+	check(memcmp(ftr_fixup_test4, ftr_fixup_test4_expected, size) == 0);
+}
+
+static void test_alternative_case_with_branch(void)
+{
+	extern unsigned int ftr_fixup_test5[];
+	extern unsigned int end_ftr_fixup_test5[];
+	extern unsigned int ftr_fixup_test5_expected[];
+	int size = 4 * (end_ftr_fixup_test5 - ftr_fixup_test5);
+
+	check(memcmp(ftr_fixup_test5, ftr_fixup_test5_expected, size) == 0);
+}
+
+static void test_alternative_case_with_external_branch(void)
+{
+	extern unsigned int ftr_fixup_test6[];
+	extern unsigned int end_ftr_fixup_test6[];
+	extern unsigned int ftr_fixup_test6_expected[];
+	int size = 4 * (end_ftr_fixup_test6 - ftr_fixup_test6);
+
+	check(memcmp(ftr_fixup_test6, ftr_fixup_test6_expected, size) == 0);
+}
+
+static void test_alternative_case_with_branch_to_end(void)
+{
+	extern unsigned int ftr_fixup_test7[];
+	extern unsigned int end_ftr_fixup_test7[];
+	extern unsigned int ftr_fixup_test7_expected[];
+	int size = 4 * (end_ftr_fixup_test7 - ftr_fixup_test7);
+
+	check(memcmp(ftr_fixup_test7, ftr_fixup_test7_expected, size) == 0);
+}
+
+static void test_cpu_macros(void)
+{
+	extern u8 ftr_fixup_test_FTR_macros[];
+	extern u8 ftr_fixup_test_FTR_macros_expected[];
+	unsigned long size = ftr_fixup_test_FTR_macros_expected -
+			     ftr_fixup_test_FTR_macros;
+
+	/* The fixups have already been done for us during boot */
+	check(memcmp(ftr_fixup_test_FTR_macros,
+		     ftr_fixup_test_FTR_macros_expected, size) == 0);
+}
+
+static void test_fw_macros(void)
+{
+#ifdef CONFIG_PPC64
+	extern u8 ftr_fixup_test_FW_FTR_macros[];
+	extern u8 ftr_fixup_test_FW_FTR_macros_expected[];
+	unsigned long size = ftr_fixup_test_FW_FTR_macros_expected -
+			     ftr_fixup_test_FW_FTR_macros;
+
+	/* The fixups have already been done for us during boot */
+	check(memcmp(ftr_fixup_test_FW_FTR_macros,
+		     ftr_fixup_test_FW_FTR_macros_expected, size) == 0);
+#endif
+}
+
+static void test_lwsync_macros(void)
+{
+	extern u8 lwsync_fixup_test[];
+	extern u8 end_lwsync_fixup_test[];
+	extern u8 lwsync_fixup_test_expected_LWSYNC[];
+	extern u8 lwsync_fixup_test_expected_SYNC[];
+	unsigned long size = end_lwsync_fixup_test -
+			     lwsync_fixup_test;
+
+	/* The fixups have already been done for us during boot */
+	if (cur_cpu_spec->cpu_features & CPU_FTR_LWSYNC) {
+		check(memcmp(lwsync_fixup_test,
+			     lwsync_fixup_test_expected_LWSYNC, size) == 0);
+	} else {
+		check(memcmp(lwsync_fixup_test,
+			     lwsync_fixup_test_expected_SYNC, size) == 0);
+	}
+}
+
+static int __init test_feature_fixups(void)
+{
+	printk(KERN_DEBUG "Running feature fixup self-tests ...\n");
+
+	test_basic_patching();
+	test_alternative_patching();
+	test_alternative_case_too_big();
+	test_alternative_case_too_small();
+	test_alternative_case_with_branch();
+	test_alternative_case_with_external_branch();
+	test_alternative_case_with_branch_to_end();
+	test_cpu_macros();
+	test_fw_macros();
+	test_lwsync_macros();
+
+	return 0;
+}
+late_initcall(test_feature_fixups);
+
+#endif /* CONFIG_FTR_FIXUP_SELFTEST */
diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S
new file mode 100644
index 000000000..0526b2225
--- /dev/null
+++ b/arch/powerpc/lib/hweight_64.S
@@ -0,0 +1,116 @@
+/*
+ * 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.
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2010
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/feature-fixups.h>
+
+/* Note: This code relies on -mminimal-toc */
+
+_GLOBAL(__arch_hweight8)
+BEGIN_FTR_SECTION
+	b __sw_hweight8
+	nop
+	nop
+FTR_SECTION_ELSE
+	PPC_POPCNTB(R3,R3)
+	clrldi	r3,r3,64-8
+	blr
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+EXPORT_SYMBOL(__arch_hweight8)
+
+_GLOBAL(__arch_hweight16)
+BEGIN_FTR_SECTION
+	b __sw_hweight16
+	nop
+	nop
+	nop
+	nop
+FTR_SECTION_ELSE
+  BEGIN_FTR_SECTION_NESTED(50)
+	PPC_POPCNTB(R3,R3)
+	srdi	r4,r3,8
+	add	r3,r4,r3
+	clrldi	r3,r3,64-8
+	blr
+  FTR_SECTION_ELSE_NESTED(50)
+	clrlwi  r3,r3,16
+	PPC_POPCNTW(R3,R3)
+	clrldi	r3,r3,64-8
+	blr
+  ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 50)
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+EXPORT_SYMBOL(__arch_hweight16)
+
+_GLOBAL(__arch_hweight32)
+BEGIN_FTR_SECTION
+	b __sw_hweight32
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+FTR_SECTION_ELSE
+  BEGIN_FTR_SECTION_NESTED(51)
+	PPC_POPCNTB(R3,R3)
+	srdi	r4,r3,16
+	add	r3,r4,r3
+	srdi	r4,r3,8
+	add	r3,r4,r3
+	clrldi	r3,r3,64-8
+	blr
+  FTR_SECTION_ELSE_NESTED(51)
+	PPC_POPCNTW(R3,R3)
+	clrldi	r3,r3,64-8
+	blr
+  ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 51)
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+EXPORT_SYMBOL(__arch_hweight32)
+
+_GLOBAL(__arch_hweight64)
+BEGIN_FTR_SECTION
+	b __sw_hweight64
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+FTR_SECTION_ELSE
+  BEGIN_FTR_SECTION_NESTED(52)
+	PPC_POPCNTB(R3,R3)
+	srdi	r4,r3,32
+	add	r3,r4,r3
+	srdi	r4,r3,16
+	add	r3,r4,r3
+	srdi	r4,r3,8
+	add	r3,r4,r3
+	clrldi	r3,r3,64-8
+	blr
+  FTR_SECTION_ELSE_NESTED(52)
+	PPC_POPCNTD(R3,R3)
+	clrldi	r3,r3,64-8
+	blr
+  ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 52)
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+EXPORT_SYMBOL(__arch_hweight64)
diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S
new file mode 100644
index 000000000..32e91994b
--- /dev/null
+++ b/arch/powerpc/lib/ldstfp.S
@@ -0,0 +1,245 @@
+/*
+ * Floating-point, VMX/Altivec and VSX loads and stores
+ * for use in instruction emulation.
+ *
+ * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ *  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>
+#include <asm/ppc-opcode.h>
+#include <asm/reg.h>
+#include <asm/asm-offsets.h>
+#include <asm/asm-compat.h>
+#include <linux/errno.h>
+
+#ifdef CONFIG_PPC_FPU
+
+#define STKFRM	(PPC_MIN_STKFRM + 16)
+
+/* Get the contents of frN into *p; N is in r3 and p is in r4. */
+_GLOBAL(get_fpr)
+	mflr	r0
+	mfmsr	r6
+	ori	r7, r6, MSR_FP
+	MTMSRD(r7)
+	isync
+	rlwinm	r3,r3,3,0xf8
+	bcl	20,31,1f
+reg = 0
+	.rept	32
+	stfd	reg, 0(r4)
+	b	2f
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+2:	MTMSRD(r6)
+	isync
+	blr
+
+/* Put the contents of *p into frN; N is in r3 and p is in r4. */
+_GLOBAL(put_fpr)
+	mflr	r0
+	mfmsr	r6
+	ori	r7, r6, MSR_FP
+	MTMSRD(r7)
+	isync
+	rlwinm	r3,r3,3,0xf8
+	bcl	20,31,1f
+reg = 0
+	.rept	32
+	lfd	reg, 0(r4)
+	b	2f
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+2:	MTMSRD(r6)
+	isync
+	blr
+
+#ifdef CONFIG_ALTIVEC
+/* Get the contents of vrN into *p; N is in r3 and p is in r4. */
+_GLOBAL(get_vr)
+	mflr	r0
+	mfmsr	r6
+	oris	r7, r6, MSR_VEC@h
+	MTMSRD(r7)
+	isync
+	rlwinm	r3,r3,3,0xf8
+	bcl	20,31,1f
+reg = 0
+	.rept	32
+	stvx	reg, 0, r4
+	b	2f
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+2:	MTMSRD(r6)
+	isync
+	blr
+
+/* Put the contents of *p into vrN; N is in r3 and p is in r4. */
+_GLOBAL(put_vr)
+	mflr	r0
+	mfmsr	r6
+	oris	r7, r6, MSR_VEC@h
+	MTMSRD(r7)
+	isync
+	rlwinm	r3,r3,3,0xf8
+	bcl	20,31,1f
+reg = 0
+	.rept	32
+	lvx	reg, 0, r4
+	b	2f
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+2:	MTMSRD(r6)
+	isync
+	blr
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+/* Get the contents of vsN into vs0; N is in r3. */
+_GLOBAL(get_vsr)
+	mflr	r0
+	rlwinm	r3,r3,3,0x1f8
+	bcl	20,31,1f
+	blr			/* vs0 is already in vs0 */
+	nop
+reg = 1
+	.rept	63
+	XXLOR(0,reg,reg)
+	blr
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+
+/* Put the contents of vs0 into vsN; N is in r3. */
+_GLOBAL(put_vsr)
+	mflr	r0
+	rlwinm	r3,r3,3,0x1f8
+	bcl	20,31,1f
+	blr			/* v0 is already in v0 */
+	nop
+reg = 1
+	.rept	63
+	XXLOR(reg,0,0)
+	blr
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+
+/* Load VSX reg N from vector doubleword *p.  N is in r3, p in r4. */
+_GLOBAL(load_vsrn)
+	PPC_STLU r1,-STKFRM(r1)
+	mflr	r0
+	PPC_STL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mfmsr	r6
+	oris	r7,r6,MSR_VSX@h
+	cmpwi	cr7,r3,0
+	li	r8,STKFRM-16
+	MTMSRD(r7)
+	isync
+	beq	cr7,1f
+	STXVD2X(0,R1,R8)
+1:	LXVD2X(0,R0,R4)
+#ifdef __LITTLE_ENDIAN__
+	XXSWAPD(0,0)
+#endif
+	beq	cr7,4f
+	bl	put_vsr
+	LXVD2X(0,R1,R8)
+4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	MTMSRD(r6)
+	isync
+	addi	r1,r1,STKFRM
+	blr
+
+/* Store VSX reg N to vector doubleword *p.  N is in r3, p in r4. */
+_GLOBAL(store_vsrn)
+	PPC_STLU r1,-STKFRM(r1)
+	mflr	r0
+	PPC_STL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mfmsr	r6
+	oris	r7,r6,MSR_VSX@h
+	li	r8,STKFRM-16
+	MTMSRD(r7)
+	isync
+	STXVD2X(0,R1,R8)
+	bl	get_vsr
+#ifdef __LITTLE_ENDIAN__
+	XXSWAPD(0,0)
+#endif
+	STXVD2X(0,R0,R4)
+	LXVD2X(0,R1,R8)
+	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	MTMSRD(r6)
+	isync
+	mr	r3,r9
+	addi	r1,r1,STKFRM
+	blr
+#endif /* CONFIG_VSX */
+
+/* Convert single-precision to double, without disturbing FPRs. */
+/* conv_sp_to_dp(float *sp, double *dp) */
+_GLOBAL(conv_sp_to_dp)
+	mfmsr	r6
+	ori	r7, r6, MSR_FP
+	MTMSRD(r7)
+	isync
+	stfd	fr0, -16(r1)
+	lfs	fr0, 0(r3)
+	stfd	fr0, 0(r4)
+	lfd	fr0, -16(r1)
+	MTMSRD(r6)
+	isync
+	blr
+
+/* Convert single-precision to double, without disturbing FPRs. */
+/* conv_sp_to_dp(double *dp, float *sp) */
+_GLOBAL(conv_dp_to_sp)
+	mfmsr	r6
+	ori	r7, r6, MSR_FP
+	MTMSRD(r7)
+	isync
+	stfd	fr0, -16(r1)
+	lfd	fr0, 0(r3)
+	stfs	fr0, 0(r4)
+	lfd	fr0, -16(r1)
+	MTMSRD(r6)
+	isync
+	blr
+
+#endif	/* CONFIG_PPC_FPU */
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
new file mode 100644
index 000000000..35a0ef932
--- /dev/null
+++ b/arch/powerpc/lib/locks.c
@@ -0,0 +1,69 @@
+/*
+ * 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/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/export.h>
+#include <linux/smp.h>
+
+/* waiting for a spinlock... */
+#if defined(CONFIG_PPC_SPLPAR)
+#include <asm/hvcall.h>
+#include <asm/smp.h>
+
+void __spin_yield(arch_spinlock_t *lock)
+{
+	unsigned int lock_value, holder_cpu, yield_count;
+
+	lock_value = lock->slock;
+	if (lock_value == 0)
+		return;
+	holder_cpu = lock_value & 0xffff;
+	BUG_ON(holder_cpu >= NR_CPUS);
+	yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count);
+	if ((yield_count & 1) == 0)
+		return;		/* virtual cpu is currently running */
+	rmb();
+	if (lock->slock != lock_value)
+		return;		/* something has changed */
+	plpar_hcall_norets(H_CONFER,
+		get_hard_smp_processor_id(holder_cpu), yield_count);
+}
+EXPORT_SYMBOL_GPL(__spin_yield);
+
+/*
+ * 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(arch_rwlock_t *rw)
+{
+	int lock_value;
+	unsigned int holder_cpu, yield_count;
+
+	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);
+	yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count);
+	if ((yield_count & 1) == 0)
+		return;		/* virtual cpu is currently running */
+	rmb();
+	if (rw->lock != lock_value)
+		return;		/* something has changed */
+	plpar_hcall_norets(H_CONFER,
+		get_hard_smp_processor_id(holder_cpu), yield_count);
+}
+#endif
diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S
new file mode 100644
index 000000000..ec531de99
--- /dev/null
+++ b/arch/powerpc/lib/mem_64.S
@@ -0,0 +1,141 @@
+/*
+ * 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>
+#include <asm/export.h>
+
+_GLOBAL(__memset16)
+	rlwimi	r4,r4,16,0,15
+	/* fall through */
+
+_GLOBAL(__memset32)
+	rldimi	r4,r4,32,0
+	/* fall through */
+
+_GLOBAL(__memset64)
+	neg	r0,r3
+	andi.	r0,r0,7
+	cmplw	cr1,r5,r0
+	b	.Lms
+EXPORT_SYMBOL(__memset16)
+EXPORT_SYMBOL(__memset32)
+EXPORT_SYMBOL(__memset64)
+
+_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
+.Lms:	PPC_MTOCRF(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
+	.balign 16
+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
+	PPC_MTOCRF(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
+	PPC_MTOCRF(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
+EXPORT_SYMBOL(memset)
+
+_GLOBAL_TOC(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
+	.balign 16
+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
+EXPORT_SYMBOL(memmove)
diff --git a/arch/powerpc/lib/memcmp_32.S b/arch/powerpc/lib/memcmp_32.S
new file mode 100644
index 000000000..5010e376f
--- /dev/null
+++ b/arch/powerpc/lib/memcmp_32.S
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * memcmp for PowerPC32
+ *
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+
+	.text
+
+_GLOBAL(memcmp)
+	srawi.	r7, r5, 2		/* Divide len by 4 */
+	mr	r6, r3
+	beq-	3f
+	mtctr	r7
+	li	r7, 0
+1:	lwzx	r3, r6, r7
+	lwzx	r0, r4, r7
+	addi	r7, r7, 4
+	cmplw	cr0, r3, r0
+	bdnzt	eq, 1b
+	bne	5f
+3:	andi.	r3, r5, 3
+	beqlr
+	cmplwi	cr1, r3, 2
+	blt-	cr1, 4f
+	lhzx	r3, r6, r7
+	lhzx	r0, r4, r7
+	addi	r7, r7, 2
+	subf.	r3, r0, r3
+	beqlr	cr1
+	bnelr
+4:	lbzx	r3, r6, r7
+	lbzx	r0, r4, r7
+	subf.	r3, r0, r3
+	blr
+5:	li	r3, 1
+	bgtlr
+	li	r3, -1
+	blr
+EXPORT_SYMBOL(memcmp)
diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S
new file mode 100644
index 000000000..b7f6f6e0b
--- /dev/null
+++ b/arch/powerpc/lib/memcmp_64.S
@@ -0,0 +1,642 @@
+/*
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ * Copyright 2015 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) any later version.
+ */
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/ppc-opcode.h>
+
+#define off8	r6
+#define off16	r7
+#define off24	r8
+
+#define rA	r9
+#define rB	r10
+#define rC	r11
+#define rD	r27
+#define rE	r28
+#define rF	r29
+#define rG	r30
+#define rH	r31
+
+#ifdef __LITTLE_ENDIAN__
+#define LH	lhbrx
+#define LW	lwbrx
+#define LD	ldbrx
+#define LVS	lvsr
+#define VPERM(_VRT,_VRA,_VRB,_VRC) \
+	vperm _VRT,_VRB,_VRA,_VRC
+#else
+#define LH	lhzx
+#define LW	lwzx
+#define LD	ldx
+#define LVS	lvsl
+#define VPERM(_VRT,_VRA,_VRB,_VRC) \
+	vperm _VRT,_VRA,_VRB,_VRC
+#endif
+
+#define VMX_THRESH 4096
+#define ENTER_VMX_OPS	\
+	mflr    r0;	\
+	std     r3,-STACKFRAMESIZE+STK_REG(R31)(r1); \
+	std     r4,-STACKFRAMESIZE+STK_REG(R30)(r1); \
+	std     r5,-STACKFRAMESIZE+STK_REG(R29)(r1); \
+	std     r0,16(r1); \
+	stdu    r1,-STACKFRAMESIZE(r1); \
+	bl      enter_vmx_ops; \
+	cmpwi   cr1,r3,0; \
+	ld      r0,STACKFRAMESIZE+16(r1); \
+	ld      r3,STK_REG(R31)(r1); \
+	ld      r4,STK_REG(R30)(r1); \
+	ld      r5,STK_REG(R29)(r1); \
+	addi	r1,r1,STACKFRAMESIZE; \
+	mtlr    r0
+
+#define EXIT_VMX_OPS \
+	mflr    r0; \
+	std     r3,-STACKFRAMESIZE+STK_REG(R31)(r1); \
+	std     r4,-STACKFRAMESIZE+STK_REG(R30)(r1); \
+	std     r5,-STACKFRAMESIZE+STK_REG(R29)(r1); \
+	std     r0,16(r1); \
+	stdu    r1,-STACKFRAMESIZE(r1); \
+	bl      exit_vmx_ops; \
+	ld      r0,STACKFRAMESIZE+16(r1); \
+	ld      r3,STK_REG(R31)(r1); \
+	ld      r4,STK_REG(R30)(r1); \
+	ld      r5,STK_REG(R29)(r1); \
+	addi	r1,r1,STACKFRAMESIZE; \
+	mtlr    r0
+
+/*
+ * LD_VSR_CROSS16B load the 2nd 16 bytes for _vaddr which is unaligned with
+ * 16 bytes boundary and permute the result with the 1st 16 bytes.
+
+ *    |  y y y y y y y y y y y y y 0 1 2 | 3 4 5 6 7 8 9 a b c d e f z z z |
+ *    ^                                  ^                                 ^
+ * 0xbbbb10                          0xbbbb20                          0xbbb30
+ *                                 ^
+ *                                _vaddr
+ *
+ *
+ * _vmask is the mask generated by LVS
+ * _v1st_qw is the 1st aligned QW of current addr which is already loaded.
+ *   for example: 0xyyyyyyyyyyyyy012 for big endian
+ * _v2nd_qw is the 2nd aligned QW of cur _vaddr to be loaded.
+ *   for example: 0x3456789abcdefzzz for big endian
+ * The permute result is saved in _v_res.
+ *   for example: 0x0123456789abcdef for big endian.
+ */
+#define LD_VSR_CROSS16B(_vaddr,_vmask,_v1st_qw,_v2nd_qw,_v_res) \
+        lvx     _v2nd_qw,_vaddr,off16; \
+        VPERM(_v_res,_v1st_qw,_v2nd_qw,_vmask)
+
+/*
+ * There are 2 categories for memcmp:
+ * 1) src/dst has the same offset to the 8 bytes boundary. The handlers
+ * are named like .Lsameoffset_xxxx
+ * 2) src/dst has different offset to the 8 bytes boundary. The handlers
+ * are named like .Ldiffoffset_xxxx
+ */
+_GLOBAL_TOC(memcmp)
+	cmpdi	cr1,r5,0
+
+	/* Use the short loop if the src/dst addresses are not
+	 * with the same offset of 8 bytes align boundary.
+	 */
+	xor	r6,r3,r4
+	andi.	r6,r6,7
+
+	/* Fall back to short loop if compare at aligned addrs
+	 * with less than 8 bytes.
+	 */
+	cmpdi   cr6,r5,7
+
+	beq	cr1,.Lzero
+	bgt	cr6,.Lno_short
+
+.Lshort:
+	mtctr	r5
+1:	lbz	rA,0(r3)
+	lbz	rB,0(r4)
+	subf.	rC,rB,rA
+	bne	.Lnon_zero
+	bdz	.Lzero
+
+	lbz	rA,1(r3)
+	lbz	rB,1(r4)
+	subf.	rC,rB,rA
+	bne	.Lnon_zero
+	bdz	.Lzero
+
+	lbz	rA,2(r3)
+	lbz	rB,2(r4)
+	subf.	rC,rB,rA
+	bne	.Lnon_zero
+	bdz	.Lzero
+
+	lbz	rA,3(r3)
+	lbz	rB,3(r4)
+	subf.	rC,rB,rA
+	bne	.Lnon_zero
+
+	addi	r3,r3,4
+	addi	r4,r4,4
+
+	bdnz	1b
+
+.Lzero:
+	li	r3,0
+	blr
+
+.Lno_short:
+	dcbt	0,r3
+	dcbt	0,r4
+	bne	.Ldiffoffset_8bytes_make_align_start
+
+
+.Lsameoffset_8bytes_make_align_start:
+	/* attempt to compare bytes not aligned with 8 bytes so that
+	 * rest comparison can run based on 8 bytes alignment.
+	 */
+	andi.   r6,r3,7
+
+	/* Try to compare the first double word which is not 8 bytes aligned:
+	 * load the first double word at (src & ~7UL) and shift left appropriate
+	 * bits before comparision.
+	 */
+	rlwinm  r6,r3,3,26,28
+	beq     .Lsameoffset_8bytes_aligned
+	clrrdi	r3,r3,3
+	clrrdi	r4,r4,3
+	LD	rA,0,r3
+	LD	rB,0,r4
+	sld	rA,rA,r6
+	sld	rB,rB,r6
+	cmpld	cr0,rA,rB
+	srwi	r6,r6,3
+	bne	cr0,.LcmpAB_lightweight
+	subfic  r6,r6,8
+	subf.	r5,r6,r5
+	addi	r3,r3,8
+	addi	r4,r4,8
+	beq	.Lzero
+
+.Lsameoffset_8bytes_aligned:
+	/* now we are aligned with 8 bytes.
+	 * Use .Llong loop if left cmp bytes are equal or greater than 32B.
