powerpc: Emulate most Book I instructions in emulate_step()

This extends the emulate_step() function to handle a large proportion
of the Book I instructions implemented on current 64-bit server
processors.  The aim is to handle all the load and store instructions
used in the kernel, plus all of the instructions that appear between
l[wd]arx and st[wd]cx., so this handles the Altivec/VMX lvx and stvx
and the VSX lxv2dx and stxv2dx instructions (implemented in POWER7).

The new code can emulate user mode instructions, and checks the
effective address for a load or store if the saved state is for
user mode.  It doesn't handle little-endian mode at present.

For floating-point, Altivec/VMX and VSX instructions, it checks
that the saved MSR has the enable bit for the relevant facility
set, and if so, assumes that the FP/VMX/VSX registers contain
valid state, and does loads or stores directly to/from the
FP/VMX/VSX registers, using assembly helpers in ldstfp.S.

Instructions supported now include:
* Loads and stores, including some but not all VMX and VSX instructions,
  and lmw/stmw
* Atomic loads and stores (l[dw]arx, st[dw]cx.)
* Arithmetic instructions (add, subtract, multiply, divide, etc.)
* Compare instructions
* Rotate and mask instructions
* Shift instructions
* Logical instructions (and, or, xor, etc.)
* Condition register logical instructions
* mtcrf, cntlz[wd], exts[bhw]
* isync, sync, lwsync, ptesync, eieio
* Cache operations (dcbf, dcbst, dcbt, dcbtst)

The overflow-checking arithmetic instructions are not included, but
they appear not to be ever used in C code.

This uses decimal values for the minor opcodes in the switch statements
because that is what appears in the Power ISA specification, thus it is
easier to check that they are correct if they are in decimal.

If this is used to single-step an instruction where a data breakpoint
interrupt occurred, then there is the possibility that the instruction
is a lwarx or ldarx.  In that case we have to be careful not to lose the
reservation until we get to the matching st[wd]cx., or we'll never make
forward progress.  One alternative is to try to arrange that we can
return from interrupts and handle data breakpoint interrupts without
losing the reservation, which means not using any spinlocks, mutexes,
or atomic ops (including bitops).  That seems rather fragile.  The
other alternative is to emulate the larx/stcx and all the instructions
in between.  This is why this commit adds support for a wide range
of integer instructions.

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

3 files changed, 1846 insertions, 47 deletions

diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 3040dac18a37..7581dbffa18e 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -18,8 +18,8 @@ obj-$(CONFIG_HAS_IOMEM)	+= devres.o
 
 obj-$(CONFIG_PPC64)	+= copypage_64.o copyuser_64.o \
 			   memcpy_64.o usercopy_64.o mem_64.o string.o
-obj-$(CONFIG_XMON)	+= sstep.o
-obj-$(CONFIG_KPROBES)	+= sstep.o
+obj-$(CONFIG_XMON)	+= sstep.o ldstfp.o
+obj-$(CONFIG_KPROBES)	+= sstep.o ldstfp.o
 