+	 */
+	cmpdi   cr6,r5,31
+	bgt	cr6,.Llong
+
+.Lcmp_lt32bytes:
+	/* compare 1 ~ 31 bytes, at least r3 addr is 8 bytes aligned now */
+	cmpdi   cr5,r5,7
+	srdi    r0,r5,3
+	ble	cr5,.Lcmp_rest_lt8bytes
+
+	/* handle 8 ~ 31 bytes */
+	clrldi  r5,r5,61
+	mtctr   r0
+2:
+	LD	rA,0,r3
+	LD	rB,0,r4
+	cmpld	cr0,rA,rB
+	addi	r3,r3,8
+	addi	r4,r4,8
+	bne	cr0,.LcmpAB_lightweight
+	bdnz	2b
+
+	cmpwi   r5,0
+	beq	.Lzero
+
+.Lcmp_rest_lt8bytes:
+	/*
+	 * Here we have less than 8 bytes to compare. At least s1 is aligned to
+	 * 8 bytes, but s2 may not be. We must make sure s2 + 7 doesn't cross a
+	 * page boundary, otherwise we might read past the end of the buffer and
+	 * trigger a page fault. We use 4K as the conservative minimum page
+	 * size. If we detect that case we go to the byte-by-byte loop.
+	 *
+	 * Otherwise the next double word is loaded from s1 and s2, and shifted
+	 * right to compare the appropriate bits.
+	 */
+	clrldi	r6,r4,(64-12)	// r6 = r4 & 0xfff
+	cmpdi	r6,0xff8
+	bgt	.Lshort
+
+	subfic  r6,r5,8
+	slwi	r6,r6,3
+	LD	rA,0,r3
+	LD	rB,0,r4
+	srd	rA,rA,r6
+	srd	rB,rB,r6
+	cmpld	cr0,rA,rB
+	bne	cr0,.LcmpAB_lightweight
+	b	.Lzero
+
+.Lnon_zero:
+	mr	r3,rC
+	blr
+
+.Llong:
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+	/* Try to use vmx loop if length is equal or greater than 4K */
+	cmpldi  cr6,r5,VMX_THRESH
+	bge	cr6,.Lsameoffset_vmx_cmp
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
+.Llong_novmx_cmp:
+#endif
+	/* At least s1 addr is aligned with 8 bytes */
+	li	off8,8
+	li	off16,16
+	li	off24,24
+
+	std	r31,-8(r1)
+	std	r30,-16(r1)
+	std	r29,-24(r1)
+	std	r28,-32(r1)
+	std	r27,-40(r1)
+
+	srdi	r0,r5,5
+	mtctr	r0
+	andi.	r5,r5,31
+
+	LD	rA,0,r3
+	LD	rB,0,r4
+
+	LD	rC,off8,r3
+	LD	rD,off8,r4
+
+	LD	rE,off16,r3
+	LD	rF,off16,r4
+
+	LD	rG,off24,r3
+	LD	rH,off24,r4
+	cmpld	cr0,rA,rB
+
+	addi	r3,r3,32
+	addi	r4,r4,32
+
+	bdz	.Lfirst32
+
+	LD	rA,0,r3
+	LD	rB,0,r4
+	cmpld	cr1,rC,rD
+
+	LD	rC,off8,r3
+	LD	rD,off8,r4
+	cmpld	cr6,rE,rF
+
+	LD	rE,off16,r3
+	LD	rF,off16,r4
+	cmpld	cr7,rG,rH
+	bne	cr0,.LcmpAB
+
+	LD	rG,off24,r3
+	LD	rH,off24,r4
+	cmpld	cr0,rA,rB
+	bne	cr1,.LcmpCD
+
+	addi	r3,r3,32
+	addi	r4,r4,32
+
+	bdz	.Lsecond32
+
+	.balign	16
+
+1:	LD	rA,0,r3
+	LD	rB,0,r4
+	cmpld	cr1,rC,rD
+	bne	cr6,.LcmpEF
+
+	LD	rC,off8,r3
+	LD	rD,off8,r4
+	cmpld	cr6,rE,rF
+	bne	cr7,.LcmpGH
+
+	LD	rE,off16,r3
+	LD	rF,off16,r4
+	cmpld	cr7,rG,rH
+	bne	cr0,.LcmpAB
+
+	LD	rG,off24,r3
+	LD	rH,off24,r4
+	cmpld	cr0,rA,rB
+	bne	cr1,.LcmpCD
+
+	addi	r3,r3,32
+	addi	r4,r4,32
+
+	bdnz	1b
+
+.Lsecond32:
+	cmpld	cr1,rC,rD
+	bne	cr6,.LcmpEF
+
+	cmpld	cr6,rE,rF
+	bne	cr7,.LcmpGH
+
+	cmpld	cr7,rG,rH
+	bne	cr0,.LcmpAB
+
+	bne	cr1,.LcmpCD
+	bne	cr6,.LcmpEF
+	bne	cr7,.LcmpGH
+
+.Ltail:
+	ld	r31,-8(r1)
+	ld	r30,-16(r1)
+	ld	r29,-24(r1)
+	ld	r28,-32(r1)
+	ld	r27,-40(r1)
+
+	cmpdi	r5,0
+	beq	.Lzero
+	b	.Lshort
+
+.Lfirst32:
+	cmpld	cr1,rC,rD
+	cmpld	cr6,rE,rF
+	cmpld	cr7,rG,rH
+
+	bne	cr0,.LcmpAB
+	bne	cr1,.LcmpCD
+	bne	cr6,.LcmpEF
+	bne	cr7,.LcmpGH
+
+	b	.Ltail
+
+.LcmpAB:
+	li	r3,1
+	bgt	cr0,.Lout
+	li	r3,-1
+	b	.Lout
+
+.LcmpCD:
+	li	r3,1
+	bgt	cr1,.Lout
+	li	r3,-1
+	b	.Lout
+
+.LcmpEF:
+	li	r3,1
+	bgt	cr6,.Lout
+	li	r3,-1
+	b	.Lout
+
+.LcmpGH:
+	li	r3,1
+	bgt	cr7,.Lout
+	li	r3,-1
+
+.Lout:
+	ld	r31,-8(r1)
+	ld	r30,-16(r1)
+	ld	r29,-24(r1)
+	ld	r28,-32(r1)
+	ld	r27,-40(r1)
+	blr
+
+.LcmpAB_lightweight:   /* skip NV GPRS restore */
+	li	r3,1
+	bgtlr
+	li	r3,-1
+	blr
+
+#ifdef CONFIG_ALTIVEC
+.Lsameoffset_vmx_cmp:
+	/* Enter with src/dst addrs has the same offset with 8 bytes
+	 * align boundary.
+	 *
+	 * There is an optimization based on following fact: memcmp()
+	 * prones to fail early at the first 32 bytes.
+	 * Before applying VMX instructions which will lead to 32x128bits
+	 * VMX regs load/restore penalty, we compare the first 32 bytes
+	 * so that we can catch the ~80% fail cases.
+	 */
+
+	li	r0,4
+	mtctr	r0
+.Lsameoffset_prechk_32B_loop:
+	LD	rA,0,r3
+	LD	rB,0,r4
+	cmpld	cr0,rA,rB
+	addi	r3,r3,8
+	addi	r4,r4,8
+	bne     cr0,.LcmpAB_lightweight
+	addi	r5,r5,-8
+	bdnz	.Lsameoffset_prechk_32B_loop
+
+	ENTER_VMX_OPS
+	beq     cr1,.Llong_novmx_cmp
+
+3:
+	/* need to check whether r4 has the same offset with r3
+	 * for 16 bytes boundary.
+	 */
+	xor	r0,r3,r4
+	andi.	r0,r0,0xf
+	bne	.Ldiffoffset_vmx_cmp_start
+
+	/* len is no less than 4KB. Need to align with 16 bytes further.
+	 */
+	andi.	rA,r3,8
+	LD	rA,0,r3
+	beq	4f
+	LD	rB,0,r4
+	cmpld	cr0,rA,rB
+	addi	r3,r3,8
+	addi	r4,r4,8
+	addi	r5,r5,-8
+
+	beq	cr0,4f
+	/* save and restore cr0 */
+	mfocrf  r5,128
+	EXIT_VMX_OPS
+	mtocrf  128,r5
+	b	.LcmpAB_lightweight
+
+4:
+	/* compare 32 bytes for each loop */
+	srdi	r0,r5,5
+	mtctr	r0
+	clrldi  r5,r5,59
+	li	off16,16
+
+.balign 16
+5:
+	lvx 	v0,0,r3
+	lvx 	v1,0,r4
+	VCMPEQUD_RC(v0,v0,v1)
+	bnl	cr6,7f
+	lvx 	v0,off16,r3
+	lvx 	v1,off16,r4
+	VCMPEQUD_RC(v0,v0,v1)
+	bnl	cr6,6f
+	addi	r3,r3,32
+	addi	r4,r4,32
+	bdnz	5b
+
+	EXIT_VMX_OPS
+	cmpdi	r5,0
+	beq	.Lzero
+	b	.Lcmp_lt32bytes
+
+6:
+	addi	r3,r3,16
+	addi	r4,r4,16
+
+7:
+	/* diff the last 16 bytes */
+	EXIT_VMX_OPS
+	LD	rA,0,r3
+	LD	rB,0,r4
+	cmpld	cr0,rA,rB
+	li	off8,8
+	bne	cr0,.LcmpAB_lightweight
+
+	LD	rA,off8,r3
+	LD	rB,off8,r4
+	cmpld	cr0,rA,rB
+	bne	cr0,.LcmpAB_lightweight
+	b	.Lzero
+#endif
+
+.Ldiffoffset_8bytes_make_align_start:
+	/* now try to align s1 with 8 bytes */
+	rlwinm  r6,r3,3,26,28
+	beq     .Ldiffoffset_align_s1_8bytes
+
+	clrrdi	r3,r3,3
+	LD	rA,0,r3
+	LD	rB,0,r4  /* unaligned load */
+	sld	rA,rA,r6
+	srd	rA,rA,r6
+	srd	rB,rB,r6
+	cmpld	cr0,rA,rB
+	srwi	r6,r6,3
+	bne	cr0,.LcmpAB_lightweight
+
+	subfic  r6,r6,8
+	subf.	r5,r6,r5
+	addi	r3,r3,8
+	add	r4,r4,r6
+
+	beq	.Lzero
+
+.Ldiffoffset_align_s1_8bytes:
+	/* now s1 is aligned with 8 bytes. */
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+	/* only do vmx ops when the size equal or greater than 4K bytes */
+	cmpdi	cr5,r5,VMX_THRESH
+	bge	cr5,.Ldiffoffset_vmx_cmp
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
+.Ldiffoffset_novmx_cmp:
+#endif
+
+
+	cmpdi   cr5,r5,31
+	ble	cr5,.Lcmp_lt32bytes
+
+#ifdef CONFIG_ALTIVEC
+	b	.Llong_novmx_cmp
+#else
+	b	.Llong
+#endif
+
+#ifdef CONFIG_ALTIVEC
+.Ldiffoffset_vmx_cmp:
+	/* perform a 32 bytes pre-checking before
+	 * enable VMX operations.
+	 */
+	li	r0,4
+	mtctr	r0
+.Ldiffoffset_prechk_32B_loop:
+	LD	rA,0,r3
+	LD	rB,0,r4
+	cmpld	cr0,rA,rB
+	addi	r3,r3,8
+	addi	r4,r4,8
+	bne     cr0,.LcmpAB_lightweight
+	addi	r5,r5,-8
+	bdnz	.Ldiffoffset_prechk_32B_loop
+
+	ENTER_VMX_OPS
+	beq     cr1,.Ldiffoffset_novmx_cmp
+
+.Ldiffoffset_vmx_cmp_start:
+	/* Firstly try to align r3 with 16 bytes */
+	andi.   r6,r3,0xf
+	li	off16,16
+	beq     .Ldiffoffset_vmx_s1_16bytes_align
+
+	LVS	v3,0,r3
+	LVS	v4,0,r4
+
+	lvx     v5,0,r3
+	lvx     v6,0,r4
+	LD_VSR_CROSS16B(r3,v3,v5,v7,v9)
+	LD_VSR_CROSS16B(r4,v4,v6,v8,v10)
+
+	VCMPEQUB_RC(v7,v9,v10)
+	bnl	cr6,.Ldiffoffset_vmx_diff_found
+
+	subfic  r6,r6,16
+	subf    r5,r6,r5
+	add     r3,r3,r6
+	add     r4,r4,r6
+
+.Ldiffoffset_vmx_s1_16bytes_align:
+	/* now s1 is aligned with 16 bytes */
+	lvx     v6,0,r4
+	LVS	v4,0,r4
+	srdi	r6,r5,5  /* loop for 32 bytes each */
+	clrldi  r5,r5,59
+	mtctr	r6
+
+.balign	16
+.Ldiffoffset_vmx_32bytesloop:
+	/* the first qw of r4 was saved in v6 */
+	lvx	v9,0,r3
+	LD_VSR_CROSS16B(r4,v4,v6,v8,v10)
+	VCMPEQUB_RC(v7,v9,v10)
+	vor	v6,v8,v8
+	bnl	cr6,.Ldiffoffset_vmx_diff_found
+
+	addi	r3,r3,16
+	addi	r4,r4,16
+
+	lvx	v9,0,r3
+	LD_VSR_CROSS16B(r4,v4,v6,v8,v10)
+	VCMPEQUB_RC(v7,v9,v10)
+	vor	v6,v8,v8
+	bnl	cr6,.Ldiffoffset_vmx_diff_found
+
+	addi	r3,r3,16
+	addi	r4,r4,16
+
+	bdnz	.Ldiffoffset_vmx_32bytesloop
+
+	EXIT_VMX_OPS
+
+	cmpdi	r5,0
+	beq	.Lzero
+	b	.Lcmp_lt32bytes
+
+.Ldiffoffset_vmx_diff_found:
+	EXIT_VMX_OPS
+	/* anyway, the diff will appear in next 16 bytes */
+	li	r5,16
+	b	.Lcmp_lt32bytes
+
+#endif
+EXPORT_SYMBOL(memcmp)
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
new file mode 100644
index 000000000..273ea67e6
--- /dev/null
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -0,0 +1,232 @@
+/*
+ * 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>
+#include <asm/export.h>
+#include <asm/asm-compat.h>
+#include <asm/feature-fixups.h>
+
+#ifndef SELFTEST_CASE
+/* For big-endian, 0 == most CPUs, 1 == POWER6, 2 == Cell */
+#define SELFTEST_CASE	0
+#endif
+
+	.align	7
+_GLOBAL_TOC(memcpy)
+BEGIN_FTR_SECTION
+#ifdef __LITTLE_ENDIAN__
+	cmpdi	cr7,r5,0
+#else
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* save destination pointer for return value */
+#endif
+FTR_SECTION_ELSE
+#ifdef CONFIG_PPC_BOOK3S_64
+	b	memcpy_power7
+#endif
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
+#ifdef __LITTLE_ENDIAN__
+	/* dumb little-endian memcpy that will get replaced at runtime */
+	addi r9,r3,-1
+	addi r4,r4,-1
+	beqlr cr7
+	mtctr r5
+1:	lbzu r10,1(r4)
+	stbu r10,1(r9)
+	bdnz 1b
+	blr
+#else
+	PPC_MTOCRF(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
+/* Below we want to nop out the bne if we're on a CPU that has the
+   CPU_FTR_UNALIGNED_LD_STD bit set and the CPU_FTR_CP_USE_DCBTZ bit
+   cleared.
+   At the time of writing the only CPU that has this combination of bits
+   set is Power6. */
+test_feature = (SELFTEST_CASE == 1)
+BEGIN_FTR_SECTION
+	nop
+FTR_SECTION_ELSE
+	bne	.Ldst_unaligned
+ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
+                    CPU_FTR_UNALIGNED_LD_STD)
+.Ldst_aligned:
+	addi	r3,r3,-16
+test_feature = (SELFTEST_CASE == 0)
+BEGIN_FTR_SECTION
+	andi.	r0,r4,7
+	bne	.Lsrc_unaligned
+END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
+	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)
+	beq	3f
+	addi	r3,r3,16
+.Ldo_tail:
+	bf	cr7*4+1,1f
+	lwz	r9,8(r4)
+	addi	r4,r4,4
+	stw	r9,0(r3)
+	addi	r3,r3,4
+1:	bf	cr7*4+2,2f
+	lhz	r9,8(r4)
+	addi	r4,r4,2
+	sth	r9,0(r3)
+	addi	r3,r3,2
+2:	bf	cr7*4+3,3f
+	lbz	r9,8(r4)
+	stb	r9,0(r3)
+3:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* return dest pointer */
+	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)
+	beq	4f
+	cmpwi	cr1,r5,8
+	addi	r3,r3,32
+	sld	r9,r9,r10
+	ble	cr1,6f
+	ld	r0,8(r4)
+	srd	r7,r0,r11
+	or	r9,r7,r9
+6:
+	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:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* return dest pointer */
+	blr
+
+.Ldst_unaligned:
+	PPC_MTOCRF(0x01,r6)		# put #bytes to 8B bdry into cr7
+	subf	r5,r6,r5
+	li	r7,0
+	cmpldi	cr1,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:	PPC_MTOCRF(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:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* return dest pointer */
+	blr
+#endif
+EXPORT_SYMBOL(memcpy)
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
new file mode 100644
index 000000000..89bfefcf7
--- /dev/null
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -0,0 +1,653 @@
+/*
+ * 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.
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/ppc_asm.h>
+
+#ifndef SELFTEST_CASE
+/* 0 == don't use VMX, 1 == use VMX */
+#define SELFTEST_CASE	0
+#endif
+
+#ifdef __BIG_ENDIAN__
+#define LVS(VRT,RA,RB)		lvsl	VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRA,VRB,VRC
+#else
+#define LVS(VRT,RA,RB)		lvsr	VRT,RA,RB
+#define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRB,VRA,VRC
+#endif
+
+_GLOBAL(memcpy_power7)
+	cmpldi	r5,16
+	cmpldi	cr1,r5,4096
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	blt	.Lshort_copy
+
+#ifdef CONFIG_ALTIVEC
+test_feature = SELFTEST_CASE
+BEGIN_FTR_SECTION
+	bgt	cr1, .Lvmx_copy
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+
+.Lnonvmx_copy:
+	/* Get the source 8B aligned */
+	neg	r6,r4
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	bf	cr7*4+3,1f
+	lbz	r0,0(r4)
+	addi	r4,r4,1
+	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	sub	r5,r5,r6
+	cmpldi	r5,128
+	blt	5f
+
+	mflr	r0
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
+	std	r0,STACKFRAMESIZE+16(r1)
+
+	srdi	r6,r5,7
+	mtctr	r6
+
+	/* Now do cacheline (128B) sized loads and stores. */
+	.align	5
+4:
+	ld	r0,0(r4)
+	ld	r6,8(r4)
+	ld	r7,16(r4)
+	ld	r8,24(r4)
+	ld	r9,32(r4)
+	ld	r10,40(r4)
+	ld	r11,48(r4)
+	ld	r12,56(r4)
+	ld	r14,64(r4)
+	ld	r15,72(r4)
+	ld	r16,80(r4)
+	ld	r17,88(r4)
+	ld	r18,96(r4)
+	ld	r19,104(r4)
+	ld	r20,112(r4)
+	ld	r21,120(r4)
+	addi	r4,r4,128
+	std	r0,0(r3)
+	std	r6,8(r3)
+	std	r7,16(r3)
+	std	r8,24(r3)
+	std	r9,32(r3)
+	std	r10,40(r3)
+	std	r11,48(r3)
+	std	r12,56(r3)
+	std	r14,64(r3)
+	std	r15,72(r3)
+	std	r16,80(r3)
+	std	r17,88(r3)
+	std	r18,96(r3)
+	std	r19,104(r3)
+	std	r20,112(r3)
+	std	r21,120(r3)
+	addi	r3,r3,128
+	bdnz	4b
+
+	clrldi	r5,r5,(64-7)
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	/* Up to 127B to go */
+5:	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+6:	bf	cr7*4+1,7f
+	ld	r0,0(r4)
+	ld	r6,8(r4)
+	ld	r7,16(r4)
+	ld	r8,24(r4)
+	ld	r9,32(r4)
+	ld	r10,40(r4)
+	ld	r11,48(r4)
+	ld	r12,56(r4)
+	addi	r4,r4,64
+	std	r0,0(r3)
+	std	r6,8(r3)
+	std	r7,16(r3)
+	std	r8,24(r3)
+	std	r9,32(r3)
+	std	r10,40(r3)
+	std	r11,48(r3)
+	std	r12,56(r3)
+	addi	r3,r3,64
+
+	/* Up to 63B to go */
+7:	bf	cr7*4+2,8f
+	ld	r0,0(r4)
+	ld	r6,8(r4)
+	ld	r7,16(r4)
+	ld	r8,24(r4)
+	addi	r4,r4,32
+	std	r0,0(r3)
+	std	r6,8(r3)
+	std	r7,16(r3)
+	std	r8,24(r3)
+	addi	r3,r3,32
+
+	/* Up to 31B to go */
+8:	bf	cr7*4+3,9f
+	ld	r0,0(r4)
+	ld	r6,8(r4)
+	addi	r4,r4,16
+	std	r0,0(r3)
+	std	r6,8(r3)
+	addi	r3,r3,16
+
+9:	clrldi	r5,r5,(64-4)
+
+	/* Up to 15B to go */
+.Lshort_copy:
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+	lwz	r6,4(r4)
+	addi	r4,r4,8
+	stw	r0,0(r3)
+	stw	r6,4(r3)
+	addi	r3,r3,8
+
+12:	bf	cr7*4+1,13f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+13:	bf	cr7*4+2,14f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+14:	bf	cr7*4+3,15f
+	lbz	r0,0(r4)
+	stb	r0,0(r3)
+
+15:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	blr
+
+.Lunwind_stack_nonvmx_copy:
+	addi	r1,r1,STACKFRAMESIZE
+	b	.Lnonvmx_copy
+
+.Lvmx_copy:
+#ifdef CONFIG_ALTIVEC
+	mflr	r0
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
+	std	r0,16(r1)
+	stdu	r1,-STACKFRAMESIZE(r1)
+	bl	enter_vmx_ops
+	cmpwi	cr1,r3,0
+	ld	r0,STACKFRAMESIZE+16(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
+	ld	r5,STK_REG(R29)(r1)
+	mtlr	r0
+
+	/*
+	 * We prefetch both the source and destination using enhanced touch
+	 * instructions. We use a stream ID of 0 for the load side and
+	 * 1 for the store side.
+	 */
+	clrrdi	r6,r4,7
+	clrrdi	r9,r3,7
+	ori	r9,r9,1		/* stream=1 */
+
+	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
+	cmpldi	r7,0x3FF
+	ble	1f
+	li	r7,0x3FF
+1:	lis	r0,0x0E00	/* depth=7 */
+	sldi	r7,r7,7
+	or	r7,r7,r0
+	ori	r10,r7,1	/* stream=1 */
+
+	lis	r8,0x8000	/* GO=1 */
+	clrldi	r8,r8,32
+
+	dcbt	0,r6,0b01000
+	dcbt	0,r7,0b01010
+	dcbtst	0,r9,0b01000
+	dcbtst	0,r10,0b01010
+	eieio
+	dcbt	0,r8,0b01010	/* GO */
+
+	beq	cr1,.Lunwind_stack_nonvmx_copy
+
+	/*
+	 * If source and destination are not relatively aligned we use a
+	 * slower permute loop.
+	 */
+	xor	r6,r4,r3
+	rldicl.	r6,r6,0,(64-4)
+	bne	.Lvmx_unaligned_copy
+
+	/* Get the destination 16B aligned */
+	neg	r6,r3
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-4)
+
+	bf	cr7*4+3,1f
+	lbz	r0,0(r4)
+	addi	r4,r4,1
+	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	bf	cr7*4+0,4f
+	ld	r0,0(r4)
+	addi	r4,r4,8
+	std	r0,0(r3)
+	addi	r3,r3,8
+
+4:	sub	r5,r5,r6
+
+	/* Get the desination 128B aligned */
+	neg	r6,r3
+	srdi	r7,r6,4
+	mtocrf	0x01,r7
+	clrldi	r6,r6,(64-7)
+
+	li	r9,16
+	li	r10,32
+	li	r11,48
+
+	bf	cr7*4+3,5f
+	lvx	v1,0,r4
+	addi	r4,r4,16
+	stvx	v1,0,r3
+	addi	r3,r3,16
+
+5:	bf	cr7*4+2,6f
+	lvx	v1,0,r4
+	lvx	v0,r4,r9
+	addi	r4,r4,32
+	stvx	v1,0,r3
+	stvx	v0,r3,r9
+	addi	r3,r3,32
+
+6:	bf	cr7*4+1,7f
+	lvx	v3,0,r4
+	lvx	v2,r4,r9
+	lvx	v1,r4,r10
+	lvx	v0,r4,r11
+	addi	r4,r4,64
+	stvx	v3,0,r3
+	stvx	v2,r3,r9
+	stvx	v1,r3,r10
+	stvx	v0,r3,r11
+	addi	r3,r3,64
+
+7:	sub	r5,r5,r6
+	srdi	r6,r5,7
+
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+
+	li	r12,64
+	li	r14,80
+	li	r15,96
+	li	r16,112
+
+	mtctr	r6
+
+	/*
+	 * Now do cacheline sized loads and stores. By this stage the
+	 * cacheline stores are also cacheline aligned.
+	 */
+	.align	5
+8:
+	lvx	v7,0,r4
+	lvx	v6,r4,r9
+	lvx	v5,r4,r10
+	lvx	v4,r4,r11
+	lvx	v3,r4,r12
+	lvx	v2,r4,r14
+	lvx	v1,r4,r15
+	lvx	v0,r4,r16
+	addi	r4,r4,128
+	stvx	v7,0,r3
+	stvx	v6,r3,r9
+	stvx	v5,r3,r10
+	stvx	v4,r3,r11
+	stvx	v3,r3,r12
+	stvx	v2,r3,r14
+	stvx	v1,r3,r15
+	stvx	v0,r3,r16
+	addi	r3,r3,128
+	bdnz	8b
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+
+	/* Up to 127B to go */
+	clrldi	r5,r5,(64-7)
+	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+	bf	cr7*4+1,9f
+	lvx	v3,0,r4
+	lvx	v2,r4,r9
+	lvx	v1,r4,r10
+	lvx	v0,r4,r11
+	addi	r4,r4,64
+	stvx	v3,0,r3
+	stvx	v2,r3,r9
+	stvx	v1,r3,r10
+	stvx	v0,r3,r11
+	addi	r3,r3,64
+
+9:	bf	cr7*4+2,10f
+	lvx	v1,0,r4
+	lvx	v0,r4,r9
+	addi	r4,r4,32
+	stvx	v1,0,r3
+	stvx	v0,r3,r9
+	addi	r3,r3,32
+
+10:	bf	cr7*4+3,11f
+	lvx	v1,0,r4
+	addi	r4,r4,16
+	stvx	v1,0,r3
+	addi	r3,r3,16
+
+	/* Up to 15B to go */
+11:	clrldi	r5,r5,(64-4)
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+	ld	r0,0(r4)
+	addi	r4,r4,8
+	std	r0,0(r3)
+	addi	r3,r3,8
+
+12:	bf	cr7*4+1,13f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+13:	bf	cr7*4+2,14f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+14:	bf	cr7*4+3,15f
+	lbz	r0,0(r4)
+	stb	r0,0(r3)
+
+15:	addi	r1,r1,STACKFRAMESIZE
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	b	exit_vmx_ops		/* tail call optimise */
+
+.Lvmx_unaligned_copy:
+	/* Get the destination 16B aligned */
+	neg	r6,r3
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-4)
+
+	bf	cr7*4+3,1f
+	lbz	r0,0(r4)
+	addi	r4,r4,1
+	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	bf	cr7*4+0,4f
+	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+	lwz	r7,4(r4)
+	addi	r4,r4,8
+	stw	r0,0(r3)
+	stw	r7,4(r3)
+	addi	r3,r3,8
+
+4:	sub	r5,r5,r6
+
+	/* Get the desination 128B aligned */
+	neg	r6,r3
+	srdi	r7,r6,4
+	mtocrf	0x01,r7
+	clrldi	r6,r6,(64-7)
+
+	li	r9,16
+	li	r10,32
+	li	r11,48
+
+	LVS(v16,0,r4)		/* Setup permute control vector */
+	lvx	v0,0,r4
+	addi	r4,r4,16
+
+	bf	cr7*4+3,5f
+	lvx	v1,0,r4
+	VPERM(v8,v0,v1,v16)
+	addi	r4,r4,16
+	stvx	v8,0,r3
+	addi	r3,r3,16
+	vor	v0,v1,v1
+
+5:	bf	cr7*4+2,6f
+	lvx	v1,0,r4
+	VPERM(v8,v0,v1,v16)
+	lvx	v0,r4,r9
+	VPERM(v9,v1,v0,v16)
+	addi	r4,r4,32
+	stvx	v8,0,r3
+	stvx	v9,r3,r9
+	addi	r3,r3,32
+
+6:	bf	cr7*4+1,7f
+	lvx	v3,0,r4
+	VPERM(v8,v0,v3,v16)
+	lvx	v2,r4,r9
+	VPERM(v9,v3,v2,v16)
+	lvx	v1,r4,r10
+	VPERM(v10,v2,v1,v16)
+	lvx	v0,r4,r11
+	VPERM(v11,v1,v0,v16)
+	addi	r4,r4,64
+	stvx	v8,0,r3
+	stvx	v9,r3,r9
+	stvx	v10,r3,r10
+	stvx	v11,r3,r11
+	addi	r3,r3,64
+
+7:	sub	r5,r5,r6
+	srdi	r6,r5,7
+
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+
+	li	r12,64
+	li	r14,80
+	li	r15,96
+	li	r16,112
+
+	mtctr	r6
+
+	/*
+	 * Now do cacheline sized loads and stores. By this stage the
+	 * cacheline stores are also cacheline aligned.
+	 */
+	.align	5
+8:
+	lvx	v7,0,r4
+	VPERM(v8,v0,v7,v16)
+	lvx	v6,r4,r9
+	VPERM(v9,v7,v6,v16)
+	lvx	v5,r4,r10
+	VPERM(v10,v6,v5,v16)
+	lvx	v4,r4,r11
+	VPERM(v11,v5,v4,v16)
+	lvx	v3,r4,r12
+	VPERM(v12,v4,v3,v16)
+	lvx	v2,r4,r14
+	VPERM(v13,v3,v2,v16)
+	lvx	v1,r4,r15
+	VPERM(v14,v2,v1,v16)
+	lvx	v0,r4,r16
+	VPERM(v15,v1,v0,v16)
+	addi	r4,r4,128
+	stvx	v8,0,r3
+	stvx	v9,r3,r9
+	stvx	v10,r3,r10
+	stvx	v11,r3,r11
+	stvx	v12,r3,r12
+	stvx	v13,r3,r14
+	stvx	v14,r3,r15
+	stvx	v15,r3,r16
+	addi	r3,r3,128
+	bdnz	8b
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+
+	/* Up to 127B to go */
+	clrldi	r5,r5,(64-7)
+	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+	bf	cr7*4+1,9f
+	lvx	v3,0,r4
+	VPERM(v8,v0,v3,v16)
+	lvx	v2,r4,r9
+	VPERM(v9,v3,v2,v16)
+	lvx	v1,r4,r10
+	VPERM(v10,v2,v1,v16)
+	lvx	v0,r4,r11
+	VPERM(v11,v1,v0,v16)
+	addi	r4,r4,64
+	stvx	v8,0,r3
+	stvx	v9,r3,r9
+	stvx	v10,r3,r10
+	stvx	v11,r3,r11
+	addi	r3,r3,64
+
+9:	bf	cr7*4+2,10f
+	lvx	v1,0,r4
+	VPERM(v8,v0,v1,v16)
+	lvx	v0,r4,r9
+	VPERM(v9,v1,v0,v16)
+	addi	r4,r4,32
+	stvx	v8,0,r3
+	stvx	v9,r3,r9
+	addi	r3,r3,32
+
+10:	bf	cr7*4+3,11f
+	lvx	v1,0,r4
+	VPERM(v8,v0,v1,v16)
+	addi	r4,r4,16
+	stvx	v8,0,r3
+	addi	r3,r3,16
+
+	/* Up to 15B to go */
+11:	clrldi	r5,r5,(64-4)
+	addi	r4,r4,-16	/* Unwind the +16 load offset */
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+	lwz	r6,4(r4)
+	addi	r4,r4,8
+	stw	r0,0(r3)
+	stw	r6,4(r3)
+	addi	r3,r3,8
+
+12:	bf	cr7*4+1,13f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+13:	bf	cr7*4+2,14f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+14:	bf	cr7*4+3,15f
+	lbz	r0,0(r4)
+	stb	r0,0(r3)
+
+15:	addi	r1,r1,STACKFRAMESIZE
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	b	exit_vmx_ops		/* tail call optimise */
+#endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c
new file mode 100644
index 000000000..53c018762
--- /dev/null
+++ b/arch/powerpc/lib/pmem.c
@@ -0,0 +1,67 @@
+/*
+ * Copyright(c) 2017 IBM Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ */
+
+#include <linux/string.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+
+/*
+ * CONFIG_ARCH_HAS_PMEM_API symbols
+ */
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+	unsigned long start = (unsigned long) addr;
+	flush_inval_dcache_range(start, start + size);
+}
+EXPORT_SYMBOL(arch_wb_cache_pmem);
+
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+	unsigned long start = (unsigned long) addr;
+	flush_inval_dcache_range(start, start + size);
+}
+EXPORT_SYMBOL(arch_invalidate_pmem);
+
+/*
+ * CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE symbols
+ */
+long __copy_from_user_flushcache(void *dest, const void __user *src,
+		unsigned size)
+{
+	unsigned long copied, start = (unsigned long) dest;
+
+	copied = __copy_from_user(dest, src, size);
+	flush_inval_dcache_range(start, start + size);
+
+	return copied;
+}
+
+void *memcpy_flushcache(void *dest, const void *src, size_t size)
+{
+	unsigned long start = (unsigned long) dest;
+
+	memcpy(dest, src, size);
+	flush_inval_dcache_range(start, start + size);
+
+	return dest;
+}
+EXPORT_SYMBOL(memcpy_flushcache);
+
+void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
+	size_t len)
+{
+	memcpy_flushcache(to, page_to_virt(page) + offset, len);
+}
+EXPORT_SYMBOL(memcpy_page_flushcache);
diff --git a/arch/powerpc/lib/quad.S b/arch/powerpc/lib/quad.S
new file mode 100644
index 000000000..c4d12fae8
--- /dev/null
+++ b/arch/powerpc/lib/quad.S
@@ -0,0 +1,62 @@
+/*
+ * Quadword loads and stores
+ * for use in instruction emulation.
+ *
+ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ *  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>
+#include <asm/ppc-opcode.h>
+#include <asm/reg.h>
+#include <asm/asm-offsets.h>
+#include <linux/errno.h>
+
+/* do_lq(unsigned long ea, unsigned long *regs) */
+_GLOBAL(do_lq)
+1:	lq	r6, 0(r3)
+	std	r6, 0(r4)
+	std	r7, 8(r4)
+	li	r3, 0
+	blr
+2:	li	r3, -EFAULT
+	blr
+	EX_TABLE(1b, 2b)
+
+/* do_stq(unsigned long ea, unsigned long val0, unsigned long val1) */
+_GLOBAL(do_stq)
+1:	stq	r4, 0(r3)
+	li	r3, 0
+	blr
+2:	li	r3, -EFAULT
+	blr
+	EX_TABLE(1b, 2b)
+
+/* do_lqarx(unsigned long ea, unsigned long *regs) */
+_GLOBAL(do_lqarx)
+1:	PPC_LQARX(6, 0, 3, 0)
+	std	r6, 0(r4)
+	std	r7, 8(r4)
+	li	r3, 0
+	blr
+2:	li	r3, -EFAULT
+	blr
+	EX_TABLE(1b, 2b)
+
+/* do_stqcx(unsigned long ea, unsigned long val0, unsigned long val1,
+	    unsigned int *crp) */
+
+_GLOBAL(do_stqcx)
+1:	PPC_STQCX(4, 0, 3)
+	mfcr	r5
+	stw	r5, 0(r6)
+	li	r3, 0
+	blr
+2:	li	r3, -EFAULT
+	blr
+	EX_TABLE(1b, 2b)
diff --git a/arch/powerpc/lib/rheap.c b/arch/powerpc/lib/rheap.c
new file mode 100644
index 000000000..6aa774aa5
--- /dev/null
+++ b/arch/powerpc/lib/rheap.c
@@ -0,0 +1,747 @@
+/*
+ * 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/kernel.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/err.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_array(max_blocks, sizeof(rh_block_t), GFP_ATOMIC);
+	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 */
+	blk = block + info->max_blocks - new_blocks;
+	for (i = 0; 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 = 0;
+	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 = 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 = 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 && s != (before->start + before->size))
+		before = NULL;
+
+	if (after && e != 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 -= 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_ATOMIC);
+	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;
+}
+EXPORT_SYMBOL_GPL(rh_create);
+
+/*
+ * 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)
+		kfree(info->block);
+
+	if ((info->flags & RHIF_STATIC_INFO) == 0)
+		kfree(info);
+}
+EXPORT_SYMBOL_GPL(rh_destroy);
+
+/*
+ * 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);
+}
+EXPORT_SYMBOL_GPL(rh_init);
+
+/* Attach a free memory region, coalesces regions if adjacent */
+int rh_attach_region(rh_info_t * info, unsigned long start, int size)
+{
+	rh_block_t *blk;
+	unsigned long s, e, m;
+	int r;
+
+	/* The region must be aligned */
+	s = start;
+	e = s + size;
+	m = info->alignment - 1;
+
+	/* Round start up */
+	s = (s + m) & ~m;
+
+	/* Round end down */
+	e = e & ~m;
+
+	if (IS_ERR_VALUE(e) || (e < s))
+		return -ERANGE;
+
+	/* Take final values */
+	start = s;
+	size = 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;
+}
+EXPORT_SYMBOL_GPL(rh_attach_region);
+
+/* Detatch given address range, splits free block if needed. */
+unsigned long rh_detach_region(rh_info_t * info, unsigned long 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 (unsigned long) -EINVAL;
+
+	/* The region must be aligned */
+	s = 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 (unsigned long) -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 = blk->start;
+		be = blk->start + blk->size;
+		if (s >= bs && e <= be)
+			break;
+		blk = NULL;
+	}
+
+	if (blk == NULL)
+		return (unsigned long) -ENOMEM;
+
+	/* Perfect fit */
+	if (bs == s && be == e) {
+		/* Delete from free list, release slot */
+		list_del(&blk->list);
+		release_slot(info, blk);
+		return s;
+	}
+
+	/* blk still in free list, with updated start and/or size */
+	if (bs == s || be == e) {
+		if (bs == s)
+			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 = e;
+		newblk->size = be - e;
+
+		list_add(&newblk->list, &blk->list);
+	}
+
+	return s;
+}
+EXPORT_SYMBOL_GPL(rh_detach_region);
+
+/* Allocate a block of memory at the specified alignment.  The value returned
+ * is an offset into the buffer initialized by rh_init(), or a negative number
+ * if there is an error.
+ */
+unsigned long rh_alloc_align(rh_info_t * info, int size, int alignment, const char *owner)
+{
+	struct list_head *l;
+	rh_block_t *blk;
+	rh_block_t *newblk;
+	unsigned long start, sp_size;
+
+	/* Validate size, and alignment must be power of two */
+	if (size <= 0 || (alignment & (alignment - 1)) != 0)
+		return (unsigned long) -EINVAL;
+
+	/* Align to configured alignment */
+	size = (size + (info->alignment - 1)) & ~(info->alignment - 1);
+
+	if (assure_empty(info, 2) < 0)
+		return (unsigned long) -ENOMEM;
+
+	blk = NULL;
+	list_for_each(l, &info->free_list) {
+		blk = list_entry(l, rh_block_t, list);
+		if (size <= blk->size) {
+			start = (blk->start + alignment - 1) & ~(alignment - 1);
+			if (start + size <= blk->start + blk->size)
+				break;
+		}
+		blk = NULL;
+	}
+
+	if (blk == NULL)
+		return (unsigned long) -ENOMEM;
+
+	/* Just fits */
+	if (blk->size == size) {
+		/* Move from free list to taken list */
+		list_del(&blk->list);
+		newblk = blk;
+	} else {
+		/* Fragment caused, split if needed */
+		/* Create block for fragment in the beginning */
+		sp_size = start - blk->start;
+		if (sp_size) {
+			rh_block_t *spblk;
+
+			spblk = get_slot(info);
+			spblk->start = blk->start;
+			spblk->size = sp_size;
+			/* add before the blk */
+			list_add(&spblk->list, blk->list.prev);
+		}
+		newblk = get_slot(info);
+		newblk->start = start;
+		newblk->size = size;
+
+		/* blk still in free list, with updated start and size
+		 * for fragment in the end */
+		blk->start = start + size;
+		blk->size -= sp_size + size;
+		/* No fragment in the end, remove blk */
+		if (blk->size == 0) {
+			list_del(&blk->list);
+			release_slot(info, blk);
+		}
+	}
+
+	newblk->owner = owner;
+	attach_taken_block(info, newblk);
+
+	return start;
+}
+EXPORT_SYMBOL_GPL(rh_alloc_align);
+
+/* Allocate a block of memory at the default alignment.  The value returned is
+ * an offset into the buffer initialized by rh_init(), or a negative number if
+ * there is an error.
+ */
+unsigned long rh_alloc(rh_info_t * info, int size, const char *owner)
+{
+	return rh_alloc_align(info, size, info->alignment, owner);
+}
+EXPORT_SYMBOL_GPL(rh_alloc);
+
+/* Allocate a block of memory at the given offset, rounded up to the default
+ * alignment.  The value returned is an offset into the buffer initialized by
+ * rh_init(), or a negative number if there is an error.
+ */
+unsigned long rh_alloc_fixed(rh_info_t * info, unsigned long start, int size, const char *owner)
+{
+	struct list_head *l;
+	rh_block_t *blk, *newblk1, *newblk2;
+	unsigned long s, e, m, bs = 0, be = 0;
+
+	/* Validate size */
+	if (size <= 0)
+		return (unsigned long) -EINVAL;
+
+	/* The region must be aligned */
+	s = 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 (unsigned long) -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 = blk->start;
+		be = blk->start + blk->size;
+		if (s >= bs && e <= be)
+			break;
+		blk = NULL;
+	}
+
+	if (blk == NULL)
+		return (unsigned long) -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 += size;
+		blk->size -= size;
+
+	} else {
+		/* The front free fragment */
+		blk->size = s - bs;
+
+		/* The back free fragment */
+		newblk2 = get_slot(info);
+		newblk2->start = e;
+		newblk2->size = be - e;
+
+		list_add(&newblk2->list, &blk->list);
+	}
+
+	newblk1 = get_slot(info);
+	newblk1->start = s;
+	newblk1->size = e - s;
+	newblk1->owner = owner;
+
+	start = newblk1->start;
+	attach_taken_block(info, newblk1);
+
+	return start;
+}
+EXPORT_SYMBOL_GPL(rh_alloc_fixed);
+
+/* Deallocate the memory previously allocated by one of the rh_alloc functions.
+ * The return value is the size of the deallocated block, or a negative number
+ * if there is an error.
+ */
+int rh_free(rh_info_t * info, unsigned long 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;
+}
+EXPORT_SYMBOL_GPL(rh_free);
+
+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;
+}
+EXPORT_SYMBOL_GPL(rh_get_stats);
+
+int rh_set_owner(rh_info_t * info, unsigned long 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;
+}
+EXPORT_SYMBOL_GPL(rh_set_owner);
+
+void rh_dump(rh_info_t * info)
+{
+	static rh_stats_t st[32];	/* XXX maximum 32 blocks */
+	int maxnr;
+	int i, nr;
+
+	maxnr = ARRAY_SIZE(st);
+
+	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%lx-0x%lx (%u)\n",
+		       st[i].start, 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%lx-0x%lx (%u) %s\n",
+		       st[i].start, st[i].start + st[i].size,
+		       st[i].size, st[i].owner != NULL ? st[i].owner : "");
+	printk(KERN_INFO "\n");
+}
+EXPORT_SYMBOL_GPL(rh_dump);
+
+void rh_dump_blk(rh_info_t * info, rh_block_t * blk)
+{
+	printk(KERN_INFO
+	       "blk @0x%p: 0x%lx-0x%lx (%u)\n",
+	       blk, blk->start, blk->start + blk->size, blk->size);
+}
+EXPORT_SYMBOL_GPL(rh_dump_blk);
+
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
new file mode 100644
index 000000000..30c434abe
--- /dev/null
+++ b/arch/powerpc/lib/sstep.c
@@ -0,0 +1,3108 @@
+/*
+ * 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/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/prefetch.h>
+#include <asm/sstep.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+#include <asm/cpu_has_feature.h>
+#include <asm/cputable.h>
+
+extern char system_call_common[];
+
+#ifdef CONFIG_PPC64
+/* Bits in SRR1 that are copied from MSR */
+#define MSR_MASK	0xffffffff87c0ffffUL
+#else
+#define MSR_MASK	0x87c0ffff
+#endif
+
+/* Bits in XER */
+#define XER_SO		0x80000000U
+#define XER_OV		0x40000000U
+#define XER_CA		0x20000000U
+#define XER_OV32	0x00080000U
+#define XER_CA32	0x00040000U
+
+#ifdef CONFIG_PPC_FPU
+/*
+ * Functions in ldstfp.S
+ */
+extern void get_fpr(int rn, double *p);
+extern void put_fpr(int rn, const double *p);
+extern void get_vr(int rn, __vector128 *p);
+extern void put_vr(int rn, __vector128 *p);
+extern void load_vsrn(int vsr, const void *p);
+extern void store_vsrn(int vsr, void *p);
+extern void conv_sp_to_dp(const float *sp, double *dp);
+extern void conv_dp_to_sp(const double *dp, float *sp);
+#endif
+
+#ifdef __powerpc64__
+/*
+ * Functions in quad.S
+ */
+extern int do_lq(unsigned long ea, unsigned long *regs);
+extern int do_stq(unsigned long ea, unsigned long val0, unsigned long val1);
+extern int do_lqarx(unsigned long ea, unsigned long *regs);
+extern int do_stqcx(unsigned long ea, unsigned long val0, unsigned long val1,
+		    unsigned int *crp);
+#endif
+
+#ifdef __LITTLE_ENDIAN__
+#define IS_LE	1
+#define IS_BE	0
+#else
+#define IS_LE	0
+#define IS_BE	1
+#endif
+
+/*
+ * Emulate the truncation of 64 bit values in 32-bit mode.
+ */
+static nokprobe_inline unsigned long truncate_if_32bit(unsigned long msr,
+							unsigned long val)
+{
+#ifdef __powerpc64__
+	if ((msr & MSR_64BIT) == 0)
+		val &= 0xffffffffUL;
+#endif
+	return val;
+}
+
+/*
+ * Determine whether a conditional branch instruction would branch.