 ifeq ($(CONFIG_PPC64),y)
 obj-$(CONFIG_SMP)	+= locks.o
diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S
new file mode 100644
index 000000000000..f6448636baf5
--- /dev/null
+++ b/arch/powerpc/lib/ldstfp.S
@@ -0,0 +1,375 @@
+/*
+ * 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 <linux/errno.h>
+
+#define STKFRM	(PPC_MIN_STKFRM + 16)
+
+	.macro	extab	instr,handler
+	.section __ex_table,"a"
+	PPC_LONG \instr,\handler
+	.previous
+	.endm
+
+	.macro	inst32	op
+reg = 0
+	.rept	32
+20:	\op	reg,0,r4
+	b	3f
+	extab	20b,99f
+reg = reg + 1
+	.endr
+	.endm
+
+/* Get the contents of frN into fr0; N is in r3. */
+_GLOBAL(get_fpr)
+	mflr	r0
+	rlwinm	r3,r3,3,0xf8
+	bcl	20,31,1f
+	blr			/* fr0 is already in fr0 */
+	nop
+reg = 1
+	.rept	31
+	fmr	fr0,reg
+	blr
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+
+/* Put the contents of fr0 into frN; N is in r3. */
+_GLOBAL(put_fpr)
+	mflr	r0
+	rlwinm	r3,r3,3,0xf8
+	bcl	20,31,1f
+	blr			/* fr0 is already in fr0 */
+	nop
+reg = 1
+	.rept	31
+	fmr	reg,fr0
+	blr
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+
+/* Load FP reg N from float at *p.  N is in r3, p in r4. */
+_GLOBAL(do_lfs)
+	PPC_STLU r1,-STKFRM(r1)
+	mflr	r0
+	PPC_STL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mfmsr	r6
+	ori	r7,r6,MSR_FP
+	cmpwi	cr7,r3,0
+	mtmsrd	r7
+	isync
+	beq	cr7,1f
+	stfd	fr0,STKFRM-16(r1)
+1:	li	r9,-EFAULT
+2:	lfs	fr0,0(r4)
+	li	r9,0
+3:	bl	put_fpr
+	beq	cr7,4f
+	lfd	fr0,STKFRM-16(r1)
+4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	mtmsrd	r6
+	isync
+	mr	r3,r9
+	addi	r1,r1,STKFRM
+	blr
+	extab	2b,3b
+
+/* Load FP reg N from double at *p.  N is in r3, p in r4. */
+_GLOBAL(do_lfd)
+	PPC_STLU r1,-STKFRM(r1)
+	mflr	r0
+	PPC_STL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mfmsr	r6
+	ori	r7,r6,MSR_FP
+	cmpwi	cr7,r3,0
+	mtmsrd	r7
+	isync
+	beq	cr7,1f
+	stfd	fr0,STKFRM-16(r1)
+1:	li	r9,-EFAULT
+2:	lfd	fr0,0(r4)
+	li	r9,0
+3:	beq	cr7,4f
+	bl	put_fpr
+	lfd	fr0,STKFRM-16(r1)
+4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	mtmsrd	r6
+	isync
+	mr	r3,r9
+	addi	r1,r1,STKFRM
+	blr
+	extab	2b,3b
+
+/* Store FP reg N to float at *p.  N is in r3, p in r4. */
+_GLOBAL(do_stfs)
+	PPC_STLU r1,-STKFRM(r1)
+	mflr	r0
+	PPC_STL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mfmsr	r6
+	ori	r7,r6,MSR_FP
+	cmpwi	cr7,r3,0
+	mtmsrd	r7
+	isync
+	beq	cr7,1f
+	stfd	fr0,STKFRM-16(r1)
+	bl	get_fpr
+1:	li	r9,-EFAULT
+2:	stfs	fr0,0(r4)
+	li	r9,0
+3:	beq	cr7,4f
+	lfd	fr0,STKFRM-16(r1)
+4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	mtmsrd	r6
+	isync
+	mr	r3,r9
+	addi	r1,r1,STKFRM
+	blr
+	extab	2b,3b
+
+/* Store FP reg N to double at *p.  N is in r3, p in r4. */
+_GLOBAL(do_stfd)
+	PPC_STLU r1,-STKFRM(r1)
+	mflr	r0
+	PPC_STL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mfmsr	r6
+	ori	r7,r6,MSR_FP
+	cmpwi	cr7,r3,0
+	mtmsrd	r7
+	isync
+	beq	cr7,1f
+	stfd	fr0,STKFRM-16(r1)
+	bl	get_fpr
+1:	li	r9,-EFAULT
+2:	stfd	fr0,0(r4)
+	li	r9,0
+3:	beq	cr7,4f
+	lfd	fr0,STKFRM-16(r1)
+4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	mtmsrd	r6
+	isync
+	mr	r3,r9