+ */
+static nokprobe_inline int branch_taken(unsigned int instr,
+					const struct pt_regs *regs,
+					struct instruction_op *op)
+{
+	unsigned int bo = (instr >> 21) & 0x1f;
+	unsigned int bi;
+
+	if ((bo & 4) == 0) {
+		/* decrement counter */
+		op->type |= DECCTR;
+		if (((bo >> 1) & 1) ^ (regs->ctr == 1))
+			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;
+}
+
+static nokprobe_inline long address_ok(struct pt_regs *regs,
+				       unsigned long ea, int nb)
+{
+	if (!user_mode(regs))
+		return 1;
+	if (__access_ok(ea, nb, USER_DS))
+		return 1;
+	if (__access_ok(ea, 1, USER_DS))
+		/* Access overlaps the end of the user region */
+		regs->dar = USER_DS.seg;
+	else
+		regs->dar = ea;
+	return 0;
+}
+
+/*
+ * Calculate effective address for a D-form instruction
+ */
+static nokprobe_inline unsigned long dform_ea(unsigned int instr,
+					      const struct pt_regs *regs)
+{
+	int ra;
+	unsigned long ea;
+
+	ra = (instr >> 16) & 0x1f;
+	ea = (signed short) instr;		/* sign-extend */
+	if (ra)
+		ea += regs->gpr[ra];
+
+	return ea;
+}
+
+#ifdef __powerpc64__
+/*
+ * Calculate effective address for a DS-form instruction
+ */
+static nokprobe_inline unsigned long dsform_ea(unsigned int instr,
+					       const struct pt_regs *regs)
+{
+	int ra;
+	unsigned long ea;
+
+	ra = (instr >> 16) & 0x1f;
+	ea = (signed short) (instr & ~3);	/* sign-extend */
+	if (ra)
+		ea += regs->gpr[ra];
+
+	return ea;
+}
+
+/*
+ * Calculate effective address for a DQ-form instruction
+ */
+static nokprobe_inline unsigned long dqform_ea(unsigned int instr,
+					       const struct pt_regs *regs)
+{
+	int ra;
+	unsigned long ea;
+
+	ra = (instr >> 16) & 0x1f;
+	ea = (signed short) (instr & ~0xf);	/* sign-extend */
+	if (ra)
+		ea += regs->gpr[ra];
+
+	return ea;
+}
+#endif /* __powerpc64 */
+
+/*
+ * Calculate effective address for an X-form instruction
+ */
+static nokprobe_inline unsigned long xform_ea(unsigned int instr,
+					      const struct pt_regs *regs)
+{
+	int ra, rb;
+	unsigned long ea;
+
+	ra = (instr >> 16) & 0x1f;
+	rb = (instr >> 11) & 0x1f;
+	ea = regs->gpr[rb];
+	if (ra)
+		ea += regs->gpr[ra];
+
+	return ea;
+}
+
+/*
+ * Return the largest power of 2, not greater than sizeof(unsigned long),
+ * such that x is a multiple of it.
+ */
+static nokprobe_inline unsigned long max_align(unsigned long x)
+{
+	x |= sizeof(unsigned long);
+	return x & -x;		/* isolates rightmost bit */
+}
+
+static nokprobe_inline unsigned long byterev_2(unsigned long x)
+{
+	return ((x >> 8) & 0xff) | ((x & 0xff) << 8);
+}
+
+static nokprobe_inline unsigned long byterev_4(unsigned long x)
+{
+	return ((x >> 24) & 0xff) | ((x >> 8) & 0xff00) |
+		((x & 0xff00) << 8) | ((x & 0xff) << 24);
+}
+
+#ifdef __powerpc64__
+static nokprobe_inline unsigned long byterev_8(unsigned long x)
+{
+	return (byterev_4(x) << 32) | byterev_4(x >> 32);
+}
+#endif
+
+static nokprobe_inline void do_byte_reverse(void *ptr, int nb)
+{
+	switch (nb) {
+	case 2:
+		*(u16 *)ptr = byterev_2(*(u16 *)ptr);
+		break;
+	case 4:
+		*(u32 *)ptr = byterev_4(*(u32 *)ptr);
+		break;
+#ifdef __powerpc64__
+	case 8:
+		*(unsigned long *)ptr = byterev_8(*(unsigned long *)ptr);
+		break;
+	case 16: {
+		unsigned long *up = (unsigned long *)ptr;
+		unsigned long tmp;
+		tmp = byterev_8(up[0]);
+		up[0] = byterev_8(up[1]);
+		up[1] = tmp;
+		break;
+	}
+#endif
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+
+static nokprobe_inline int read_mem_aligned(unsigned long *dest,
+					    unsigned long ea, int nb,
+					    struct pt_regs *regs)
+{
+	int err = 0;
+	unsigned long x = 0;
+
+	switch (nb) {
+	case 1:
+		err = __get_user(x, (unsigned char __user *) ea);
+		break;
+	case 2:
+		err = __get_user(x, (unsigned short __user *) ea);
+		break;
+	case 4:
+		err = __get_user(x, (unsigned int __user *) ea);
+		break;
+#ifdef __powerpc64__
+	case 8:
+		err = __get_user(x, (unsigned long __user *) ea);
+		break;
+#endif
+	}
+	if (!err)
+		*dest = x;
+	else
+		regs->dar = ea;
+	return err;
+}
+
+/*
+ * Copy from userspace to a buffer, using the largest possible
+ * aligned accesses, up to sizeof(long).
+ */
+static nokprobe_inline int copy_mem_in(u8 *dest, unsigned long ea, int nb,
+				       struct pt_regs *regs)
+{
+	int err = 0;
+	int c;
+
+	for (; nb > 0; nb -= c) {
+		c = max_align(ea);
+		if (c > nb)
+			c = max_align(nb);
+		switch (c) {
+		case 1:
+			err = __get_user(*dest, (unsigned char __user *) ea);
+			break;
+		case 2:
+			err = __get_user(*(u16 *)dest,
+					 (unsigned short __user *) ea);
+			break;
+		case 4:
+			err = __get_user(*(u32 *)dest,
+					 (unsigned int __user *) ea);
+			break;
+#ifdef __powerpc64__
+		case 8:
+			err = __get_user(*(unsigned long *)dest,
+					 (unsigned long __user *) ea);
+			break;
+#endif
+		}
+		if (err) {
+			regs->dar = ea;
+			return err;
+		}
+		dest += c;
+		ea += c;
+	}
+	return 0;
+}
+
+static nokprobe_inline int read_mem_unaligned(unsigned long *dest,
+					      unsigned long ea, int nb,
+					      struct pt_regs *regs)
+{
+	union {
+		unsigned long ul;
+		u8 b[sizeof(unsigned long)];
+	} u;
+	int i;
+	int err;
+
+	u.ul = 0;
+	i = IS_BE ? sizeof(unsigned long) - nb : 0;
+	err = copy_mem_in(&u.b[i], ea, nb, regs);
+	if (!err)
+		*dest = u.ul;
+	return err;
+}
+
+/*
+ * Read memory at address ea for nb bytes, return 0 for success
+ * or -EFAULT if an error occurred.  N.B. nb must be 1, 2, 4 or 8.
+ * If nb < sizeof(long), the result is right-justified on BE systems.
+ */
+static int read_mem(unsigned long *dest, unsigned long ea, int nb,
+			      struct pt_regs *regs)
+{
+	if (!address_ok(regs, ea, nb))
+		return -EFAULT;
+	if ((ea & (nb - 1)) == 0)
+		return read_mem_aligned(dest, ea, nb, regs);
+	return read_mem_unaligned(dest, ea, nb, regs);
+}
+NOKPROBE_SYMBOL(read_mem);
+
+static nokprobe_inline int write_mem_aligned(unsigned long val,
+					     unsigned long ea, int nb,
+					     struct pt_regs *regs)
+{
+	int err = 0;
+
+	switch (nb) {
+	case 1:
+		err = __put_user(val, (unsigned char __user *) ea);
+		break;
+	case 2:
+		err = __put_user(val, (unsigned short __user *) ea);
+		break;
+	case 4:
+		err = __put_user(val, (unsigned int __user *) ea);
+		break;
+#ifdef __powerpc64__
+	case 8:
+		err = __put_user(val, (unsigned long __user *) ea);
+		break;
+#endif
+	}
+	if (err)
+		regs->dar = ea;
+	return err;
+}
+
+/*
+ * Copy from a buffer to userspace, using the largest possible
+ * aligned accesses, up to sizeof(long).
+ */
+static nokprobe_inline int copy_mem_out(u8 *dest, unsigned long ea, int nb,
+					struct pt_regs *regs)
+{
+	int err = 0;
+	int c;
+
+	for (; nb > 0; nb -= c) {
+		c = max_align(ea);
+		if (c > nb)
+			c = max_align(nb);
+		switch (c) {
+		case 1:
+			err = __put_user(*dest, (unsigned char __user *) ea);
+			break;
+		case 2:
+			err = __put_user(*(u16 *)dest,
+					 (unsigned short __user *) ea);
+			break;
+		case 4:
+			err = __put_user(*(u32 *)dest,
+					 (unsigned int __user *) ea);
+			break;
+#ifdef __powerpc64__
+		case 8:
+			err = __put_user(*(unsigned long *)dest,
+					 (unsigned long __user *) ea);
+			break;
+#endif
+		}
+		if (err) {
+			regs->dar = ea;
+			return err;
+		}
+		dest += c;
+		ea += c;
+	}
+	return 0;
+}
+
+static nokprobe_inline int write_mem_unaligned(unsigned long val,
+					       unsigned long ea, int nb,
+					       struct pt_regs *regs)
+{
+	union {
+		unsigned long ul;
+		u8 b[sizeof(unsigned long)];
+	} u;
+	int i;
+
+	u.ul = val;
+	i = IS_BE ? sizeof(unsigned long) - nb : 0;
+	return copy_mem_out(&u.b[i], ea, nb, regs);
+}
+
+/*
+ * Write memory at address ea for nb bytes, return 0 for success
+ * or -EFAULT if an error occurred.  N.B. nb must be 1, 2, 4 or 8.
+ */
+static int write_mem(unsigned long val, unsigned long ea, int nb,
+			       struct pt_regs *regs)
+{
+	if (!address_ok(regs, ea, nb))
+		return -EFAULT;
+	if ((ea & (nb - 1)) == 0)
+		return write_mem_aligned(val, ea, nb, regs);
+	return write_mem_unaligned(val, ea, nb, regs);
+}
+NOKPROBE_SYMBOL(write_mem);
+
+#ifdef CONFIG_PPC_FPU
+/*
+ * These access either the real FP register or the image in the
+ * thread_struct, depending on regs->msr & MSR_FP.
+ */
+static int do_fp_load(struct instruction_op *op, unsigned long ea,
+		      struct pt_regs *regs, bool cross_endian)
+{
+	int err, rn, nb;
+	union {
+		int i;
+		unsigned int u;
+		float f;
+		double d[2];
+		unsigned long l[2];
+		u8 b[2 * sizeof(double)];
+	} u;
+
+	nb = GETSIZE(op->type);
+	if (!address_ok(regs, ea, nb))
+		return -EFAULT;
+	rn = op->reg;
+	err = copy_mem_in(u.b, ea, nb, regs);
+	if (err)
+		return err;
+	if (unlikely(cross_endian)) {
+		do_byte_reverse(u.b, min(nb, 8));
+		if (nb == 16)
+			do_byte_reverse(&u.b[8], 8);
+	}
+	preempt_disable();
+	if (nb == 4) {
+		if (op->type & FPCONV)
+			conv_sp_to_dp(&u.f, &u.d[0]);
+		else if (op->type & SIGNEXT)
+			u.l[0] = u.i;
+		else
+			u.l[0] = u.u;
+	}
+	if (regs->msr & MSR_FP)
+		put_fpr(rn, &u.d[0]);
+	else
+		current->thread.TS_FPR(rn) = u.l[0];
+	if (nb == 16) {
+		/* lfdp */
+		rn |= 1;
+		if (regs->msr & MSR_FP)
+			put_fpr(rn, &u.d[1]);
+		else
+			current->thread.TS_FPR(rn) = u.l[1];
+	}
+	preempt_enable();
+	return 0;
+}
+NOKPROBE_SYMBOL(do_fp_load);
+
+static int do_fp_store(struct instruction_op *op, unsigned long ea,
+		       struct pt_regs *regs, bool cross_endian)
+{
+	int rn, nb;
+	union {
+		unsigned int u;
+		float f;
+		double d[2];
+		unsigned long l[2];
+		u8 b[2 * sizeof(double)];
+	} u;
+
+	nb = GETSIZE(op->type);
+	if (!address_ok(regs, ea, nb))
+		return -EFAULT;
+	rn = op->reg;
+	preempt_disable();
+	if (regs->msr & MSR_FP)
+		get_fpr(rn, &u.d[0]);
+	else
+		u.l[0] = current->thread.TS_FPR(rn);
+	if (nb == 4) {
+		if (op->type & FPCONV)
+			conv_dp_to_sp(&u.d[0], &u.f);
+		else
+			u.u = u.l[0];
+	}
+	if (nb == 16) {
+		rn |= 1;
+		if (regs->msr & MSR_FP)
+			get_fpr(rn, &u.d[1]);
+		else
+			u.l[1] = current->thread.TS_FPR(rn);
+	}
+	preempt_enable();
+	if (unlikely(cross_endian)) {
+		do_byte_reverse(u.b, min(nb, 8));
+		if (nb == 16)
+			do_byte_reverse(&u.b[8], 8);
+	}
+	return copy_mem_out(u.b, ea, nb, regs);
+}
+NOKPROBE_SYMBOL(do_fp_store);
+#endif
+
+#ifdef CONFIG_ALTIVEC
+/* For Altivec/VMX, no need to worry about alignment */
+static nokprobe_inline int do_vec_load(int rn, unsigned long ea,
+				       int size, struct pt_regs *regs,
+				       bool cross_endian)
+{
+	int err;
+	union {
+		__vector128 v;
+		u8 b[sizeof(__vector128)];
+	} u = {};
+
+	if (!address_ok(regs, ea & ~0xfUL, 16))
+		return -EFAULT;
+	/* align to multiple of size */
+	ea &= ~(size - 1);
+	err = copy_mem_in(&u.b[ea & 0xf], ea, size, regs);
+	if (err)
+		return err;
+	if (unlikely(cross_endian))
+		do_byte_reverse(&u.b[ea & 0xf], size);
+	preempt_disable();
+	if (regs->msr & MSR_VEC)
+		put_vr(rn, &u.v);
+	else
+		current->thread.vr_state.vr[rn] = u.v;
+	preempt_enable();
+	return 0;
+}
+
+static nokprobe_inline int do_vec_store(int rn, unsigned long ea,
+					int size, struct pt_regs *regs,
+					bool cross_endian)
+{
+	union {
+		__vector128 v;
+		u8 b[sizeof(__vector128)];
+	} u;
+
+	if (!address_ok(regs, ea & ~0xfUL, 16))
+		return -EFAULT;
+	/* align to multiple of size */
+	ea &= ~(size - 1);
+
+	preempt_disable();
+	if (regs->msr & MSR_VEC)
+		get_vr(rn, &u.v);
+	else
+		u.v = current->thread.vr_state.vr[rn];
+	preempt_enable();
+	if (unlikely(cross_endian))
+		do_byte_reverse(&u.b[ea & 0xf], size);
+	return copy_mem_out(&u.b[ea & 0xf], ea, size, regs);
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef __powerpc64__
+static nokprobe_inline int emulate_lq(struct pt_regs *regs, unsigned long ea,
+				      int reg, bool cross_endian)
+{
+	int err;
+
+	if (!address_ok(regs, ea, 16))
+		return -EFAULT;
+	/* if aligned, should be atomic */
+	if ((ea & 0xf) == 0) {
+		err = do_lq(ea, &regs->gpr[reg]);
+	} else {
+		err = read_mem(&regs->gpr[reg + IS_LE], ea, 8, regs);
+		if (!err)
+			err = read_mem(&regs->gpr[reg + IS_BE], ea + 8, 8, regs);
+	}
+	if (!err && unlikely(cross_endian))
+		do_byte_reverse(&regs->gpr[reg], 16);
+	return err;
+}
+
+static nokprobe_inline int emulate_stq(struct pt_regs *regs, unsigned long ea,
+				       int reg, bool cross_endian)
+{
+	int err;
+	unsigned long vals[2];
+
+	if (!address_ok(regs, ea, 16))
+		return -EFAULT;
+	vals[0] = regs->gpr[reg];
+	vals[1] = regs->gpr[reg + 1];
+	if (unlikely(cross_endian))
+		do_byte_reverse(vals, 16);
+
+	/* if aligned, should be atomic */
+	if ((ea & 0xf) == 0)
+		return do_stq(ea, vals[0], vals[1]);
+
+	err = write_mem(vals[IS_LE], ea, 8, regs);
+	if (!err)
+		err = write_mem(vals[IS_BE], ea + 8, 8, regs);
+	return err;
+}
+#endif /* __powerpc64 */
+
+#ifdef CONFIG_VSX
+void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
+		      const void *mem, bool rev)
+{
+	int size, read_size;
+	int i, j;
+	const unsigned int *wp;
+	const unsigned short *hp;
+	const unsigned char *bp;
+
+	size = GETSIZE(op->type);
+	reg->d[0] = reg->d[1] = 0;
+
+	switch (op->element_size) {
+	case 16:
+		/* whole vector; lxv[x] or lxvl[l] */
+		if (size == 0)
+			break;
+		memcpy(reg, mem, size);
+		if (IS_LE && (op->vsx_flags & VSX_LDLEFT))
+			rev = !rev;
+		if (rev)
+			do_byte_reverse(reg, 16);
+		break;
+	case 8:
+		/* scalar loads, lxvd2x, lxvdsx */
+		read_size = (size >= 8) ? 8 : size;
+		i = IS_LE ? 8 : 8 - read_size;
+		memcpy(&reg->b[i], mem, read_size);
+		if (rev)
+			do_byte_reverse(&reg->b[i], 8);
+		if (size < 8) {
+			if (op->type & SIGNEXT) {
+				/* size == 4 is the only case here */
+				reg->d[IS_LE] = (signed int) reg->d[IS_LE];
+			} else if (op->vsx_flags & VSX_FPCONV) {
+				preempt_disable();
+				conv_sp_to_dp(&reg->fp[1 + IS_LE],
+					      &reg->dp[IS_LE]);
+				preempt_enable();
+			}
+		} else {
+			if (size == 16) {
+				unsigned long v = *(unsigned long *)(mem + 8);
+				reg->d[IS_BE] = !rev ? v : byterev_8(v);
+			} else if (op->vsx_flags & VSX_SPLAT)
+				reg->d[IS_BE] = reg->d[IS_LE];
+		}
+		break;
+	case 4:
+		/* lxvw4x, lxvwsx */
+		wp = mem;
+		for (j = 0; j < size / 4; ++j) {
+			i = IS_LE ? 3 - j : j;
+			reg->w[i] = !rev ? *wp++ : byterev_4(*wp++);
+		}
+		if (op->vsx_flags & VSX_SPLAT) {
+			u32 val = reg->w[IS_LE ? 3 : 0];
+			for (; j < 4; ++j) {
+				i = IS_LE ? 3 - j : j;
+				reg->w[i] = val;
+			}
+		}
+		break;
+	case 2:
+		/* lxvh8x */
+		hp = mem;
+		for (j = 0; j < size / 2; ++j) {
+			i = IS_LE ? 7 - j : j;
+			reg->h[i] = !rev ? *hp++ : byterev_2(*hp++);
+		}
+		break;
+	case 1:
+		/* lxvb16x */
+		bp = mem;
+		for (j = 0; j < size; ++j) {
+			i = IS_LE ? 15 - j : j;
+			reg->b[i] = *bp++;
+		}
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(emulate_vsx_load);
+NOKPROBE_SYMBOL(emulate_vsx_load);
+
+void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
+		       void *mem, bool rev)
+{
+	int size, write_size;
+	int i, j;
+	union vsx_reg buf;
+	unsigned int *wp;
+	unsigned short *hp;
+	unsigned char *bp;
+
+	size = GETSIZE(op->type);
+
+	switch (op->element_size) {
+	case 16:
+		/* stxv, stxvx, stxvl, stxvll */
+		if (size == 0)
+			break;
+		if (IS_LE && (op->vsx_flags & VSX_LDLEFT))
+			rev = !rev;
+		if (rev) {
+			/* reverse 16 bytes */
+			buf.d[0] = byterev_8(reg->d[1]);
+			buf.d[1] = byterev_8(reg->d[0]);
+			reg = &buf;
+		}
+		memcpy(mem, reg, size);
+		break;
+	case 8:
+		/* scalar stores, stxvd2x */
+		write_size = (size >= 8) ? 8 : size;
+		i = IS_LE ? 8 : 8 - write_size;
+		if (size < 8 && op->vsx_flags & VSX_FPCONV) {
+			buf.d[0] = buf.d[1] = 0;
+			preempt_disable();
+			conv_dp_to_sp(&reg->dp[IS_LE], &buf.fp[1 + IS_LE]);
+			preempt_enable();
+			reg = &buf;
+		}
+		memcpy(mem, &reg->b[i], write_size);
+		if (size == 16)
+			memcpy(mem + 8, &reg->d[IS_BE], 8);
+		if (unlikely(rev)) {
+			do_byte_reverse(mem, write_size);
+			if (size == 16)
+				do_byte_reverse(mem + 8, 8);
+		}
+		break;
+	case 4:
+		/* stxvw4x */
+		wp = mem;
+		for (j = 0; j < size / 4; ++j) {
+			i = IS_LE ? 3 - j : j;
+			*wp++ = !rev ? reg->w[i] : byterev_4(reg->w[i]);
+		}
+		break;
+	case 2:
+		/* stxvh8x */
+		hp = mem;
+		for (j = 0; j < size / 2; ++j) {
+			i = IS_LE ? 7 - j : j;
+			*hp++ = !rev ? reg->h[i] : byterev_2(reg->h[i]);
+		}
+		break;
+	case 1:
+		/* stvxb16x */
+		bp = mem;
+		for (j = 0; j < size; ++j) {
+			i = IS_LE ? 15 - j : j;
+			*bp++ = reg->b[i];
+		}
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(emulate_vsx_store);
+NOKPROBE_SYMBOL(emulate_vsx_store);
+
+static nokprobe_inline int do_vsx_load(struct instruction_op *op,
+				       unsigned long ea, struct pt_regs *regs,
+				       bool cross_endian)
+{
+	int reg = op->reg;
+	u8 mem[16];
+	union vsx_reg buf;
+	int size = GETSIZE(op->type);
+
+	if (!address_ok(regs, ea, size) || copy_mem_in(mem, ea, size, regs))
+		return -EFAULT;
+
+	emulate_vsx_load(op, &buf, mem, cross_endian);
+	preempt_disable();
+	if (reg < 32) {
+		/* FP regs + extensions */
+		if (regs->msr & MSR_FP) {
+			load_vsrn(reg, &buf);
+		} else {
+			current->thread.fp_state.fpr[reg][0] = buf.d[0];
+			current->thread.fp_state.fpr[reg][1] = buf.d[1];
+		}
+	} else {
+		if (regs->msr & MSR_VEC)
+			load_vsrn(reg, &buf);
+		else
+			current->thread.vr_state.vr[reg - 32] = buf.v;
+	}
+	preempt_enable();
+	return 0;
+}
+
+static nokprobe_inline int do_vsx_store(struct instruction_op *op,
+					unsigned long ea, struct pt_regs *regs,
+					bool cross_endian)
+{
+	int reg = op->reg;
+	u8 mem[16];
+	union vsx_reg buf;
+	int size = GETSIZE(op->type);
+
+	if (!address_ok(regs, ea, size))
+		return -EFAULT;
+
+	preempt_disable();
+	if (reg < 32) {
+		/* FP regs + extensions */
+		if (regs->msr & MSR_FP) {
+			store_vsrn(reg, &buf);
+		} else {
+			buf.d[0] = current->thread.fp_state.fpr[reg][0];
+			buf.d[1] = current->thread.fp_state.fpr[reg][1];
+		}
+	} else {
+		if (regs->msr & MSR_VEC)
+			store_vsrn(reg, &buf);
+		else
+			buf.v = current->thread.vr_state.vr[reg - 32];
+	}
+	preempt_enable();
+	emulate_vsx_store(op, &buf, mem, cross_endian);
+	return  copy_mem_out(mem, ea, size, regs);
+}
+#endif /* CONFIG_VSX */
+
+int emulate_dcbz(unsigned long ea, struct pt_regs *regs)
+{
+	int err;
+	unsigned long i, size;
+
+#ifdef __powerpc64__
+	size = ppc64_caches.l1d.block_size;
+	if (!(regs->msr & MSR_64BIT))
+		ea &= 0xffffffffUL;
+#else
+	size = L1_CACHE_BYTES;
+#endif
+	ea &= ~(size - 1);
+	if (!address_ok(regs, ea, size))
+		return -EFAULT;
+	for (i = 0; i < size; i += sizeof(long)) {
+		err = __put_user(0, (unsigned long __user *) (ea + i));
+		if (err) {
+			regs->dar = ea;
+			return err;
+		}
+	}
+	return 0;
+}
+NOKPROBE_SYMBOL(emulate_dcbz);
+
+#define __put_user_asmx(x, addr, err, op, cr)		\
+	__asm__ __volatile__(				\
+		".machine push\n"			\
+		".machine power8\n"			\
+		"1:	" op " %2,0,%3\n"		\
+		".machine pop\n"			\
+		"	mfcr	%1\n"			\
+		"2:\n"					\
+		".section .fixup,\"ax\"\n"		\
+		"3:	li	%0,%4\n"		\
+		"	b	2b\n"			\
+		".previous\n"				\
+		EX_TABLE(1b, 3b)			\
+		: "=r" (err), "=r" (cr)			\
+		: "r" (x), "r" (addr), "i" (-EFAULT), "0" (err))
+
+#define __get_user_asmx(x, addr, err, op)		\
+	__asm__ __volatile__(				\
+		".machine push\n"			\
+		".machine power8\n"			\
+		"1:	"op" %1,0,%2\n"			\
+		".machine pop\n"			\
+		"2:\n"					\
+		".section .fixup,\"ax\"\n"		\
+		"3:	li	%0,%3\n"		\
+		"	b	2b\n"			\
+		".previous\n"				\
+		EX_TABLE(1b, 3b)			\
+		: "=r" (err), "=r" (x)			\
+		: "r" (addr), "i" (-EFAULT), "0" (err))
+
+#define __cacheop_user_asmx(addr, err, op)		\
+	__asm__ __volatile__(				\
+		"1:	"op" 0,%1\n"			\
+		"2:\n"					\
+		".section .fixup,\"ax\"\n"		\
+		"3:	li	%0,%3\n"		\
+		"	b	2b\n"			\
+		".previous\n"				\
+		EX_TABLE(1b, 3b)			\
+		: "=r" (err)				\
+		: "r" (addr), "i" (-EFAULT), "0" (err))
+
+static nokprobe_inline void set_cr0(const struct pt_regs *regs,
+				    struct instruction_op *op)
+{
+	long val = op->val;
+
+	op->type |= SETCC;
+	op->ccval = (regs->ccr & 0x0fffffff) | ((regs->xer >> 3) & 0x10000000);
+#ifdef __powerpc64__
+	if (!(regs->msr & MSR_64BIT))
+		val = (int) val;
+#endif
+	if (val < 0)
+		op->ccval |= 0x80000000;
+	else if (val > 0)
+		op->ccval |= 0x40000000;
+	else
+		op->ccval |= 0x20000000;
+}
+
+static nokprobe_inline void set_ca32(struct instruction_op *op, bool val)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (val)
+			op->xerval |= XER_CA32;
+		else
+			op->xerval &= ~XER_CA32;
+	}
+}
+
+static nokprobe_inline void add_with_carry(const struct pt_regs *regs,
+				     struct instruction_op *op, int rd,
+				     unsigned long val1, unsigned long val2,
+				     unsigned long carry_in)
+{
+	unsigned long val = val1 + val2;
+
+	if (carry_in)
+		++val;
+	op->type = COMPUTE + SETREG + SETXER;
+	op->reg = rd;
+	op->val = val;
+#ifdef __powerpc64__
+	if (!(regs->msr & MSR_64BIT)) {
+		val = (unsigned int) val;
+		val1 = (unsigned int) val1;
+	}
+#endif
+	op->xerval = regs->xer;
+	if (val < val1 || (carry_in && val == val1))
+		op->xerval |= XER_CA;
+	else
+		op->xerval &= ~XER_CA;
+
+	set_ca32(op, (unsigned int)val < (unsigned int)val1 ||
+			(carry_in && (unsigned int)val == (unsigned int)val1));
+}
+
+static nokprobe_inline void do_cmp_signed(const struct pt_regs *regs,
+					  struct instruction_op *op,
+					  long v1, long v2, int crfld)
+{
+	unsigned int crval, shift;
+
+	op->type = COMPUTE + SETCC;
+	crval = (regs->xer >> 31) & 1;		/* get SO bit */
+	if (v1 < v2)
+		crval |= 8;
+	else if (v1 > v2)
+		crval |= 4;
+	else
+		crval |= 2;
+	shift = (7 - crfld) * 4;
+	op->ccval = (regs->ccr & ~(0xf << shift)) | (crval << shift);
+}
+
+static nokprobe_inline void do_cmp_unsigned(const struct pt_regs *regs,
+					    struct instruction_op *op,
+					    unsigned long v1,
+					    unsigned long v2, int crfld)
+{
+	unsigned int crval, shift;
+
+	op->type = COMPUTE + SETCC;
+	crval = (regs->xer >> 31) & 1;		/* get SO bit */
+	if (v1 < v2)
+		crval |= 8;
+	else if (v1 > v2)
+		crval |= 4;
+	else
+		crval |= 2;
+	shift = (7 - crfld) * 4;
+	op->ccval = (regs->ccr & ~(0xf << shift)) | (crval << shift);
+}
+
+static nokprobe_inline void do_cmpb(const struct pt_regs *regs,
+				    struct instruction_op *op,
+				    unsigned long v1, unsigned long v2)
+{
+	unsigned long long out_val, mask;
+	int i;
+
+	out_val = 0;
+	for (i = 0; i < 8; i++) {
+		mask = 0xffUL << (i * 8);
+		if ((v1 & mask) == (v2 & mask))
+			out_val |= mask;
+	}
+	op->val = out_val;
+}
+
+/*
+ * The size parameter is used to adjust the equivalent popcnt instruction.
+ * popcntb = 8, popcntw = 32, popcntd = 64
+ */
+static nokprobe_inline void do_popcnt(const struct pt_regs *regs,
+				      struct instruction_op *op,
+				      unsigned long v1, int size)
+{
+	unsigned long long out = v1;
+
+	out -= (out >> 1) & 0x5555555555555555ULL;
+	out = (0x3333333333333333ULL & out) +
+	      (0x3333333333333333ULL & (out >> 2));
+	out = (out + (out >> 4)) & 0x0f0f0f0f0f0f0f0fULL;
+
+	if (size == 8) {	/* popcntb */
+		op->val = out;
+		return;
+	}
+	out += out >> 8;
+	out += out >> 16;
+	if (size == 32) {	/* popcntw */
+		op->val = out & 0x0000003f0000003fULL;
+		return;
+	}
+
+	out = (out + (out >> 32)) & 0x7f;
+	op->val = out;	/* popcntd */
+}
+
+#ifdef CONFIG_PPC64
+static nokprobe_inline void do_bpermd(const struct pt_regs *regs,
+				      struct instruction_op *op,
+				      unsigned long v1, unsigned long v2)
+{
+	unsigned char perm, idx;
+	unsigned int i;
+
+	perm = 0;
+	for (i = 0; i < 8; i++) {
+		idx = (v1 >> (i * 8)) & 0xff;
+		if (idx < 64)
+			if (v2 & PPC_BIT(idx))
+				perm |= 1 << i;
+	}
+	op->val = perm;
+}
+#endif /* CONFIG_PPC64 */
+/*
+ * The size parameter adjusts the equivalent prty instruction.
+ * prtyw = 32, prtyd = 64
+ */
+static nokprobe_inline void do_prty(const struct pt_regs *regs,
+				    struct instruction_op *op,
+				    unsigned long v, int size)
+{
+	unsigned long long res = v ^ (v >> 8);
+
+	res ^= res >> 16;
+	if (size == 32) {		/* prtyw */
+		op->val = res & 0x0000000100000001ULL;
+		return;
+	}
+
+	res ^= res >> 32;
+	op->val = res & 1;	/*prtyd */
+}
+
+static nokprobe_inline int trap_compare(long v1, long v2)
+{
+	int ret = 0;
+
+	if (v1 < v2)
+		ret |= 0x10;
+	else if (v1 > v2)
+		ret |= 0x08;
+	else
+		ret |= 0x04;
+	if ((unsigned long)v1 < (unsigned long)v2)
+		ret |= 0x02;
+	else if ((unsigned long)v1 > (unsigned long)v2)
+		ret |= 0x01;
+	return ret;
+}
+
+/*
+ * Elements of 32-bit rotate and mask instructions.
+ */
+#define MASK32(mb, me)	((0xffffffffUL >> (mb)) + \
+			 ((signed long)-0x80000000L >> (me)) + ((me) >= (mb)))
+#ifdef __powerpc64__
+#define MASK64_L(mb)	(~0UL >> (mb))
+#define MASK64_R(me)	((signed long)-0x8000000000000000L >> (me))
+#define MASK64(mb, me)	(MASK64_L(mb) + MASK64_R(me) + ((me) >= (mb)))
+#define DATA32(x)	(((x) & 0xffffffffUL) | (((x) & 0xffffffffUL) << 32))
+#else
+#define DATA32(x)	(x)
+#endif
+#define ROTATE(x, n)	((n) ? (((x) << (n)) | ((x) >> (8 * sizeof(long) - (n)))) : (x))
+
+/*
+ * Decode an instruction, and return information about it in *op
+ * without changing *regs.
+ * Integer arithmetic and logical instructions, branches, and barrier
+ * instructions can be emulated just using the information in *op.
+ *
+ * Return value is 1 if the instruction can be emulated just by
+ * updating *regs with the information in *op, -1 if we need the
+ * GPRs but *regs doesn't contain the full register set, or 0
+ * otherwise.
+ */
+int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
+		  unsigned int instr)
+{
+	unsigned int opcode, ra, rb, rd, spr, u;
+	unsigned long int imm;
+	unsigned long int val, val2;
+	unsigned int mb, me, sh;
+	long ival;
+
+	op->type = COMPUTE;
+
+	opcode = instr >> 26;
+	switch (opcode) {
+	case 16:	/* bc */
+		op->type = BRANCH;
+		imm = (signed short)(instr & 0xfffc);
+		if ((instr & 2) == 0)
+			imm += regs->nip;
+		op->val = truncate_if_32bit(regs->msr, imm);
+		if (instr & 1)
+			op->type |= SETLK;
+		if (branch_taken(instr, regs, op))
+			op->type |= BRTAKEN;
+		return 1;
+#ifdef CONFIG_PPC64
+	case 17:	/* sc */
+		if ((instr & 0xfe2) == 2)
+			op->type = SYSCALL;
+		else
+			op->type = UNKNOWN;
+		return 0;
+#endif
+	case 18:	/* b */
+		op->type = BRANCH | BRTAKEN;
+		imm = instr & 0x03fffffc;
+		if (imm & 0x02000000)
+			imm -= 0x04000000;
+		if ((instr & 2) == 0)
+			imm += regs->nip;
+		op->val = truncate_if_32bit(regs->msr, imm);
+		if (instr & 1)
+			op->type |= SETLK;
+		return 1;
+	case 19:
+		switch ((instr >> 1) & 0x3ff) {
+		case 0:		/* mcrf */
+			op->type = COMPUTE + SETCC;
+			rd = 7 - ((instr >> 23) & 0x7);
+			ra = 7 - ((instr >> 18) & 0x7);
+			rd *= 4;
+			ra *= 4;
+			val = (regs->ccr >> ra) & 0xf;
+			op->ccval = (regs->ccr & ~(0xfUL << rd)) | (val << rd);
+			return 1;
+
+		case 16:	/* bclr */
+		case 528:	/* bcctr */
+			op->type = BRANCH;
+			imm = (instr & 0x400)? regs->ctr: regs->link;
+			op->val = truncate_if_32bit(regs->msr, imm);
+			if (instr & 1)
+				op->type |= SETLK;
+			if (branch_taken(instr, regs, op))
+				op->type |= BRTAKEN;
+			return 1;
+
+		case 18:	/* rfid, scary */
+			if (regs->msr & MSR_PR)
+				goto priv;
+			op->type = RFI;
+			return 0;
+
+		case 150:	/* isync */
+			op->type = BARRIER | BARRIER_ISYNC;
+			return 1;
+
+		case 33:	/* crnor */
+		case 129:	/* crandc */
+		case 193:	/* crxor */
+		case 225:	/* crnand */
+		case 257:	/* crand */
+		case 289:	/* creqv */
+		case 417:	/* crorc */
+		case 449:	/* cror */
+			op->type = COMPUTE + SETCC;
+			ra = (instr >> 16) & 0x1f;
+			rb = (instr >> 11) & 0x1f;
+			rd = (instr >> 21) & 0x1f;
+			ra = (regs->ccr >> (31 - ra)) & 1;
+			rb = (regs->ccr >> (31 - rb)) & 1;
+			val = (instr >> (6 + ra * 2 + rb)) & 1;
+			op->ccval = (regs->ccr & ~(1UL << (31 - rd))) |
+				(val << (31 - rd));
+			return 1;
+		}
+		break;
+	case 31:
+		switch ((instr >> 1) & 0x3ff) {
+		case 598:	/* sync */
+			op->type = BARRIER + BARRIER_SYNC;
+#ifdef __powerpc64__
+			switch ((instr >> 21) & 3) {
+			case 1:		/* lwsync */
+				op->type = BARRIER + BARRIER_LWSYNC;
+				break;
+			case 2:		/* ptesync */
+				op->type = BARRIER + BARRIER_PTESYNC;
+				break;
+			}
+#endif
+			return 1;
+
+		case 854:	/* eieio */
+			op->type = BARRIER + BARRIER_EIEIO;
+			return 1;
+		}
+		break;
+	}
+
+	/* Following cases refer to regs->gpr[], so we need all regs */
+	if (!FULL_REGS(regs))
+		return -1;
+
+	rd = (instr >> 21) & 0x1f;
+	ra = (instr >> 16) & 0x1f;
+	rb = (instr >> 11) & 0x1f;
+
+	switch (opcode) {
+#ifdef __powerpc64__
+	case 2:		/* tdi */
+		if (rd & trap_compare(regs->gpr[ra], (short) instr))
+			goto trap;
+		return 1;
+#endif
+	case 3:		/* twi */
+		if (rd & trap_compare((int)regs->gpr[ra], (short) instr))
+			goto trap;
+		return 1;
+
+	case 7:		/* mulli */
+		op->val = regs->gpr[ra] * (short) instr;
+		goto compute_done;
+
+	case 8:		/* subfic */
+		imm = (short) instr;
+		add_with_carry(regs, op, rd, ~regs->gpr[ra], imm, 1);
+		return 1;
+
+	case 10:	/* cmpli */
+		imm = (unsigned short) instr;
+		val = regs->gpr[ra];
+#ifdef __powerpc64__
+		if ((rd & 1) == 0)
+			val = (unsigned int) val;
+#endif
+		do_cmp_unsigned(regs, op, val, imm, rd >> 2);
+		return 1;
+
+	case 11:	/* cmpi */
+		imm = (short) instr;
+		val = regs->gpr[ra];
+#ifdef __powerpc64__
+		if ((rd & 1) == 0)
+			val = (int) val;
+#endif
+		do_cmp_signed(regs, op, val, imm, rd >> 2);
+		return 1;
+
+	case 12:	/* addic */
+		imm = (short) instr;
+		add_with_carry(regs, op, rd, regs->gpr[ra], imm, 0);
+		return 1;
+
+	case 13:	/* addic. */
+		imm = (short) instr;
+		add_with_carry(regs, op, rd, regs->gpr[ra], imm, 0);
+		set_cr0(regs, op);
+		return 1;
+
+	case 14:	/* addi */
+		imm = (short) instr;
+		if (ra)
+			imm += regs->gpr[ra];
+		op->val = imm;
+		goto compute_done;
+
+	case 15:	/* addis */
+		imm = ((short) instr) << 16;
+		if (ra)
+			imm += regs->gpr[ra];
+		op->val = imm;
+		goto compute_done;
+
+	case 19:
+		if (((instr >> 1) & 0x1f) == 2) {
+			/* addpcis */
+			imm = (short) (instr & 0xffc1);	/* d0 + d2 fields */
+			imm |= (instr >> 15) & 0x3e;	/* d1 field */
+			op->val = regs->nip + (imm << 16) + 4;
+			goto compute_done;
+		}
+		op->type = UNKNOWN;
+		return 0;
+
+	case 20:	/* rlwimi */
+		mb = (instr >> 6) & 0x1f;
+		me = (instr >> 1) & 0x1f;
+		val = DATA32(regs->gpr[rd]);
+		imm = MASK32(mb, me);
+		op->val = (regs->gpr[ra] & ~imm) | (ROTATE(val, rb) & imm);
+		goto logical_done;
+
+	case 21:	/* rlwinm */
+		mb = (instr >> 6) & 0x1f;
+		me = (instr >> 1) & 0x1f;
+		val = DATA32(regs->gpr[rd]);
+		op->val = ROTATE(val, rb) & MASK32(mb, me);
+		goto logical_done;
+
+	case 23:	/* rlwnm */
+		mb = (instr >> 6) & 0x1f;
+		me = (instr >> 1) & 0x1f;
+		rb = regs->gpr[rb] & 0x1f;
+		val = DATA32(regs->gpr[rd]);
+		op->val = ROTATE(val, rb) & MASK32(mb, me);
+		goto logical_done;
+
+	case 24:	/* ori */
+		op->val = regs->gpr[rd] | (unsigned short) instr;
+		goto logical_done_nocc;
+
+	case 25:	/* oris */
+		imm = (unsigned short) instr;
+		op->val = regs->gpr[rd] | (imm << 16);
+		goto logical_done_nocc;
+
+	case 26:	/* xori */
+		op->val = regs->gpr[rd] ^ (unsigned short) instr;
+		goto logical_done_nocc;
+
+	case 27:	/* xoris */
+		imm = (unsigned short) instr;
+		op->val = regs->gpr[rd] ^ (imm << 16);
+		goto logical_done_nocc;
+
+	case 28:	/* andi. */
+		op->val = regs->gpr[rd] & (unsigned short) instr;
+		set_cr0(regs, op);
+		goto logical_done_nocc;
+
+	case 29:	/* andis. */
+		imm = (unsigned short) instr;
+		op->val = regs->gpr[rd] & (imm << 16);
+		set_cr0(regs, op);
+		goto logical_done_nocc;
+
+#ifdef __powerpc64__
+	case 30:	/* rld* */
+		mb = ((instr >> 6) & 0x1f) | (instr & 0x20);
+		val = regs->gpr[rd];
+		if ((instr & 0x10) == 0) {
+			sh = rb | ((instr & 2) << 4);
+			val = ROTATE(val, sh);
+			switch ((instr >> 2) & 3) {
+			case 0:		/* rldicl */
+				val &= MASK64_L(mb);
+				break;
+			case 1:		/* rldicr */
+				val &= MASK64_R(mb);
+				break;
+			case 2:		/* rldic */
+				val &= MASK64(mb, 63 - sh);
+				break;
+			case 3:		/* rldimi */
+				imm = MASK64(mb, 63 - sh);
+				val = (regs->gpr[ra] & ~imm) |
+					(val & imm);
+			}
+			op->val = val;
+			goto logical_done;
+		} else {
+			sh = regs->gpr[rb] & 0x3f;
+			val = ROTATE(val, sh);
+			switch ((instr >> 1) & 7) {
+			case 0:		/* rldcl */
+				op->val = val & MASK64_L(mb);
+				goto logical_done;
+			case 1:		/* rldcr */
+				op->val = val & MASK64_R(mb);
+				goto logical_done;
+			}
+		}
+#endif
+		op->type = UNKNOWN;	/* illegal instruction */
+		return 0;
+
+	case 31:
+		/* isel occupies 32 minor opcodes */
+		if (((instr >> 1) & 0x1f) == 15) {
+			mb = (instr >> 6) & 0x1f; /* bc field */
+			val = (regs->ccr >> (31 - mb)) & 1;
+			val2 = (ra) ? regs->gpr[ra] : 0;
+
+			op->val = (val) ? val2 : regs->gpr[rb];
+			goto compute_done;
+		}
+
+		switch ((instr >> 1) & 0x3ff) {
+		case 4:		/* tw */
+			if (rd == 0x1f ||
+			    (rd & trap_compare((int)regs->gpr[ra],
+					       (int)regs->gpr[rb])))
+				goto trap;
+			return 1;
+#ifdef __powerpc64__
+		case 68:	/* td */
+			if (rd & trap_compare(regs->gpr[ra], regs->gpr[rb]))
+				goto trap;
+			return 1;
+#endif
+		case 83:	/* mfmsr */
+			if (regs->msr & MSR_PR)
+				goto priv;
+			op->type = MFMSR;
+			op->reg = rd;
+			return 0;
+		case 146:	/* mtmsr */
+			if (regs->msr & MSR_PR)
+				goto priv;
+			op->type = MTMSR;
+			op->reg = rd;
+			op->val = 0xffffffff & ~(MSR_ME | MSR_LE);
+			return 0;
+#ifdef CONFIG_PPC64
+		case 178:	/* mtmsrd */
+			if (regs->msr & MSR_PR)
+				goto priv;
+			op->type = MTMSR;
+			op->reg = rd;
+			/* only MSR_EE and MSR_RI get changed if bit 15 set */
+			/* mtmsrd doesn't change MSR_HV, MSR_ME or MSR_LE */
+			imm = (instr & 0x10000)? 0x8002: 0xefffffffffffeffeUL;
+			op->val = imm;
+			return 0;
+#endif
+
+		case 19:	/* mfcr */
+			imm = 0xffffffffUL;
+			if ((instr >> 20) & 1) {
+				imm = 0xf0000000UL;
+				for (sh = 0; sh < 8; ++sh) {
+					if (instr & (0x80000 >> sh))
+						break;
+					imm >>= 4;
+				}
+			}
+			op->val = regs->ccr & imm;
+			goto compute_done;
+
+		case 144:	/* mtcrf */
+			op->type = COMPUTE + SETCC;
+			imm = 0xf0000000UL;
+			val = regs->gpr[rd];
+			op->ccval = regs->ccr;
+			for (sh = 0; sh < 8; ++sh) {
+				if (instr & (0x80000 >> sh))
+					op->ccval = (op->ccval & ~imm) |
+						(val & imm);
+				imm >>= 4;
+			}
+			return 1;
+
+		case 339:	/* mfspr */
+			spr = ((instr >> 16) & 0x1f) | ((instr >> 6) & 0x3e0);
+			op->type = MFSPR;
+			op->reg = rd;
+			op->spr = spr;
+			if (spr == SPRN_XER || spr == SPRN_LR ||
+			    spr == SPRN_CTR)
+				return 1;
+			return 0;
+
+		case 467:	/* mtspr */
+			spr = ((instr >> 16) & 0x1f) | ((instr >> 6) & 0x3e0);
+			op->type = MTSPR;
+			op->val = regs->gpr[rd];
+			op->spr = spr;
+			if (spr == SPRN_XER || spr == SPRN_LR ||
+			    spr == SPRN_CTR)
+				return 1;
+			return 0;
+
+/*
+ * Compare instructions
+ */
+		case 0:	/* cmp */
+			val = regs->gpr[ra];
+			val2 = regs->gpr[rb];
+#ifdef __powerpc64__
+			if ((rd & 1) == 0) {
+				/* word (32-bit) compare */
+				val = (int) val;
+				val2 = (int) val2;
+			}
+#endif
+			do_cmp_signed(regs, op, val, val2, rd >> 2);
+			return 1;
+
+		case 32:	/* cmpl */
+			val = regs->gpr[ra];
+			val2 = regs->gpr[rb];
+#ifdef __powerpc64__
+			if ((rd & 1) == 0) {
+				/* word (32-bit) compare */
+				val = (unsigned int) val;
+				val2 = (unsigned int) val2;
+			}
+#endif
+			do_cmp_unsigned(regs, op, val, val2, rd >> 2);
+			return 1;
+
+		case 508: /* cmpb */
+			do_cmpb(regs, op, regs->gpr[rd], regs->gpr[rb]);
+			goto logical_done_nocc;
+
+/*
+ * Arithmetic instructions
+ */
+		case 8:	/* subfc */
+			add_with_carry(regs, op, rd, ~regs->gpr[ra],
+				       regs->gpr[rb], 1);
+			goto arith_done;
+#ifdef __powerpc64__
+		case 9:	/* mulhdu */
+			asm("mulhdu %0,%1,%2" : "=r" (op->val) :
+			    "r" (regs->gpr[ra]), "r" (regs->gpr[rb]));
+			goto arith_done;
+#endif
+		case 10:	/* addc */
+			add_with_carry(regs, op, rd, regs->gpr[ra],
+				       regs->gpr[rb], 0);
+			goto arith_done;
+
+		case 11:	/* mulhwu */
+			asm("mulhwu %0,%1,%2" : "=r" (op->val) :
+			    "r" (regs->gpr[ra]), "r" (regs->gpr[rb]));
+			goto arith_done;
+
+		case 40:	/* subf */
+			op->val = regs->gpr[rb] - regs->gpr[ra];
+			goto arith_done;
+#ifdef __powerpc64__
+		case 73:	/* mulhd */
+			asm("mulhd %0,%1,%2" : "=r" (op->val) :
+			    "r" (regs->gpr[ra]), "r" (regs->gpr[rb]));
+			goto arith_done;
+#endif
+		case 75:	/* mulhw */
+			asm("mulhw %0,%1,%2" : "=r" (op->val) :
+			    "r" (regs->gpr[ra]), "r" (regs->gpr[rb]));
+			goto arith_done;
+
+		case 104:	/* neg */
+			op->val = -regs->gpr[ra];
+			goto arith_done;
+
+		case 136:	/* subfe */
+			add_with_carry(regs, op, rd, ~regs->gpr[ra],
+				       regs->gpr[rb], regs->xer & XER_CA);
+			goto arith_done;
+
+		case 138:	/* adde */
+			add_with_carry(regs, op, rd, regs->gpr[ra],
+				       regs->gpr[rb], regs->xer & XER_CA);
+			goto arith_done;
+
+		case 200:	/* subfze */
+			add_with_carry(regs, op, rd, ~regs->gpr[ra], 0L,
+				       regs->xer & XER_CA);
+			goto arith_done;
+
+		case 202:	/* addze */
+			add_with_carry(regs, op, rd, regs->gpr[ra], 0L,
+				       regs->xer & XER_CA);
+			goto arith_done;
+
+		case 232:	/* subfme */
+			add_with_carry(regs, op, rd, ~regs->gpr[ra], -1L,
+				       regs->xer & XER_CA);
+			goto arith_done;
+#ifdef __powerpc64__
+		case 233:	/* mulld */
+			op->val = regs->gpr[ra] * regs->gpr[rb];
+			goto arith_done;
+#endif
+		case 234:	/* addme */
+			add_with_carry(regs, op, rd, regs->gpr[ra], -1L,
+				       regs->xer & XER_CA);
+			goto arith_done;
+
+		case 235:	/* mullw */
+			op->val = (long)(int) regs->gpr[ra] *
+				(int) regs->gpr[rb];
+
+			goto arith_done;
+
+		case 266:	/* add */
+			op->val = regs->gpr[ra] + regs->gpr[rb];
+			goto arith_done;
+#ifdef __powerpc64__
+		case 457:	/* divdu */
+			op->val = regs->gpr[ra] / regs->gpr[rb];
+			goto arith_done;
+#endif
+		case 459:	/* divwu */
+			op->val = (unsigned int) regs->gpr[ra] /
+				(unsigned int) regs->gpr[rb];
+			goto arith_done;
+#ifdef __powerpc64__
+		case 489:	/* divd */
+			op->val = (long int) regs->gpr[ra] /
+				(long int) regs->gpr[rb];
+			goto arith_done;
+#endif
+		case 491:	/* divw */
+			op->val = (int) regs->gpr[ra] /
+				(int) regs->gpr[rb];
+			goto arith_done;
+
+
+/*
+ * Logical instructions
+ */
+		case 26:	/* cntlzw */
+			val = (unsigned int) regs->gpr[rd];
+			op->val = ( val ? __builtin_clz(val) : 32 );
+			goto logical_done;
+#ifdef __powerpc64__
+		case 58:	/* cntlzd */
+			val = regs->gpr[rd];
+			op->val = ( val ? __builtin_clzl(val) : 64 );
+			goto logical_done;
+#endif
+		case 28:	/* and */
+			op->val = regs->gpr[rd] & regs->gpr[rb];
+			goto logical_done;
+
+		case 60:	/* andc */
+			op->val = regs->gpr[rd] & ~regs->gpr[rb];
+			goto logical_done;
+
+		case 122:	/* popcntb */
+			do_popcnt(regs, op, regs->gpr[rd], 8);
+			goto logical_done_nocc;
+
+		case 124:	/* nor */
+			op->val = ~(regs->gpr[rd] | regs->gpr[rb]);
+			goto logical_done;
+
+		case 154:	/* prtyw */
+			do_prty(regs, op, regs->gpr[rd], 32);
+			goto logical_done_nocc;
+
+		case 186:	/* prtyd */
+			do_prty(regs, op, regs->gpr[rd], 64);
+			goto logical_done_nocc;
+#ifdef CONFIG_PPC64
+		case 252:	/* bpermd */
+			do_bpermd(regs, op, regs->gpr[rd], regs->gpr[rb]);
+			goto logical_done_nocc;
+#endif
+		case 284:	/* xor */
+			op->val = ~(regs->gpr[rd] ^ regs->gpr[rb]);
+			goto logical_done;
+
+		case 316:	/* xor */
+			op->val = regs->gpr[rd] ^ regs->gpr[rb];
+			goto logical_done;
+
+		case 378:	/* popcntw */
+			do_popcnt(regs, op, regs->gpr[rd], 32);
+			goto logical_done_nocc;
+
+		case 412:	/* orc */
+			op->val = regs->gpr[rd] | ~regs->gpr[rb];
+			goto logical_done;
+
+		case 444:	/* or */
+			op->val = regs->gpr[rd] | regs->gpr[rb];
+			goto logical_done;
+
+		case 476:	/* nand */
+			op->val = ~(regs->gpr[rd] & regs->gpr[rb]);
+			goto logical_done;
+#ifdef CONFIG_PPC64
+		case 506:	/* popcntd */
+			do_popcnt(regs, op, regs->gpr[rd], 64);
+			goto logical_done_nocc;
+#endif
+		case 922:	/* extsh */
+			op->val = (signed short) regs->gpr[rd];
+			goto logical_done;
+
+		case 954:	/* extsb */
+			op->val = (signed char) regs->gpr[rd];
+			goto logical_done;
+#ifdef __powerpc64__
+		case 986:	/* extsw */
+			op->val = (signed int) regs->gpr[rd];
+			goto logical_done;
+#endif
+
+/*
+ * Shift instructions