+	addi	r1,r1,STKFRM
+	blr
+	extab	2b,3b
+
+#ifdef CONFIG_ALTIVEC
+/* Get the contents of vrN into vr0; N is in r3. */
+_GLOBAL(get_vr)
+	mflr	r0
+	rlwinm	r3,r3,3,0xf8
+	bcl	20,31,1f
+	blr			/* vr0 is already in vr0 */
+	nop
+reg = 1
+	.rept	31
+	vor	vr0,reg,reg	/* assembler doesn't know vmr? */
+	blr
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+
+/* Put the contents of vr0 into vrN; N is in r3. */
+_GLOBAL(put_vr)
+	mflr	r0
+	rlwinm	r3,r3,3,0xf8
+	bcl	20,31,1f
+	blr			/* vr0 is already in vr0 */
+	nop
+reg = 1
+	.rept	31
+	vor	reg,vr0,vr0
+	blr
+reg = reg + 1
+	.endr
+1:	mflr	r5
+	add	r5,r3,r5
+	mtctr	r5
+	mtlr	r0
+	bctr
+
+/* Load vector reg N from *p.  N is in r3, p in r4. */
+_GLOBAL(do_lvx)
+	PPC_STLU r1,-STKFRM(r1)
+	mflr	r0
+	PPC_STL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mfmsr	r6
+	oris	r7,r6,MSR_VEC@h
+	cmpwi	cr7,r3,0
+	li	r8,STKFRM-16
+	mtmsrd	r7
+	isync
+	beq	cr7,1f
+	stvx	vr0,r1,r8
+1:	li	r9,-EFAULT
+2:	lvx	vr0,0,r4
+	li	r9,0
+3:	beq	cr7,4f
+	bl	put_vr
+	lvx	vr0,r1,r8
+4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	mtmsrd	r6
+	isync
+	mr	r3,r9
+	addi	r1,r1,STKFRM
+	blr
+	extab	2b,3b
+
+/* Store vector reg N to *p.  N is in r3, p in r4. */
+_GLOBAL(do_stvx)
+	PPC_STLU r1,-STKFRM(r1)
+	mflr	r0
+	PPC_STL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mfmsr	r6
+	oris	r7,r6,MSR_VEC@h
+	cmpwi	cr7,r3,0
+	li	r8,STKFRM-16
+	mtmsrd	r7
+	isync
+	beq	cr7,1f
+	stvx	vr0,r1,r8
+	bl	get_vr
+1:	li	r9,-EFAULT
+2:	stvx	vr0,0,r4
+	li	r9,0
+3:	beq	cr7,4f
+	lvx	vr0,r1,r8
+4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	mtmsrd	r6
+	isync
+	mr	r3,r9
+	addi	r1,r1,STKFRM
+	blr
+	extab	2b,3b
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+/* Get the contents of vsrN into vsr0; N is in r3. */
+_GLOBAL(get_vsr)
+	mflr	r0
+	rlwinm	r3,r3,3,0x1f8
+	bcl	20,31,1f
+	blr			/* vsr0 is already in vsr0 */
+	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 vsr0 into vsrN; N is in r3. */
+_GLOBAL(put_vsr)
+	mflr	r0
+	rlwinm	r3,r3,3,0x1f8
+	bcl	20,31,1f
+	blr			/* vr0 is already in vr0 */
+	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(do_lxvd2x)
+	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:	li	r9,-EFAULT
+2:	LXVD2X(0,0,r4)
+	li	r9,0
+3:	beq	cr7,4f
+	bl	put_vsr
+	LXVD2X(0,r1,r8)
+4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	mtmsrd	r6
+	isync
+	mr	r3,r9
+	addi	r1,r1,STKFRM
+	blr
+	extab	2b,3b
+
+/* Store VSX reg N to vector doubleword *p.  N is in r3, p in r4. */
+_GLOBAL(do_stxvd2x)
+	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)
+	bl	get_vsr
+1:	li	r9,-EFAULT
+2:	STXVD2X(0,0,r4)
+	li	r9,0
+3:	beq	cr7,4f
+	LXVD2X(0,r1,r8)
+4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	mtlr	r0
+	mtmsrd	r6
+	isync
+	mr	r3,r9
+	addi	r1,r1,STKFRM
+	blr
+	extab	2b,3b
+
+#endif /* CONFIG_VSX */
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 13b7d54f185b..e0a9858d537e 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -13,6 +13,8 @@
 #include <linux/ptrace.h>
 #include <asm/sstep.h>
 #include <asm/processor.h>
+#include <asm/uaccess.h>
+#include <asm/cputable.h>
 