+ */
+		case 24:	/* slw */
+			sh = regs->gpr[rb] & 0x3f;
+			if (sh < 32)
+				op->val = (regs->gpr[rd] << sh) & 0xffffffffUL;
+			else
+				op->val = 0;
+			goto logical_done;
+
+		case 536:	/* srw */
+			sh = regs->gpr[rb] & 0x3f;
+			if (sh < 32)
+				op->val = (regs->gpr[rd] & 0xffffffffUL) >> sh;
+			else
+				op->val = 0;
+			goto logical_done;
+
+		case 792:	/* sraw */
+			op->type = COMPUTE + SETREG + SETXER;
+			sh = regs->gpr[rb] & 0x3f;
+			ival = (signed int) regs->gpr[rd];
+			op->val = ival >> (sh < 32 ? sh : 31);
+			op->xerval = regs->xer;
+			if (ival < 0 && (sh >= 32 || (ival & ((1ul << sh) - 1)) != 0))
+				op->xerval |= XER_CA;
+			else
+				op->xerval &= ~XER_CA;
+			set_ca32(op, op->xerval & XER_CA);
+			goto logical_done;
+
+		case 824:	/* srawi */
+			op->type = COMPUTE + SETREG + SETXER;
+			sh = rb;
+			ival = (signed int) regs->gpr[rd];
+			op->val = ival >> sh;
+			op->xerval = regs->xer;
+			if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0)
+				op->xerval |= XER_CA;
+			else
+				op->xerval &= ~XER_CA;
+			set_ca32(op, op->xerval & XER_CA);
+			goto logical_done;
+
+#ifdef __powerpc64__
+		case 27:	/* sld */
+			sh = regs->gpr[rb] & 0x7f;
+			if (sh < 64)
+				op->val = regs->gpr[rd] << sh;
+			else
+				op->val = 0;
+			goto logical_done;
+
+		case 539:	/* srd */
+			sh = regs->gpr[rb] & 0x7f;
+			if (sh < 64)
+				op->val = regs->gpr[rd] >> sh;
+			else
+				op->val = 0;
+			goto logical_done;
+
+		case 794:	/* srad */
+			op->type = COMPUTE + SETREG + SETXER;
+			sh = regs->gpr[rb] & 0x7f;
+			ival = (signed long int) regs->gpr[rd];
+			op->val = ival >> (sh < 64 ? sh : 63);
+			op->xerval = regs->xer;
+			if (ival < 0 && (sh >= 64 || (ival & ((1ul << sh) - 1)) != 0))
+				op->xerval |= XER_CA;
+			else
+				op->xerval &= ~XER_CA;
+			set_ca32(op, op->xerval & XER_CA);
+			goto logical_done;
+
+		case 826:	/* sradi with sh_5 = 0 */
+		case 827:	/* sradi with sh_5 = 1 */
+			op->type = COMPUTE + SETREG + SETXER;
+			sh = rb | ((instr & 2) << 4);
+			ival = (signed long int) regs->gpr[rd];
+			op->val = ival >> sh;
+			op->xerval = regs->xer;
+			if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0)
+				op->xerval |= XER_CA;
+			else
+				op->xerval &= ~XER_CA;
+			set_ca32(op, op->xerval & XER_CA);
+			goto logical_done;
+#endif /* __powerpc64__ */
+
+/*
+ * Cache instructions
+ */
+		case 54:	/* dcbst */
+			op->type = MKOP(CACHEOP, DCBST, 0);
+			op->ea = xform_ea(instr, regs);
+			return 0;
+
+		case 86:	/* dcbf */
+			op->type = MKOP(CACHEOP, DCBF, 0);
+			op->ea = xform_ea(instr, regs);
+			return 0;
+
+		case 246:	/* dcbtst */
+			op->type = MKOP(CACHEOP, DCBTST, 0);
+			op->ea = xform_ea(instr, regs);
+			op->reg = rd;
+			return 0;
+
+		case 278:	/* dcbt */
+			op->type = MKOP(CACHEOP, DCBTST, 0);
+			op->ea = xform_ea(instr, regs);
+			op->reg = rd;
+			return 0;
+
+		case 982:	/* icbi */
+			op->type = MKOP(CACHEOP, ICBI, 0);
+			op->ea = xform_ea(instr, regs);
+			return 0;
+
+		case 1014:	/* dcbz */
+			op->type = MKOP(CACHEOP, DCBZ, 0);
+			op->ea = xform_ea(instr, regs);
+			return 0;
+		}
+		break;
+	}
+
+/*
+ * Loads and stores.
+ */
+	op->type = UNKNOWN;
+	op->update_reg = ra;
+	op->reg = rd;
+	op->val = regs->gpr[rd];
+	u = (instr >> 20) & UPDATE;
+	op->vsx_flags = 0;
+
+	switch (opcode) {
+	case 31:
+		u = instr & UPDATE;
+		op->ea = xform_ea(instr, regs);
+		switch ((instr >> 1) & 0x3ff) {
+		case 20:	/* lwarx */
+			op->type = MKOP(LARX, 0, 4);
+			break;
+
+		case 150:	/* stwcx. */
+			op->type = MKOP(STCX, 0, 4);
+			break;
+
+#ifdef __powerpc64__
+		case 84:	/* ldarx */
+			op->type = MKOP(LARX, 0, 8);
+			break;
+
+		case 214:	/* stdcx. */
+			op->type = MKOP(STCX, 0, 8);
+			break;
+
+		case 52:	/* lbarx */
+			op->type = MKOP(LARX, 0, 1);
+			break;
+
+		case 694:	/* stbcx. */
+			op->type = MKOP(STCX, 0, 1);
+			break;
+
+		case 116:	/* lharx */
+			op->type = MKOP(LARX, 0, 2);
+			break;
+
+		case 726:	/* sthcx. */
+			op->type = MKOP(STCX, 0, 2);
+			break;
+
+		case 276:	/* lqarx */
+			if (!((rd & 1) || rd == ra || rd == rb))
+				op->type = MKOP(LARX, 0, 16);
+			break;
+
+		case 182:	/* stqcx. */
+			if (!(rd & 1))
+				op->type = MKOP(STCX, 0, 16);
+			break;
+#endif
+
+		case 23:	/* lwzx */
+		case 55:	/* lwzux */
+			op->type = MKOP(LOAD, u, 4);
+			break;
+
+		case 87:	/* lbzx */
+		case 119:	/* lbzux */
+			op->type = MKOP(LOAD, u, 1);
+			break;
+
+#ifdef CONFIG_ALTIVEC
+		/*
+		 * Note: for the load/store vector element instructions,
+		 * bits of the EA say which field of the VMX register to use.
+		 */
+		case 7:		/* lvebx */
+			op->type = MKOP(LOAD_VMX, 0, 1);
+			op->element_size = 1;
+			break;
+
+		case 39:	/* lvehx */
+			op->type = MKOP(LOAD_VMX, 0, 2);
+			op->element_size = 2;
+			break;
+
+		case 71:	/* lvewx */
+			op->type = MKOP(LOAD_VMX, 0, 4);
+			op->element_size = 4;
+			break;
+
+		case 103:	/* lvx */
+		case 359:	/* lvxl */
+			op->type = MKOP(LOAD_VMX, 0, 16);
+			op->element_size = 16;
+			break;
+
+		case 135:	/* stvebx */
+			op->type = MKOP(STORE_VMX, 0, 1);
+			op->element_size = 1;
+			break;
+
+		case 167:	/* stvehx */
+			op->type = MKOP(STORE_VMX, 0, 2);
+			op->element_size = 2;
+			break;
+
+		case 199:	/* stvewx */
+			op->type = MKOP(STORE_VMX, 0, 4);
+			op->element_size = 4;
+			break;
+
+		case 231:	/* stvx */
+		case 487:	/* stvxl */
+			op->type = MKOP(STORE_VMX, 0, 16);
+			break;
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef __powerpc64__
+		case 21:	/* ldx */
+		case 53:	/* ldux */
+			op->type = MKOP(LOAD, u, 8);
+			break;
+
+		case 149:	/* stdx */
+		case 181:	/* stdux */
+			op->type = MKOP(STORE, u, 8);
+			break;
+#endif
+
+		case 151:	/* stwx */
+		case 183:	/* stwux */
+			op->type = MKOP(STORE, u, 4);
+			break;
+
+		case 215:	/* stbx */
+		case 247:	/* stbux */
+			op->type = MKOP(STORE, u, 1);
+			break;
+
+		case 279:	/* lhzx */
+		case 311:	/* lhzux */
+			op->type = MKOP(LOAD, u, 2);
+			break;
+
+#ifdef __powerpc64__
+		case 341:	/* lwax */
+		case 373:	/* lwaux */
+			op->type = MKOP(LOAD, SIGNEXT | u, 4);
+			break;
+#endif
+
+		case 343:	/* lhax */
+		case 375:	/* lhaux */
+			op->type = MKOP(LOAD, SIGNEXT | u, 2);
+			break;
+
+		case 407:	/* sthx */
+		case 439:	/* sthux */
+			op->type = MKOP(STORE, u, 2);
+			break;
+
+#ifdef __powerpc64__
+		case 532:	/* ldbrx */
+			op->type = MKOP(LOAD, BYTEREV, 8);
+			break;
+
+#endif
+		case 533:	/* lswx */
+			op->type = MKOP(LOAD_MULTI, 0, regs->xer & 0x7f);
+			break;
+
+		case 534:	/* lwbrx */
+			op->type = MKOP(LOAD, BYTEREV, 4);
+			break;
+
+		case 597:	/* lswi */
+			if (rb == 0)
+				rb = 32;	/* # bytes to load */
+			op->type = MKOP(LOAD_MULTI, 0, rb);
+			op->ea = ra ? regs->gpr[ra] : 0;
+			break;
+
+#ifdef CONFIG_PPC_FPU
+		case 535:	/* lfsx */
+		case 567:	/* lfsux */
+			op->type = MKOP(LOAD_FP, u | FPCONV, 4);
+			break;
+
+		case 599:	/* lfdx */
+		case 631:	/* lfdux */
+			op->type = MKOP(LOAD_FP, u, 8);
+			break;
+
+		case 663:	/* stfsx */
+		case 695:	/* stfsux */
+			op->type = MKOP(STORE_FP, u | FPCONV, 4);
+			break;
+
+		case 727:	/* stfdx */
+		case 759:	/* stfdux */
+			op->type = MKOP(STORE_FP, u, 8);
+			break;
+
+#ifdef __powerpc64__
+		case 791:	/* lfdpx */
+			op->type = MKOP(LOAD_FP, 0, 16);
+			break;
+
+		case 855:	/* lfiwax */
+			op->type = MKOP(LOAD_FP, SIGNEXT, 4);
+			break;
+
+		case 887:	/* lfiwzx */
+			op->type = MKOP(LOAD_FP, 0, 4);
+			break;
+
+		case 919:	/* stfdpx */
+			op->type = MKOP(STORE_FP, 0, 16);
+			break;
+
+		case 983:	/* stfiwx */
+			op->type = MKOP(STORE_FP, 0, 4);
+			break;
+#endif /* __powerpc64 */
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef __powerpc64__
+		case 660:	/* stdbrx */
+			op->type = MKOP(STORE, BYTEREV, 8);
+			op->val = byterev_8(regs->gpr[rd]);
+			break;
+
+#endif
+		case 661:	/* stswx */
+			op->type = MKOP(STORE_MULTI, 0, regs->xer & 0x7f);
+			break;
+
+		case 662:	/* stwbrx */
+			op->type = MKOP(STORE, BYTEREV, 4);
+			op->val = byterev_4(regs->gpr[rd]);
+			break;
+
+		case 725:	/* stswi */
+			if (rb == 0)
+				rb = 32;	/* # bytes to store */
+			op->type = MKOP(STORE_MULTI, 0, rb);
+			op->ea = ra ? regs->gpr[ra] : 0;
+			break;
+
+		case 790:	/* lhbrx */
+			op->type = MKOP(LOAD, BYTEREV, 2);
+			break;
+
+		case 918:	/* sthbrx */
+			op->type = MKOP(STORE, BYTEREV, 2);
+			op->val = byterev_2(regs->gpr[rd]);
+			break;
+
+#ifdef CONFIG_VSX
+		case 12:	/* lxsiwzx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 4);
+			op->element_size = 8;
+			break;
+
+		case 76:	/* lxsiwax */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, SIGNEXT, 4);
+			op->element_size = 8;
+			break;
+
+		case 140:	/* stxsiwx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 4);
+			op->element_size = 8;
+			break;
+
+		case 268:	/* lxvx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 16);
+			op->element_size = 16;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 269:	/* lxvl */
+		case 301: {	/* lxvll */
+			int nb;
+			op->reg = rd | ((instr & 1) << 5);
+			op->ea = ra ? regs->gpr[ra] : 0;
+			nb = regs->gpr[rb] & 0xff;
+			if (nb > 16)
+				nb = 16;
+			op->type = MKOP(LOAD_VSX, 0, nb);
+			op->element_size = 16;
+			op->vsx_flags = ((instr & 0x20) ? VSX_LDLEFT : 0) |
+				VSX_CHECK_VEC;
+			break;
+		}
+		case 332:	/* lxvdsx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 8);
+			op->element_size = 8;
+			op->vsx_flags = VSX_SPLAT;
+			break;
+
+		case 364:	/* lxvwsx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 4);
+			op->element_size = 4;
+			op->vsx_flags = VSX_SPLAT | VSX_CHECK_VEC;
+			break;
+
+		case 396:	/* stxvx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 16);
+			op->element_size = 16;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 397:	/* stxvl */
+		case 429: {	/* stxvll */
+			int nb;
+			op->reg = rd | ((instr & 1) << 5);
+			op->ea = ra ? regs->gpr[ra] : 0;
+			nb = regs->gpr[rb] & 0xff;
+			if (nb > 16)
+				nb = 16;
+			op->type = MKOP(STORE_VSX, 0, nb);
+			op->element_size = 16;
+			op->vsx_flags = ((instr & 0x20) ? VSX_LDLEFT : 0) |
+				VSX_CHECK_VEC;
+			break;
+		}
+		case 524:	/* lxsspx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 4);
+			op->element_size = 8;
+			op->vsx_flags = VSX_FPCONV;
+			break;
+
+		case 588:	/* lxsdx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 8);
+			op->element_size = 8;
+			break;
+
+		case 652:	/* stxsspx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 4);
+			op->element_size = 8;
+			op->vsx_flags = VSX_FPCONV;
+			break;
+
+		case 716:	/* stxsdx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 8);
+			op->element_size = 8;
+			break;
+
+		case 780:	/* lxvw4x */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 16);
+			op->element_size = 4;
+			break;
+
+		case 781:	/* lxsibzx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 1);
+			op->element_size = 8;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 812:	/* lxvh8x */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 16);
+			op->element_size = 2;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 813:	/* lxsihzx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 2);
+			op->element_size = 8;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 844:	/* lxvd2x */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 16);
+			op->element_size = 8;
+			break;
+
+		case 876:	/* lxvb16x */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, 0, 16);
+			op->element_size = 1;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 908:	/* stxvw4x */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 16);
+			op->element_size = 4;
+			break;
+
+		case 909:	/* stxsibx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 1);
+			op->element_size = 8;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 940:	/* stxvh8x */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 16);
+			op->element_size = 2;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 941:	/* stxsihx */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 2);
+			op->element_size = 8;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 972:	/* stxvd2x */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 16);
+			op->element_size = 8;
+			break;
+
+		case 1004:	/* stxvb16x */
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, 0, 16);
+			op->element_size = 1;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+#endif /* CONFIG_VSX */
+		}
+		break;
+
+	case 32:	/* lwz */
+	case 33:	/* lwzu */
+		op->type = MKOP(LOAD, u, 4);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 34:	/* lbz */
+	case 35:	/* lbzu */
+		op->type = MKOP(LOAD, u, 1);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 36:	/* stw */
+	case 37:	/* stwu */
+		op->type = MKOP(STORE, u, 4);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 38:	/* stb */
+	case 39:	/* stbu */
+		op->type = MKOP(STORE, u, 1);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 40:	/* lhz */
+	case 41:	/* lhzu */
+		op->type = MKOP(LOAD, u, 2);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 42:	/* lha */
+	case 43:	/* lhau */
+		op->type = MKOP(LOAD, SIGNEXT | u, 2);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 44:	/* sth */
+	case 45:	/* sthu */
+		op->type = MKOP(STORE, u, 2);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 46:	/* lmw */
+		if (ra >= rd)
+			break;		/* invalid form, ra in range to load */
+		op->type = MKOP(LOAD_MULTI, 0, 4 * (32 - rd));
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 47:	/* stmw */
+		op->type = MKOP(STORE_MULTI, 0, 4 * (32 - rd));
+		op->ea = dform_ea(instr, regs);
+		break;
+
+#ifdef CONFIG_PPC_FPU
+	case 48:	/* lfs */
+	case 49:	/* lfsu */
+		op->type = MKOP(LOAD_FP, u | FPCONV, 4);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 50:	/* lfd */
+	case 51:	/* lfdu */
+		op->type = MKOP(LOAD_FP, u, 8);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 52:	/* stfs */
+	case 53:	/* stfsu */
+		op->type = MKOP(STORE_FP, u | FPCONV, 4);
+		op->ea = dform_ea(instr, regs);
+		break;
+
+	case 54:	/* stfd */
+	case 55:	/* stfdu */
+		op->type = MKOP(STORE_FP, u, 8);
+		op->ea = dform_ea(instr, regs);
+		break;
+#endif
+
+#ifdef __powerpc64__
+	case 56:	/* lq */
+		if (!((rd & 1) || (rd == ra)))
+			op->type = MKOP(LOAD, 0, 16);
+		op->ea = dqform_ea(instr, regs);
+		break;
+#endif
+
+#ifdef CONFIG_VSX
+	case 57:	/* lfdp, lxsd, lxssp */
+		op->ea = dsform_ea(instr, regs);
+		switch (instr & 3) {
+		case 0:		/* lfdp */
+			if (rd & 1)
+				break;		/* reg must be even */
+			op->type = MKOP(LOAD_FP, 0, 16);
+			break;
+		case 2:		/* lxsd */
+			op->reg = rd + 32;
+			op->type = MKOP(LOAD_VSX, 0, 8);
+			op->element_size = 8;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+		case 3:		/* lxssp */
+			op->reg = rd + 32;
+			op->type = MKOP(LOAD_VSX, 0, 4);
+			op->element_size = 8;
+			op->vsx_flags = VSX_FPCONV | VSX_CHECK_VEC;
+			break;
+		}
+		break;
+#endif /* CONFIG_VSX */
+
+#ifdef __powerpc64__
+	case 58:	/* ld[u], lwa */
+		op->ea = dsform_ea(instr, regs);
+		switch (instr & 3) {
+		case 0:		/* ld */
+			op->type = MKOP(LOAD, 0, 8);
+			break;
+		case 1:		/* ldu */
+			op->type = MKOP(LOAD, UPDATE, 8);
+			break;
+		case 2:		/* lwa */
+			op->type = MKOP(LOAD, SIGNEXT, 4);
+			break;
+		}
+		break;
+#endif
+
+#ifdef CONFIG_VSX
+	case 61:	/* stfdp, lxv, stxsd, stxssp, stxv */
+		switch (instr & 7) {
+		case 0:		/* stfdp with LSB of DS field = 0 */
+		case 4:		/* stfdp with LSB of DS field = 1 */
+			op->ea = dsform_ea(instr, regs);
+			op->type = MKOP(STORE_FP, 0, 16);
+			break;
+
+		case 1:		/* lxv */
+			op->ea = dqform_ea(instr, regs);
+			if (instr & 8)
+				op->reg = rd + 32;
+			op->type = MKOP(LOAD_VSX, 0, 16);
+			op->element_size = 16;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 2:		/* stxsd with LSB of DS field = 0 */
+		case 6:		/* stxsd with LSB of DS field = 1 */
+			op->ea = dsform_ea(instr, regs);
+			op->reg = rd + 32;
+			op->type = MKOP(STORE_VSX, 0, 8);
+			op->element_size = 8;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+
+		case 3:		/* stxssp with LSB of DS field = 0 */
+		case 7:		/* stxssp with LSB of DS field = 1 */
+			op->ea = dsform_ea(instr, regs);
+			op->reg = rd + 32;
+			op->type = MKOP(STORE_VSX, 0, 4);
+			op->element_size = 8;
+			op->vsx_flags = VSX_FPCONV | VSX_CHECK_VEC;
+			break;
+
+		case 5:		/* stxv */
+			op->ea = dqform_ea(instr, regs);
+			if (instr & 8)
+				op->reg = rd + 32;
+			op->type = MKOP(STORE_VSX, 0, 16);
+			op->element_size = 16;
+			op->vsx_flags = VSX_CHECK_VEC;
+			break;
+		}
+		break;
+#endif /* CONFIG_VSX */
+
+#ifdef __powerpc64__
+	case 62:	/* std[u] */
+		op->ea = dsform_ea(instr, regs);
+		switch (instr & 3) {
+		case 0:		/* std */
+			op->type = MKOP(STORE, 0, 8);
+			break;
+		case 1:		/* stdu */
+			op->type = MKOP(STORE, UPDATE, 8);
+			break;
+		case 2:		/* stq */
+			if (!(rd & 1))
+				op->type = MKOP(STORE, 0, 16);
+			break;
+		}
+		break;
+#endif /* __powerpc64__ */
+
+	}
+
+#ifdef CONFIG_VSX
+	if ((GETTYPE(op->type) == LOAD_VSX ||
+	     GETTYPE(op->type) == STORE_VSX) &&
+	    !cpu_has_feature(CPU_FTR_VSX)) {
+		return -1;
+	}
+#endif /* CONFIG_VSX */
+
+	return 0;
+
+ logical_done:
+	if (instr & 1)
+		set_cr0(regs, op);
+ logical_done_nocc:
+	op->reg = ra;
+	op->type |= SETREG;
+	return 1;
+
+ arith_done:
+	if (instr & 1)
+		set_cr0(regs, op);
+ compute_done:
+	op->reg = rd;
+	op->type |= SETREG;
+	return 1;
+
+ priv:
+	op->type = INTERRUPT | 0x700;
+	op->val = SRR1_PROGPRIV;
+	return 0;
+
+ trap:
+	op->type = INTERRUPT | 0x700;
+	op->val = SRR1_PROGTRAP;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(analyse_instr);
+NOKPROBE_SYMBOL(analyse_instr);
+
+/*
+ * For PPC32 we always use stwu with r1 to change the stack pointer.
+ * So this emulated store may corrupt the exception frame, now we
+ * have to provide the exception frame trampoline, which is pushed
+ * below the kprobed function stack. So we only update gpr[1] but
+ * don't emulate the real store operation. We will do real store
+ * operation safely in exception return code by checking this flag.
+ */
+static nokprobe_inline int handle_stack_update(unsigned long ea, struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC32
+	/*
+	 * Check if we will touch kernel stack overflow
+	 */
+	if (ea - STACK_INT_FRAME_SIZE <= current->thread.ksp_limit) {
+		printk(KERN_CRIT "Can't kprobe this since kernel stack would overflow.\n");
+		return -EINVAL;
+	}
+#endif /* CONFIG_PPC32 */
+	/*
+	 * Check if we already set since that means we'll
+	 * lose the previous value.
+	 */
+	WARN_ON(test_thread_flag(TIF_EMULATE_STACK_STORE));
+	set_thread_flag(TIF_EMULATE_STACK_STORE);
+	return 0;
+}
+
+static nokprobe_inline void do_signext(unsigned long *valp, int size)
+{
+	switch (size) {
+	case 2:
+		*valp = (signed short) *valp;
+		break;
+	case 4:
+		*valp = (signed int) *valp;
+		break;
+	}
+}
+
+static nokprobe_inline void do_byterev(unsigned long *valp, int size)
+{
+	switch (size) {
+	case 2:
+		*valp = byterev_2(*valp);
+		break;
+	case 4:
+		*valp = byterev_4(*valp);
+		break;
+#ifdef __powerpc64__
+	case 8:
+		*valp = byterev_8(*valp);
+		break;
+#endif
+	}
+}
+
+/*
+ * Emulate an instruction that can be executed just by updating
+ * fields in *regs.
+ */
+void emulate_update_regs(struct pt_regs *regs, struct instruction_op *op)
+{
+	unsigned long next_pc;
+
+	next_pc = truncate_if_32bit(regs->msr, regs->nip + 4);
+	switch (GETTYPE(op->type)) {
+	case COMPUTE:
+		if (op->type & SETREG)
+			regs->gpr[op->reg] = op->val;
+		if (op->type & SETCC)
+			regs->ccr = op->ccval;
+		if (op->type & SETXER)
+			regs->xer = op->xerval;
+		break;
+
+	case BRANCH:
+		if (op->type & SETLK)
+			regs->link = next_pc;
+		if (op->type & BRTAKEN)
+			next_pc = op->val;
+		if (op->type & DECCTR)
+			--regs->ctr;
+		break;
+
+	case BARRIER:
+		switch (op->type & BARRIER_MASK) {
+		case BARRIER_SYNC:
+			mb();
+			break;
+		case BARRIER_ISYNC:
+			isync();
+			break;
+		case BARRIER_EIEIO:
+			eieio();
+			break;
+#ifdef CONFIG_PPC64
+		case BARRIER_LWSYNC:
+			asm volatile("lwsync" : : : "memory");
+			break;
+		case BARRIER_PTESYNC:
+			asm volatile("ptesync" : : : "memory");
+			break;
+#endif
+		}
+		break;
+
+	case MFSPR:
+		switch (op->spr) {
+		case SPRN_XER:
+			regs->gpr[op->reg] = regs->xer & 0xffffffffUL;
+			break;
+		case SPRN_LR:
+			regs->gpr[op->reg] = regs->link;
+			break;
+		case SPRN_CTR:
+			regs->gpr[op->reg] = regs->ctr;
+			break;
+		default:
+			WARN_ON_ONCE(1);
+		}
+		break;
+
+	case MTSPR:
+		switch (op->spr) {
+		case SPRN_XER:
+			regs->xer = op->val & 0xffffffffUL;
+			break;
+		case SPRN_LR:
+			regs->link = op->val;
+			break;
+		case SPRN_CTR:
+			regs->ctr = op->val;
+			break;
+		default:
+			WARN_ON_ONCE(1);
+		}
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+	}
+	regs->nip = next_pc;
+}
+NOKPROBE_SYMBOL(emulate_update_regs);
+
+/*
+ * Emulate a previously-analysed load or store instruction.
+ * Return values are:
+ * 0 = instruction emulated successfully
+ * -EFAULT = address out of range or access faulted (regs->dar
+ *	     contains the faulting address)
+ * -EACCES = misaligned access, instruction requires alignment
+ * -EINVAL = unknown operation in *op
+ */
+int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
+{
+	int err, size, type;
+	int i, rd, nb;
+	unsigned int cr;
+	unsigned long val;
+	unsigned long ea;
+	bool cross_endian;
+
+	err = 0;
+	size = GETSIZE(op->type);
+	type = GETTYPE(op->type);
+	cross_endian = (regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE);
+	ea = truncate_if_32bit(regs->msr, op->ea);
+
+	switch (type) {
+	case LARX:
+		if (ea & (size - 1))
+			return -EACCES;		/* can't handle misaligned */
+		if (!address_ok(regs, ea, size))
+			return -EFAULT;
+		err = 0;
+		val = 0;
+		switch (size) {
+#ifdef __powerpc64__
+		case 1:
+			__get_user_asmx(val, ea, err, "lbarx");
+			break;
+		case 2:
+			__get_user_asmx(val, ea, err, "lharx");
+			break;
+#endif
+		case 4:
+			__get_user_asmx(val, ea, err, "lwarx");
+			break;
+#ifdef __powerpc64__
+		case 8:
+			__get_user_asmx(val, ea, err, "ldarx");
+			break;
+		case 16:
+			err = do_lqarx(ea, &regs->gpr[op->reg]);
+			break;
+#endif
+		default:
+			return -EINVAL;
+		}
+		if (err) {
+			regs->dar = ea;
+			break;
+		}
+		if (size < 16)
+			regs->gpr[op->reg] = val;
+		break;
+
+	case STCX:
+		if (ea & (size - 1))
+			return -EACCES;		/* can't handle misaligned */
+		if (!address_ok(regs, ea, size))
+			return -EFAULT;
+		err = 0;
+		switch (size) {
+#ifdef __powerpc64__
+		case 1:
+			__put_user_asmx(op->val, ea, err, "stbcx.", cr);
+			break;
+		case 2:
+			__put_user_asmx(op->val, ea, err, "sthcx.", cr);
+			break;
+#endif
+		case 4:
+			__put_user_asmx(op->val, ea, err, "stwcx.", cr);
+			break;
+#ifdef __powerpc64__
+		case 8:
+			__put_user_asmx(op->val, ea, err, "stdcx.", cr);
+			break;
+		case 16:
+			err = do_stqcx(ea, regs->gpr[op->reg],
+				       regs->gpr[op->reg + 1], &cr);
+			break;
+#endif
+		default:
+			return -EINVAL;
+		}
+		if (!err)
+			regs->ccr = (regs->ccr & 0x0fffffff) |
+				(cr & 0xe0000000) |
+				((regs->xer >> 3) & 0x10000000);
+		else
+			regs->dar = ea;
+		break;
+
+	case LOAD:
+#ifdef __powerpc64__
+		if (size == 16) {
+			err = emulate_lq(regs, ea, op->reg, cross_endian);
+			break;
+		}
+#endif
+		err = read_mem(&regs->gpr[op->reg], ea, size, regs);
+		if (!err) {
+			if (op->type & SIGNEXT)
+				do_signext(&regs->gpr[op->reg], size);
+			if ((op->type & BYTEREV) == (cross_endian ? 0 : BYTEREV))
+				do_byterev(&regs->gpr[op->reg], size);
+		}
+		break;
+
+#ifdef CONFIG_PPC_FPU
+	case LOAD_FP:
+		/*
+		 * If the instruction is in userspace, we can emulate it even
+		 * if the VMX state is not live, because we have the state
+		 * stored in the thread_struct.  If the instruction is in
+		 * the kernel, we must not touch the state in the thread_struct.
+		 */
+		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP))
+			return 0;
+		err = do_fp_load(op, ea, regs, cross_endian);
+		break;
+#endif
+#ifdef CONFIG_ALTIVEC
+	case LOAD_VMX:
+		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC))
+			return 0;
+		err = do_vec_load(op->reg, ea, size, regs, cross_endian);
+		break;
+#endif
+#ifdef CONFIG_VSX
+	case LOAD_VSX: {
+		unsigned long msrbit = MSR_VSX;
+
+		/*
+		 * Some VSX instructions check the MSR_VEC bit rather than MSR_VSX
+		 * when the target of the instruction is a vector register.
+		 */
+		if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC))
+			msrbit = MSR_VEC;
+		if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit))
+			return 0;
+		err = do_vsx_load(op, ea, regs, cross_endian);
+		break;
+	}
+#endif
+	case LOAD_MULTI:
+		if (!address_ok(regs, ea, size))
+			return -EFAULT;
+		rd = op->reg;
+		for (i = 0; i < size; i += 4) {
+			unsigned int v32 = 0;
+
+			nb = size - i;
+			if (nb > 4)
+				nb = 4;
+			err = copy_mem_in((u8 *) &v32, ea, nb, regs);
+			if (err)
+				break;
+			if (unlikely(cross_endian))
+				v32 = byterev_4(v32);
+			regs->gpr[rd] = v32;
+			ea += 4;
+			/* reg number wraps from 31 to 0 for lsw[ix] */
+			rd = (rd + 1) & 0x1f;
+		}
+		break;
+
+	case STORE:
+#ifdef __powerpc64__
+		if (size == 16) {
+			err = emulate_stq(regs, ea, op->reg, cross_endian);
+			break;
+		}
+#endif
+		if ((op->type & UPDATE) && size == sizeof(long) &&
+		    op->reg == 1 && op->update_reg == 1 &&
+		    !(regs->msr & MSR_PR) &&
+		    ea >= regs->gpr[1] - STACK_INT_FRAME_SIZE) {
+			err = handle_stack_update(ea, regs);
+			break;
+		}
+		if (unlikely(cross_endian))
+			do_byterev(&op->val, size);
+		err = write_mem(op->val, ea, size, regs);
+		break;
+
+#ifdef CONFIG_PPC_FPU
+	case STORE_FP:
+		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP))
+			return 0;
+		err = do_fp_store(op, ea, regs, cross_endian);
+		break;
+#endif
+#ifdef CONFIG_ALTIVEC
+	case STORE_VMX:
+		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC))
+			return 0;
+		err = do_vec_store(op->reg, ea, size, regs, cross_endian);
+		break;
+#endif
+#ifdef CONFIG_VSX
+	case STORE_VSX: {
+		unsigned long msrbit = MSR_VSX;
+
+		/*
+		 * Some VSX instructions check the MSR_VEC bit rather than MSR_VSX
+		 * when the target of the instruction is a vector register.
+		 */
+		if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC))
+			msrbit = MSR_VEC;
+		if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit))
+			return 0;
+		err = do_vsx_store(op, ea, regs, cross_endian);
+		break;
+	}
+#endif
+	case STORE_MULTI:
+		if (!address_ok(regs, ea, size))
+			return -EFAULT;
+		rd = op->reg;
+		for (i = 0; i < size; i += 4) {
+			unsigned int v32 = regs->gpr[rd];
+
+			nb = size - i;
+			if (nb > 4)
+				nb = 4;
+			if (unlikely(cross_endian))
+				v32 = byterev_4(v32);
+			err = copy_mem_out((u8 *) &v32, ea, nb, regs);
+			if (err)
+				break;
+			ea += 4;
+			/* reg number wraps from 31 to 0 for stsw[ix] */
+			rd = (rd + 1) & 0x1f;
+		}
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (err)
+		return err;
+
+	if (op->type & UPDATE)
+		regs->gpr[op->update_reg] = op->ea;
+
+	return 0;
+}
+NOKPROBE_SYMBOL(emulate_loadstore);
+
+/*
+ * Emulate instructions that cause a transfer of control,
+ * loads and stores, and a few other instructions.
+ * 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)
+{
+	struct instruction_op op;
+	int r, err, type;
+	unsigned long val;
+	unsigned long ea;
+
+	r = analyse_instr(&op, regs, instr);
+	if (r < 0)
+		return r;
+	if (r > 0) {
+		emulate_update_regs(regs, &op);
+		return 1;
+	}
+
+	err = 0;
+	type = GETTYPE(op.type);
+
+	if (OP_IS_LOAD_STORE(type)) {
+		err = emulate_loadstore(regs, &op);
+		if (err)
+			return 0;
+		goto instr_done;
+	}
+
+	switch (type) {
+	case CACHEOP:
+		ea = truncate_if_32bit(regs->msr, op.ea);
+		if (!address_ok(regs, ea, 8))
+			return 0;
+		switch (op.type & CACHEOP_MASK) {
+		case DCBST:
+			__cacheop_user_asmx(ea, err, "dcbst");
+			break;
+		case DCBF:
+			__cacheop_user_asmx(ea, err, "dcbf");
+			break;
+		case DCBTST:
+			if (op.reg == 0)
+				prefetchw((void *) ea);
+			break;
+		case DCBT:
+			if (op.reg == 0)
+				prefetch((void *) ea);
+			break;
+		case ICBI:
+			__cacheop_user_asmx(ea, err, "icbi");
+			break;
+		case DCBZ:
+			err = emulate_dcbz(ea, regs);
+			break;
+		}
+		if (err) {
+			regs->dar = ea;
+			return 0;
+		}
+		goto instr_done;
+
+	case MFMSR:
+		regs->gpr[op.reg] = regs->msr & MSR_MASK;
+		goto instr_done;
+
+	case MTMSR:
+		val = regs->gpr[op.reg];
+		if ((val & MSR_RI) == 0)
+			/* can't step mtmsr[d] that would clear MSR_RI */
+			return -1;
+		/* here op.val is the mask of bits to change */
+		regs->msr = (regs->msr & ~op.val) | (val & op.val);
+		goto instr_done;
+
+#ifdef CONFIG_PPC64
+	case SYSCALL:	/* sc */
+		/*
+		 * N.B. this uses knowledge about how the syscall
+		 * entry code works.  If that is changed, this will
+		 * need to be changed also.
+		 */
+		if (regs->gpr[0] == 0x1ebe &&
+		    cpu_has_feature(CPU_FTR_REAL_LE)) {
+			regs->msr ^= MSR_LE;
+			goto instr_done;
+		}
+		regs->gpr[9] = regs->gpr[13];
+		regs->gpr[10] = MSR_KERNEL;
+		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;
+
+	case RFI:
+		return -1;
+#endif
+	}
+	return 0;
+
+ instr_done:
+	regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
+	return 1;
+}
+NOKPROBE_SYMBOL(emulate_step);
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
new file mode 100644
index 000000000..4b41970e9
--- /dev/null
+++ b/arch/powerpc/lib/string.S
@@ -0,0 +1,69 @@
+/*
+ * 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/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/cache.h>
+
+	.text
+	
+/* This clears out any unused part of the destination buffer,
+   just as the libc version does.  -- paulus */
+_GLOBAL(strncpy)
+	PPC_LCMPI 0,r5,0
+	beqlr
+	mtctr	r5
+	addi	r6,r3,-1
+	addi	r4,r4,-1
+	.balign IFETCH_ALIGN_BYTES
+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
+	PPC_LCMPI 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
+EXPORT_SYMBOL(strncpy)
+
+_GLOBAL(strncmp)
+	PPC_LCMPI 0,r5,0
+	beq-	2f
+	mtctr	r5
+	addi	r5,r3,-1
+	addi	r4,r4,-1
+	.balign IFETCH_ALIGN_BYTES
+1:	lbzu	r3,1(r5)
+	cmpwi	1,r3,0
+	lbzu	r0,1(r4)
+	subf.	r3,r0,r3
+	beqlr	1
+	bdnzt	eq,1b
+	blr
+2:	li	r3,0
+	blr
+EXPORT_SYMBOL(strncmp)
+
+_GLOBAL(memchr)
+	PPC_LCMPI 0,r5,0
+	beq-	2f
+	mtctr	r5
+	addi	r3,r3,-1
+	.balign IFETCH_ALIGN_BYTES
+1:	lbzu	r0,1(r3)
+	cmpw	0,r0,r4
+	bdnzf	2,1b
+	beqlr
+2:	li	r3,0
+	blr
+EXPORT_SYMBOL(memchr)
diff --git a/arch/powerpc/lib/string_32.S b/arch/powerpc/lib/string_32.S
new file mode 100644
index 000000000..1ddb26394
--- /dev/null
+++ b/arch/powerpc/lib/string_32.S
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * String handling functions for PowerPC32
+ *
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/cache.h>
+
+	.text
+
+CACHELINE_BYTES = L1_CACHE_BYTES
+LG_CACHELINE_BYTES = L1_CACHE_SHIFT
+CACHELINE_MASK = (L1_CACHE_BYTES-1)
+
+_GLOBAL(__arch_clear_user)
+/*
+ * Use dcbz on the complete cache lines in the destination
+ * to set them to zero.  This requires that the destination
+ * area is cacheable.
+ */
+	cmplwi	cr0, r4, 4
+	mr	r10, r3
+	li	r3, 0
+	blt	7f
+
+11:	stw	r3, 0(r10)
+	beqlr
+	andi.	r0, r10, 3
+	add	r11, r0, r4
+	subf	r6, r0, r10
+
+	clrlwi	r7, r6, 32 - LG_CACHELINE_BYTES
+	add	r8, r7, r11
+	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	r3, 4(r6)
+	bdnz	4b
+3:	mtctr	r9
+	li	r7, 4
+10:	dcbz	r7, r6
+	addi	r6, r6, CACHELINE_BYTES
+	bdnz	10b
+	clrlwi	r11, r8, 32 - LG_CACHELINE_BYTES
+	addi	r11, r11, 4
+
+2:	srwi	r0 ,r11 ,2
+	mtctr	r0
+	bdz	6f
+1:	stwu	r3, 4(r6)
+	bdnz	1b
+6:	andi.	r11, r11, 3
+	beqlr
+	mtctr	r11
+	addi	r6, r6, 3
+8:	stbu	r3, 1(r6)
+	bdnz	8b
+	blr
+
+7:	cmpwi	cr0, r4, 0
+	beqlr
+	mtctr	r4
+	addi	r6, r10, -1
+9:	stbu	r3, 1(r6)
+	bdnz	9b
+	blr
+
+90:	mr	r3, r4
+	blr
+91:	add	r3, r10, r4
+	subf	r3, r6, r3
+	blr
+
+	EX_TABLE(11b, 90b)
+	EX_TABLE(4b, 91b)
+	EX_TABLE(10b, 91b)
+	EX_TABLE(1b, 91b)
+	EX_TABLE(8b, 91b)
+	EX_TABLE(9b, 91b)
+
+EXPORT_SYMBOL(__arch_clear_user)
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
new file mode 100644
index 000000000..ea3798f4f
--- /dev/null
+++ b/arch/powerpc/lib/string_64.S
@@ -0,0 +1,196 @@
+/*
+ * 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.
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/export.h>
+
+	.section	".toc","aw"
+PPC64_CACHES:
+	.tc		ppc64_caches[TC],ppc64_caches
+	.section	".text"
+
+/**
+ * __arch_clear_user: - Zero a block of memory in user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @n:    Number of bytes to zero.