 extern char system_call_common[];
 
@@ -23,6 +25,23 @@ extern char system_call_common[];
 #define MSR_MASK	0x87c0ffff
 #endif
 
+/* Bits in XER */
+#define XER_SO		0x80000000U
+#define XER_OV		0x40000000U
+#define XER_CA		0x20000000U
+
+/*
+ * Functions in ldstfp.S
+ */
+extern int do_lfs(int rn, unsigned long ea);
+extern int do_lfd(int rn, unsigned long ea);
+extern int do_stfs(int rn, unsigned long ea);
+extern int do_stfd(int rn, unsigned long ea);
+extern int do_lvx(int rn, unsigned long ea);
+extern int do_stvx(int rn, unsigned long ea);
+extern int do_lxvd2x(int rn, unsigned long ea);
+extern int do_stxvd2x(int rn, unsigned long ea);
+
 /*
  * Determine whether a conditional branch instruction would branch.
  */
@@ -46,16 +65,499 @@ static int __kprobes branch_taken(unsigned int instr, struct pt_regs *regs)
 	return 1;
 }
 
+
+static long __kprobes address_ok(struct pt_regs *regs, unsigned long ea, int nb)
+{
+	if (!user_mode(regs))
+		return 1;
+	return __access_ok(ea, nb, USER_DS);
+}
+
+/*
+ * Calculate effective address for a D-form instruction
+ */
+static unsigned long __kprobes dform_ea(unsigned int instr, 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];
+		if (instr & 0x04000000)		/* update forms */
+			regs->gpr[ra] = ea;
+	}
+#ifdef __powerpc64__
+	if (!(regs->msr & MSR_SF))
+		ea &= 0xffffffffUL;
+#endif
+	return ea;
+}
+
+#ifdef __powerpc64__
+/*
+ * Calculate effective address for a DS-form instruction
+ */
+static unsigned long __kprobes dsform_ea(unsigned int instr, 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];
+		if ((instr & 3) == 1)		/* update forms */
+			regs->gpr[ra] = ea;
+	}
+	if (!(regs->msr & MSR_SF))
+		ea &= 0xffffffffUL;
+	return ea;
+}
+#endif /* __powerpc64 */
+
+/*
+ * Calculate effective address for an X-form instruction
+ */
+static unsigned long __kprobes xform_ea(unsigned int instr, struct pt_regs *regs,
+				     int do_update)
+{
+	int ra, rb;
+	unsigned long ea;
+
+	ra = (instr >> 16) & 0x1f;
+	rb = (instr >> 11) & 0x1f;
+	ea = regs->gpr[rb];
+	if (ra) {
+		ea += regs->gpr[ra];
+		if (do_update)		/* update forms */
+			regs->gpr[ra] = ea;
+	}
+#ifdef __powerpc64__
+	if (!(regs->msr & MSR_SF))
+		ea &= 0xffffffffUL;
+#endif
+	return ea;
+}
+
+/*
+ * Return the largest power of 2, not greater than sizeof(unsigned long),
+ * such that x is a multiple of it.
+ */
+static inline unsigned long max_align(unsigned long x)
+{
+	x |= sizeof(unsigned long);
+	return x & -x;		/* isolates rightmost bit */
+}
+
+
+static inline unsigned long byterev_2(unsigned long x)
+{
+	return ((x >> 8) & 0xff) | ((x & 0xff) << 8);
+}
+
+static inline unsigned long byterev_4(unsigned long x)
+{
+	return ((x >> 24) & 0xff) | ((x >> 8) & 0xff00) |
+		((x & 0xff00) << 8) | ((x & 0xff) << 24);
+}
+
+#ifdef __powerpc64__
+static inline unsigned long byterev_8(unsigned long x)
+{
+	return (byterev_4(x) << 32) | byterev_4(x >> 32);
+}
+#endif
+
+static int __kprobes read_mem_aligned(unsigned long *dest, unsigned long ea,
+				      int nb)
+{
+	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;
+	return err;
+}
+
+static int __kprobes read_mem_unaligned(unsigned long *dest, unsigned long ea,
+					int nb, struct pt_regs *regs)
+{
+	int err;
+	unsigned long x, b, c;
+
+	/* unaligned, do this in pieces */
+	x = 0;
+	for (; nb > 0; nb -= c) {
+		c = max_align(ea);
+		if (c > nb)
+			c = max_align(nb);
+		err = read_mem_aligned(&b, ea, c);
+		if (err)
+			return err;
+		x = (x << (8 * c)) + b;
+		ea += c;
+	}
+	*dest = x;
+	return 0;
+}
+