+ *
+ * Zero a block of memory in user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+
+	.macro err1
+100:
+	EX_TABLE(100b,.Ldo_err1)
+	.endm
+
+	.macro err2
+200:
+	EX_TABLE(200b,.Ldo_err2)
+	.endm
+
+	.macro err3
+300:
+	EX_TABLE(300b,.Ldo_err3)
+	.endm
+
+.Ldo_err1:
+	mr	r3,r8
+
+.Ldo_err2:
+	mtctr	r4
+1:
+err3;	stb	r0,0(r3)
+	addi	r3,r3,1
+	addi	r4,r4,-1
+	bdnz	1b
+
+.Ldo_err3:
+	mr	r3,r4
+	blr
+
+_GLOBAL_TOC(__arch_clear_user)
+	cmpdi	r4,32
+	neg	r6,r3
+	li	r0,0
+	blt	.Lshort_clear
+	mr	r8,r3
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	/* Get the destination 8 byte aligned */
+	bf	cr7*4+3,1f
+err1;	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	sub	r4,r4,r6
+
+	cmpdi	r4,32
+	cmpdi	cr1,r4,512
+	blt	.Lshort_clear
+	bgt	cr1,.Llong_clear
+
+.Lmedium_clear:
+	srdi	r6,r4,5
+	mtctr	r6
+
+	/* Do 32 byte chunks */
+4:
+err2;	std	r0,0(r3)
+err2;	std	r0,8(r3)
+err2;	std	r0,16(r3)
+err2;	std	r0,24(r3)
+	addi	r3,r3,32
+	addi	r4,r4,-32
+	bdnz	4b
+
+.Lshort_clear:
+	/* up to 31 bytes to go */
+	cmpdi	r4,16
+	blt	6f
+err2;	std	r0,0(r3)
+err2;	std	r0,8(r3)
+	addi	r3,r3,16
+	addi	r4,r4,-16
+
+	/* Up to 15 bytes to go */
+6:	mr	r8,r3
+	clrldi	r4,r4,(64-4)
+	mtocrf	0x01,r4
+	bf	cr7*4+0,7f
+err1;	std	r0,0(r3)
+	addi	r3,r3,8
+
+7:	bf	cr7*4+1,8f
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+8:	bf	cr7*4+2,9f
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+9:	bf	cr7*4+3,10f
+err1;	stb	r0,0(r3)
+
+10:	li	r3,0
+	blr
+
+.Llong_clear:
+	ld	r5,PPC64_CACHES@toc(r2)
+
+	bf	cr7*4+0,11f
+err2;	std	r0,0(r3)
+	addi	r3,r3,8
+	addi	r4,r4,-8
+
+	/* Destination is 16 byte aligned, need to get it cache block aligned */
+11:	lwz	r7,DCACHEL1LOGBLOCKSIZE(r5)
+	lwz	r9,DCACHEL1BLOCKSIZE(r5)
+
+	/*
+	 * With worst case alignment the long clear loop takes a minimum
+	 * of 1 byte less than 2 cachelines.
+	 */
+	sldi	r10,r9,2
+	cmpd	r4,r10
+	blt	.Lmedium_clear
+
+	neg	r6,r3
+	addi	r10,r9,-1
+	and.	r5,r6,r10
+	beq	13f
+
+	srdi	r6,r5,4
+	mtctr	r6
+	mr	r8,r3
+12:
+err1;	std	r0,0(r3)
+err1;	std	r0,8(r3)
+	addi	r3,r3,16
+	bdnz	12b
+
+	sub	r4,r4,r5
+
+13:	srd	r6,r4,r7
+	mtctr	r6
+	mr	r8,r3
+14:
+err1;	dcbz	0,r3
+	add	r3,r3,r9
+	bdnz	14b
+
+	and	r4,r4,r10
+
+	cmpdi	r4,32
+	blt	.Lshort_clear
+	b	.Lmedium_clear
+EXPORT_SYMBOL(__arch_clear_user)
diff --git a/arch/powerpc/lib/strlen_32.S b/arch/powerpc/lib/strlen_32.S
new file mode 100644
index 000000000..0a8d3f64d
--- /dev/null
+++ b/arch/powerpc/lib/strlen_32.S
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * strlen() for PPC32
+ *
+ * Copyright (C) 2018 Christophe Leroy CS Systemes d'Information.
+ *
+ * Inspired from glibc implementation
+ */
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/cache.h>
+
+	.text
+
+/*
+ * Algorithm:
+ *
+ * 1) Given a word 'x', we can test to see if it contains any 0 bytes
+ *    by subtracting 0x01010101, and seeing if any of the high bits of each
+ *    byte changed from 0 to 1. This works because the least significant
+ *    0 byte must have had no incoming carry (otherwise it's not the least
+ *    significant), so it is 0x00 - 0x01 == 0xff. For all other
+ *    byte values, either they have the high bit set initially, or when
+ *    1 is subtracted you get a value in the range 0x00-0x7f, none of which
+ *    have their high bit set. The expression here is
+ *    (x - 0x01010101) & ~x & 0x80808080), which gives 0x00000000 when
+ *    there were no 0x00 bytes in the word.  You get 0x80 in bytes that
+ *    match, but possibly false 0x80 matches in the next more significant
+ *    byte to a true match due to carries.  For little-endian this is
+ *    of no consequence since the least significant match is the one
+ *    we're interested in, but big-endian needs method 2 to find which
+ *    byte matches.
+ * 2) Given a word 'x', we can test to see _which_ byte was zero by
+ *    calculating ~(((x & ~0x80808080) - 0x80808080 - 1) | x | ~0x80808080).
+ *    This produces 0x80 in each byte that was zero, and 0x00 in all
+ *    the other bytes. The '| ~0x80808080' clears the low 7 bits in each
+ *    byte, and the '| x' part ensures that bytes with the high bit set
+ *    produce 0x00. The addition will carry into the high bit of each byte
+ *    iff that byte had one of its low 7 bits set. We can then just see
+ *    which was the most significant bit set and divide by 8 to find how
+ *    many to add to the index.
+ *    This is from the book 'The PowerPC Compiler Writer's Guide',
+ *    by Steve Hoxey, Faraydon Karim, Bill Hay and Hank Warren.
+ */
+
+_GLOBAL(strlen)
+	andi.   r0, r3, 3
+	lis	r7, 0x0101
+	addi	r10, r3, -4
+	addic	r7, r7, 0x0101	/* r7 = 0x01010101 (lomagic) & clear XER[CA] */
+	rotlwi	r6, r7, 31 	/* r6 = 0x80808080 (himagic) */
+	bne-	3f
+	.balign IFETCH_ALIGN_BYTES
+1:	lwzu	r9, 4(r10)
+2:	subf	r8, r7, r9
+	and.	r8, r8, r6
+	beq+	1b
+	andc.	r8, r8, r9
+	beq+	1b
+	andc	r8, r9, r6
+	orc	r9, r9, r6
+	subfe	r8, r6, r8
+	nor	r8, r8, r9
+	cntlzw	r8, r8
+	subf	r3, r3, r10
+	srwi	r8, r8, 3
+	add	r3, r3, r8
+	blr
+
+	/* Missaligned string: make sure bytes before string are seen not 0 */
+3:	xor	r10, r10, r0
+	orc	r8, r8, r8
+	lwzu	r9, 4(r10)
+	slwi	r0, r0, 3
+	srw	r8, r8, r0
+	orc	r9, r9, r8
+	b	2b
+EXPORT_SYMBOL(strlen)
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
new file mode 100644
index 000000000..6c47daa61
--- /dev/null
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -0,0 +1,443 @@
+/*
+ * Simple sanity test for emulate_step load/store instructions.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt) "emulate_step_test: " fmt
+
+#include <linux/ptrace.h>
+#include <asm/sstep.h>
+#include <asm/ppc-opcode.h>
+
+#define IMM_L(i)		((uintptr_t)(i) & 0xffff)
+
+/*
+ * Defined with TEST_ prefix so it does not conflict with other
+ * definitions.
+ */
+#define TEST_LD(r, base, i)	(PPC_INST_LD | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZ(r, base, i)	(PPC_INST_LWZ | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZX(t, a, b)	(PPC_INST_LWZX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STD(r, base, i)	(PPC_INST_STD | ___PPC_RS(r) |		\
+					___PPC_RA(base) | ((i) & 0xfffc))
+#define TEST_LDARX(t, a, b, eh)	(PPC_INST_LDARX | ___PPC_RT(t) |	\
+					___PPC_RA(a) | ___PPC_RB(b) |	\
+					__PPC_EH(eh))
+#define TEST_STDCX(s, a, b)	(PPC_INST_STDCX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFSX(t, a, b)	(PPC_INST_LFSX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFSX(s, a, b)	(PPC_INST_STFSX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFDX(t, a, b)	(PPC_INST_LFDX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFDX(s, a, b)	(PPC_INST_STFDX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LVX(t, a, b)	(PPC_INST_LVX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STVX(s, a, b)	(PPC_INST_STVX | ___PPC_RS(s) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LXVD2X(s, a, b)	(PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
+#define TEST_STXVD2X(s, a, b)	(PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
+
+
+static void __init init_pt_regs(struct pt_regs *regs)
+{
+	static unsigned long msr;
+	static bool msr_cached;
+
+	memset(regs, 0, sizeof(struct pt_regs));
+
+	if (likely(msr_cached)) {
+		regs->msr = msr;
+		return;
+	}
+
+	asm volatile("mfmsr %0" : "=r"(regs->msr));
+
+	regs->msr |= MSR_FP;
+	regs->msr |= MSR_VEC;
+	regs->msr |= MSR_VSX;
+
+	msr = regs->msr;
+	msr_cached = true;
+}
+
+static void __init show_result(char *ins, char *result)
+{
+	pr_info("%-14s : %s\n", ins, result);
+}
+
+static void __init test_ld(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x23;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* ld r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LD(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("ld", "PASS");
+	else
+		show_result("ld", "FAIL");
+}
+
+static void __init test_lwz(void)
+{
+	struct pt_regs regs;
+	unsigned int a = 0x4545;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* lwz r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LWZ(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("lwz", "PASS");
+	else
+		show_result("lwz", "FAIL");
+}
+
+static void __init test_lwzx(void)
+{
+	struct pt_regs regs;
+	unsigned int a[3] = {0x0, 0x0, 0x1234};
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) a;
+	regs.gpr[4] = 8;
+	regs.gpr[5] = 0x8765;
+
+	/* lwzx r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LWZX(5, 3, 4));
+	if (stepped == 1 && regs.gpr[5] == a[2])
+		show_result("lwzx", "PASS");
+	else
+		show_result("lwzx", "FAIL");
+}
+
+static void __init test_std(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[5] = 0x5678;
+
+	/* std r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_STD(5, 3, 0));
+	if (stepped == 1 || regs.gpr[5] == a)
+		show_result("std", "PASS");
+	else
+		show_result("std", "FAIL");
+}
+
+static void __init test_ldarx_stdcx(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+	unsigned long cr0_eq = 0x1 << 29; /* eq bit of CR0 */
+
+	init_pt_regs(&regs);
+	asm volatile("mfcr %0" : "=r"(regs.ccr));
+
+
+	/*** ldarx ***/
+
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[4] = 0;
+	regs.gpr[5] = 0x5678;
+
+	/* ldarx r5, r3, r4, 0 */
+	stepped = emulate_step(&regs, TEST_LDARX(5, 3, 4, 0));
+
+	/*
+	 * Don't touch 'a' here. Touching 'a' can do Load/store
+	 * of 'a' which result in failure of subsequent stdcx.
+	 * Instead, use hardcoded value for comparison.
+	 */
+	if (stepped <= 0 || regs.gpr[5] != 0x1234) {
+		show_result("ldarx / stdcx.", "FAIL (ldarx)");
+		return;
+	}
+
+
+	/*** stdcx. ***/
+
+	regs.gpr[5] = 0x9ABC;
+
+	/* stdcx. r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STDCX(5, 3, 4));
+
+	/*
+	 * Two possible scenarios that indicates successful emulation
+	 * of stdcx. :
+	 *  1. Reservation is active and store is performed. In this
+	 *     case cr0.eq bit will be set to 1.
+	 *  2. Reservation is not active and store is not performed.
+	 *     In this case cr0.eq bit will be set to 0.
+	 */
+	if (stepped == 1 && ((regs.gpr[5] == a && (regs.ccr & cr0_eq))
+			|| (regs.gpr[5] != a && !(regs.ccr & cr0_eq))))
+		show_result("ldarx / stdcx.", "PASS");
+	else
+		show_result("ldarx / stdcx.", "FAIL (stdcx.)");
+}
+
+#ifdef CONFIG_PPC_FPU
+static void __init test_lfsx_stfsx(void)
+{
+	struct pt_regs regs;
+	union {
+		float a;
+		int b;
+	} c;
+	int cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfsx ***/
+
+	c.a = 123.45;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfsx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFSX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfsx", "PASS");
+	else
+		show_result("lfsx", "FAIL");
+
+
+	/*** stfsx ***/
+
+	c.a = 678.91;
+
+	/* stfsx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFSX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfsx", "PASS");
+	else
+		show_result("stfsx", "FAIL");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	struct pt_regs regs;
+	union {
+		double a;
+		long b;
+	} c;
+	long cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfdx ***/
+
+	c.a = 123456.78;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfdx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFDX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfdx", "PASS");
+	else
+		show_result("lfdx", "FAIL");
+
+
+	/*** stfdx ***/
+
+	c.a = 987654.32;
+
+	/* stfdx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFDX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfdx", "PASS");
+	else
+		show_result("stfdx", "FAIL");
+}
+#else
+static void __init test_lfsx_stfsx(void)
+{
+	show_result("lfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	show_result("lfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static void __init test_lvx_stvx(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lvx ***/
+
+	cached_b[0] = c.b[0] = 923745;
+	cached_b[1] = c.b[1] = 2139478;
+	cached_b[2] = c.b[2] = 9012;
+	cached_b[3] = c.b[3] = 982134;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lvx vrt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LVX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lvx", "PASS");
+	else
+		show_result("lvx", "FAIL");
+
+
+	/*** stvx ***/
+
+	c.b[0] = 4987513;
+	c.b[1] = 84313948;
+	c.b[2] = 71;
+	c.b[3] = 498532;
+
+	/* stvx vrs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STVX(10, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+		show_result("stvx", "PASS");
+	else
+		show_result("stvx", "FAIL");
+}
+#else
+static void __init test_lvx_stvx(void)
+{
+	show_result("lvx", "SKIP (CONFIG_ALTIVEC is not set)");
+	show_result("stvx", "SKIP (CONFIG_ALTIVEC is not set)");
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lxvd2x ***/
+
+	cached_b[0] = c.b[0] = 18233;
+	cached_b[1] = c.b[1] = 34863571;
+	cached_b[2] = c.b[2] = 834;
+	cached_b[3] = c.b[3] = 6138911;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LXVD2X(39, 3, 4));
+
+	if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) {
+		show_result("lxvd2x", "PASS");
+	} else {
+		if (!cpu_has_feature(CPU_FTR_VSX))
+			show_result("lxvd2x", "PASS (!CPU_FTR_VSX)");
+		else
+			show_result("lxvd2x", "FAIL");
+	}
+
+
+	/*** stxvd2x ***/
+
+	c.b[0] = 21379463;
+	c.b[1] = 87;
+	c.b[2] = 374234;
+	c.b[3] = 4;
+
+	/* stxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STXVD2X(39, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3] &&
+	    cpu_has_feature(CPU_FTR_VSX)) {
+		show_result("stxvd2x", "PASS");
+	} else {
+		if (!cpu_has_feature(CPU_FTR_VSX))
+			show_result("stxvd2x", "PASS (!CPU_FTR_VSX)");
+		else
+			show_result("stxvd2x", "FAIL");
+	}
+}
+#else
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	show_result("lxvd2x", "SKIP (CONFIG_VSX is not set)");
+	show_result("stxvd2x", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
+static int __init test_emulate_step(void)
+{
+	test_ld();
+	test_lwz();
+	test_lwzx();
+	test_std();
+	test_ldarx_stdcx();
+	test_lfsx_stfsx();
+	test_lfdx_stfdx();
+	test_lvx_stvx();
+	test_lxvd2x_stxvd2x();
+
+	return 0;
+}
+late_initcall(test_emulate_step);
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
new file mode 100644
index 000000000..9f340494a
--- /dev/null
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -0,0 +1,78 @@
+/*
+ * 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.
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2011
+ *
+ * Authors: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
+ *          Anton Blanchard <anton@au.ibm.com>
+ */
+#include <linux/uaccess.h>
+#include <linux/hardirq.h>
+#include <asm/switch_to.h>
+#include <asm/asm-prototypes.h>
+
+int enter_vmx_usercopy(void)
+{
+	if (in_interrupt())
+		return 0;
+
+	preempt_disable();
+	/*
+	 * We need to disable page faults as they can call schedule and
+	 * thus make us lose the VMX context. So on page faults, we just
+	 * fail which will cause a fallback to the normal non-vmx copy.
+	 */
+	pagefault_disable();
+
+	enable_kernel_altivec();
+
+	return 1;
+}
+
+/*
+ * This function must return 0 because we tail call optimise when calling
+ * from __copy_tofrom_user_power7 which returns 0 on success.
+ */
+int exit_vmx_usercopy(void)
+{
+	disable_kernel_altivec();
+	pagefault_enable();
+	preempt_enable();
+	return 0;
+}
+
+int enter_vmx_ops(void)
+{
+	if (in_interrupt())
+		return 0;
+
+	preempt_disable();
+
+	enable_kernel_altivec();
+
+	return 1;
+}
+
+/*
+ * All calls to this function will be optimised into tail calls. We are
+ * passed a pointer to the destination which we return as required by a
+ * memcpy implementation.
+ */
+void *exit_vmx_ops(void *dest)
+{
+	disable_kernel_altivec();
+	preempt_enable();
+	return dest;
+}
diff --git a/arch/powerpc/lib/xor_vmx.c b/arch/powerpc/lib/xor_vmx.c
new file mode 100644
index 000000000..4df240aa5
--- /dev/null
+++ b/arch/powerpc/lib/xor_vmx.c
@@ -0,0 +1,160 @@
+/*
+ * 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.
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+
+/*
+ * Sparse (as at v0.5.0) gets very, very confused by this file.
+ * Make it a bit simpler for it.
+ */
+#if !defined(__CHECKER__)
+#include <altivec.h>
+#else
+#define vec_xor(a, b) a ^ b
+#define vector __attribute__((vector_size(16)))
+#endif
+
+#include "xor_vmx.h"
+
+typedef vector signed char unative_t;
+
+#define DEFINE(V)				\
+	unative_t *V = (unative_t *)V##_in;	\
+	unative_t V##_0, V##_1, V##_2, V##_3
+
+#define LOAD(V)			\
+	do {			\
+		V##_0 = V[0];	\
+		V##_1 = V[1];	\
+		V##_2 = V[2];	\
+		V##_3 = V[3];	\
+	} while (0)
+
+#define STORE(V)		\
+	do {			\
+		V[0] = V##_0;	\
+		V[1] = V##_1;	\
+		V[2] = V##_2;	\
+		V[3] = V##_3;	\
+	} while (0)
+
+#define XOR(V1, V2)					\
+	do {						\
+		V1##_0 = vec_xor(V1##_0, V2##_0);	\
+		V1##_1 = vec_xor(V1##_1, V2##_1);	\
+		V1##_2 = vec_xor(V1##_2, V2##_2);	\
+		V1##_3 = vec_xor(V1##_3, V2##_3);	\
+	} while (0)
+
+void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
+		     unsigned long *v2_in)
+{
+	DEFINE(v1);
+	DEFINE(v2);
+	unsigned long lines = bytes / (sizeof(unative_t)) / 4;
+
+	do {
+		LOAD(v1);
+		LOAD(v2);
+		XOR(v1, v2);
+		STORE(v1);
+
+		v1 += 4;
+		v2 += 4;
+	} while (--lines > 0);
+}
+
+void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
+		     unsigned long *v2_in, unsigned long *v3_in)
+{
+	DEFINE(v1);
+	DEFINE(v2);
+	DEFINE(v3);
+	unsigned long lines = bytes / (sizeof(unative_t)) / 4;
+
+	do {
+		LOAD(v1);
+		LOAD(v2);
+		LOAD(v3);
+		XOR(v1, v2);
+		XOR(v1, v3);
+		STORE(v1);
+
+		v1 += 4;
+		v2 += 4;
+		v3 += 4;
+	} while (--lines > 0);
+}
+
+void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
+		     unsigned long *v2_in, unsigned long *v3_in,
+		     unsigned long *v4_in)
+{
+	DEFINE(v1);
+	DEFINE(v2);
+	DEFINE(v3);
+	DEFINE(v4);
+	unsigned long lines = bytes / (sizeof(unative_t)) / 4;
+
+	do {
+		LOAD(v1);
+		LOAD(v2);
+		LOAD(v3);
+		LOAD(v4);
+		XOR(v1, v2);
+		XOR(v3, v4);
+		XOR(v1, v3);
+		STORE(v1);
+
+		v1 += 4;
+		v2 += 4;
+		v3 += 4;
+		v4 += 4;
+	} while (--lines > 0);
+}
+
+void __xor_altivec_5(unsigned long bytes, unsigned long *v1_in,
+		     unsigned long *v2_in, unsigned long *v3_in,
+		     unsigned long *v4_in, unsigned long *v5_in)
+{
+	DEFINE(v1);
+	DEFINE(v2);
+	DEFINE(v3);
+	DEFINE(v4);
+	DEFINE(v5);
+	unsigned long lines = bytes / (sizeof(unative_t)) / 4;
+
+	do {
+		LOAD(v1);
+		LOAD(v2);
+		LOAD(v3);
+		LOAD(v4);
+		LOAD(v5);
+		XOR(v1, v2);
+		XOR(v3, v4);
+		XOR(v1, v5);
+		XOR(v1, v3);
+		STORE(v1);
+
+		v1 += 4;
+		v2 += 4;
+		v3 += 4;
+		v4 += 4;
+		v5 += 4;
+	} while (--lines > 0);
+}
diff --git a/arch/powerpc/lib/xor_vmx.h b/arch/powerpc/lib/xor_vmx.h
new file mode 100644
index 000000000..5c2b0839b
--- /dev/null
+++ b/arch/powerpc/lib/xor_vmx.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Simple interface to link xor_vmx.c and xor_vmx_glue.c
+ *
+ * Separating these file ensures that no altivec instructions are run
+ * outside of the enable/disable altivec block.
+ */
+
+void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
+			     unsigned long *v2_in);
+
+void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
+			     unsigned long *v2_in, unsigned long *v3_in);
+
+void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
+			     unsigned long *v2_in, unsigned long *v3_in,
+			     unsigned long *v4_in);
+
+void __xor_altivec_5(unsigned long bytes, unsigned long *v1_in,
+			     unsigned long *v2_in, unsigned long *v3_in,
+			     unsigned long *v4_in, unsigned long *v5_in);
diff --git a/arch/powerpc/lib/xor_vmx_glue.c b/arch/powerpc/lib/xor_vmx_glue.c
new file mode 100644
index 000000000..dab2b6bfc
--- /dev/null
+++ b/arch/powerpc/lib/xor_vmx_glue.c
@@ -0,0 +1,63 @@
+/*
+ * Altivec XOR operations
+ *
+ * Copyright 2017 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 <linux/preempt.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <asm/switch_to.h>
+#include <asm/xor_altivec.h>
+#include "xor_vmx.h"
+
+void xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
+		   unsigned long *v2_in)
+{
+	preempt_disable();
+	enable_kernel_altivec();
+	__xor_altivec_2(bytes, v1_in, v2_in);
+	disable_kernel_altivec();
+	preempt_enable();
+}
+EXPORT_SYMBOL(xor_altivec_2);
+
+void xor_altivec_3(unsigned long bytes,  unsigned long *v1_in,
+		   unsigned long *v2_in, unsigned long *v3_in)
+{
+	preempt_disable();
+	enable_kernel_altivec();
+	__xor_altivec_3(bytes, v1_in, v2_in, v3_in);
+	disable_kernel_altivec();
+	preempt_enable();
+}
+EXPORT_SYMBOL(xor_altivec_3);
+
+void xor_altivec_4(unsigned long bytes,  unsigned long *v1_in,
+		   unsigned long *v2_in, unsigned long *v3_in,
+		   unsigned long *v4_in)
+{
+	preempt_disable();
+	enable_kernel_altivec();
+	__xor_altivec_4(bytes, v1_in, v2_in, v3_in, v4_in);
+	disable_kernel_altivec();
+	preempt_enable();
+}
+EXPORT_SYMBOL(xor_altivec_4);
+
+void xor_altivec_5(unsigned long bytes,  unsigned long *v1_in,
+		   unsigned long *v2_in, unsigned long *v3_in,
+		   unsigned long *v4_in, unsigned long *v5_in)
+{
+	preempt_disable();
+	enable_kernel_altivec();
+	__xor_altivec_5(bytes, v1_in, v2_in, v3_in, v4_in, v5_in);
+	disable_kernel_altivec();
+	preempt_enable();
+}
+EXPORT_SYMBOL(xor_altivec_5);