+/*
+ * Read memory at address ea for nb bytes, return 0 for success
+ * or -EFAULT if an error occurred.
+ */
+static int __kprobes 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);
+	return read_mem_unaligned(dest, ea, nb, regs);
+}
+
+static int __kprobes write_mem_aligned(unsigned long val, unsigned long ea,
+				       int nb)
+{
+	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
+	}
+	return err;
+}
+
+static int __kprobes write_mem_unaligned(unsigned long val, unsigned long ea,
+					 int nb, struct pt_regs *regs)
+{
+	int err;
+	unsigned long c;
+
+	/* unaligned or little-endian, do this in pieces */
+	for (; nb > 0; nb -= c) {
+		c = max_align(ea);
+		if (c > nb)
+			c = max_align(nb);
+		err = write_mem_aligned(val >> (nb - c) * 8, ea, c);
+		if (err)
+			return err;
+		++ea;
+	}
+	return 0;
+}
+
+/*
+ * Write memory at address ea for nb bytes, return 0 for success
+ * or -EFAULT if an error occurred.
+ */
+static int __kprobes 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);
+	return write_mem_unaligned(val, ea, nb, regs);
+}
+
 /*
- * Emulate instructions that cause a transfer of control.
+ * Check the address and alignment, and call func to do the actual
+ * load or store.
+ */
+static int __kprobes do_fp_load(int rn, int (*func)(int, unsigned long),
+				unsigned long ea, int nb,
+				struct pt_regs *regs)
+{
+	int err;
+	unsigned long val[sizeof(double) / sizeof(long)];
+	unsigned long ptr;
+
+	if (!address_ok(regs, ea, nb))
+		return -EFAULT;
+	if ((ea & 3) == 0)
+		return (*func)(rn, ea);
+	ptr = (unsigned long) &val[0];
+	if (sizeof(unsigned long) == 8 || nb == 4) {
+		err = read_mem_unaligned(&val[0], ea, nb, regs);
+		ptr += sizeof(unsigned long) - nb;
+	} else {
+		/* reading a double on 32-bit */
+		err = read_mem_unaligned(&val[0], ea, 4, regs);
+		if (!err)
+			err = read_mem_unaligned(&val[1], ea + 4, 4, regs);
+	}
+	if (err)
+		return err;
+	return (*func)(rn, ptr);
+}
+
+static int __kprobes do_fp_store(int rn, int (*func)(int, unsigned long),
+				 unsigned long ea, int nb,
+				 struct pt_regs *regs)
+{
+	int err;
+	unsigned long val[sizeof(double) / sizeof(long)];
+	unsigned long ptr;
+
+	if (!address_ok(regs, ea, nb))
+		return -EFAULT;
+	if ((ea & 3) == 0)
+		return (*func)(rn, ea);
+	ptr = (unsigned long) &val[0];
+	if (sizeof(unsigned long) == 8 || nb == 4) {
+		ptr += sizeof(unsigned long) - nb;
+		err = (*func)(rn, ptr);
+		if (err)
+			return err;
+		err = write_mem_unaligned(val[0], ea, nb, regs);
+	} else {
+		/* writing a double on 32-bit */
+		err = (*func)(rn, ptr);
+		if (err)
+			return err;
+		err = write_mem_unaligned(val[0], ea, 4, regs);
+		if (!err)
+			err = write_mem_unaligned(val[1], ea + 4, 4, regs);
+	}
+	return err;
+}
+
+#ifdef CONFIG_ALTIVEC
+/* For Altivec/VMX, no need to worry about alignment */
+static int __kprobes do_vec_load(int rn, int (*func)(int, unsigned long),
+				 unsigned long ea, struct pt_regs *regs)
+{
+	if (!address_ok(regs, ea & ~0xfUL, 16))
+		return -EFAULT;
+	return (*func)(rn, ea);
+}
+
+static int __kprobes do_vec_store(int rn, int (*func)(int, unsigned long),
+				  unsigned long ea, struct pt_regs *regs)
+{
+	if (!address_ok(regs, ea & ~0xfUL, 16))
+		return -EFAULT;
+	return (*func)(rn, ea);
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static int __kprobes do_vsx_load(int rn, int (*func)(int, unsigned long),
+				 unsigned long ea, struct pt_regs *regs)
+{
+	int err;
+	unsigned long val[2];
+
+	if (!address_ok(regs, ea, 16))
+		return -EFAULT;
+	if ((ea & 3) == 0)
+		return (*func)(rn, ea);
+	err = read_mem_unaligned(&val[0], ea, 8, regs);
+	if (!err)
+		err = read_mem_unaligned(&val[1], ea + 8, 8, regs);
+	if (!err)
+		err = (*func)(rn, (unsigned long) &val[0]);
+	return err;
+}
+
+static int __kprobes do_vsx_store(int rn, int (*func)(int, unsigned long),
+				 unsigned long ea, struct pt_regs *regs)
+{
+	int err;
+	unsigned long val[2];
+
+	if (!address_ok(regs, ea, 16))
+		return -EFAULT;
+	if ((ea & 3) == 0)
+		return (*func)(rn, ea);
+	err = (*func)(rn, (unsigned long) &val[0]);
+	if (err)
+		return err;
+	err = write_mem_unaligned(val[0], ea, 8, regs);
+	if (!err)
+		err = write_mem_unaligned(val[1], ea + 8, 8, regs);
+	return err;
+}
+#endif /* CONFIG_VSX */
+
+#define __put_user_asmx(x, addr, err, op, cr)		\
+	__asm__ __volatile__(				\
+		"1:	" op " %2,0,%3\n"		\
+		"	mfcr	%1\n"			\
+		"2:\n"					\
+		".section .fixup,\"ax\"\n"		\
+		"3:	li	%0,%4\n"		\
+		"	b	2b\n"			\
+		".previous\n"				\
+		".section __ex_table,\"a\"\n"		\
+			PPC_LONG_ALIGN "\n"		\
+			PPC_LONG "1b,3b\n"		\
+		".previous"				\
+		: "=r" (err), "=r" (cr)			\
+		: "r" (x), "r" (addr), "i" (-EFAULT), "0" (err))
+
+#define __get_user_asmx(x, addr, err, op)		\
+	__asm__ __volatile__(				\
+		"1:	"op" %1,0,%2\n"			\
+		"2:\n"					\
+		".section .fixup,\"ax\"\n"		\
+		"3:	li	%0,%3\n"		\
+		"	b	2b\n"			\
+		".previous\n"				\
+		".section __ex_table,\"a\"\n"		\
+			PPC_LONG_ALIGN "\n"		\
+			PPC_LONG "1b,3b\n"		\
+		".previous"				\
+		: "=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"				\
+		".section __ex_table,\"a\"\n"		\
+			PPC_LONG_ALIGN "\n"		\
+			PPC_LONG "1b,3b\n"		\
+		".previous"				\
+		: "=r" (err)				\
+		: "r" (addr), "i" (-EFAULT), "0" (err))
+
+static void __kprobes set_cr0(struct pt_regs *regs, int rd)
+{
+	long val = regs->gpr[rd];
+
+	regs->ccr = (regs->ccr & 0x0fffffff) | ((regs->xer >> 3) & 0x10000000);
+#ifdef __powerpc64__
+	if (!(regs->msr & MSR_SF))
+		val = (int) val;
+#endif
+	if (val < 0)
+		regs->ccr |= 0x80000000;
+	else if (val > 0)
+		regs->ccr |= 0x40000000;
+	else
+		regs->ccr |= 0x20000000;
+}
+
+static void __kprobes add_with_carry(struct pt_regs *regs, int rd,
+				     unsigned long val1, unsigned long val2,
+				     unsigned long carry_in)
+{
+	unsigned long val = val1 + val2;
+
+	if (carry_in)
+		++val;
+	regs->gpr[rd] = val;
+#ifdef __powerpc64__
+	if (!(regs->msr & MSR_SF)) {
+		val = (unsigned int) val;
+		val1 = (unsigned int) val1;
+	}
+#endif
+	if (val < val1 || (carry_in && val == val1))
+		regs->xer |= XER_CA;
+	else
+		regs->xer &= ~XER_CA;
+}
+
+static void __kprobes do_cmp_signed(struct pt_regs *regs, long v1, long v2,
+				    int crfld)
+{
+	unsigned int crval, shift;
+
+	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;
+	regs->ccr = (regs->ccr & ~(0xf << shift)) | (crval << shift);
+}
+
+static void __kprobes do_cmp_unsigned(struct pt_regs *regs, unsigned long v1,
+				      unsigned long v2, int crfld)
+{
+	unsigned int crval, shift;
+
+	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;
+	regs->ccr = (regs->ccr & ~(0xf << shift)) | (crval << shift);
+}
+
+/*
+ * 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))
+
+/*
+ * 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 __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 {
-	unsigned int opcode, rs, rb, rd, spr;
+	unsigned int opcode, ra, rb, rd, spr, u;
 	unsigned long int imm;
+	unsigned long int val, val2;
+	unsigned long int ea;
+	unsigned int cr, mb, me, sh;
+	int err;
+	unsigned long old_ra;
+	long ival;
 
 	opcode = instr >> 26;
 	switch (opcode) {
@@ -78,7 +580,13 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		 * 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();
@@ -102,9 +610,9 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		regs->nip = imm;
 		return 1;
 	case 19:
-		switch (instr & 0x7fe) {
-		case 0x20:	/* bclr */
-		case 0x420:	/* bcctr */
+		switch ((instr >> 1) & 0x3ff) {
+		case 16:	/* bclr */
+		case 528:	/* bcctr */
 			imm = (instr & 0x400)? regs->ctr: regs->link;
 			regs->nip += 4;
 			if ((regs->msr & MSR_SF) == 0) {
@@ -116,30 +624,233 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			if (branch_taken(instr, regs))
 				regs->nip = imm;
 			return 1;
-		case 0x24:	/* rfid, scary */
+
+		case 18:	/* rfid, scary */
 			return -1;
+
+		case 150:	/* isync */
+			isync();
+			goto instr_done;
+
+		case 33:	/* crnor */
+		case 129:	/* crandc */
+		case 193:	/* crxor */
+		case 225:	/* crnand */
+		case 257:	/* crand */
+		case 289:	/* creqv */
+		case 417:	/* crorc */
+		case 449:	/* cror */
+			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;
+			regs->ccr = (regs->ccr & ~(1UL << (31 - rd))) |
+				(val << (31 - rd));
+			goto instr_done;
+		}
+		break;
+	case 31:
+		switch ((instr >> 1) & 0x3ff) {
+		case 598:	/* sync */
+#ifdef __powerpc64__
+			switch ((instr >> 21) & 3) {
+			case 1:		/* lwsync */
+				asm volatile("lwsync" : : : "memory");
+				goto instr_done;
+			case 2:		/* ptesync */
+				asm volatile("ptesync" : : : "memory");
+				goto instr_done;
+			}
+#endif
+			mb();
+			goto instr_done;
+
+		case 854:	/* eieio */
+			eieio();
+			goto instr_done;
+		}
+		break;
+	}
+
+	/* Following cases refer to regs->gpr[], so we need all regs */
+	if (!FULL_REGS(regs))
+		return 0;
+
+	rd = (instr >> 21) & 0x1f;
+	ra = (instr >> 16) & 0x1f;
+	rb = (instr >> 11) & 0x1f;
+
+	switch (opcode) {
+	case 7:		/* mulli */
+		regs->gpr[rd] = regs->gpr[ra] * (short) instr;
+		goto instr_done;
+
+	case 8:		/* subfic */
+		imm = (short) instr;
+		add_with_carry(regs, rd, ~regs->gpr[ra], imm, 1);
+		goto instr_done;
+
+	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, val, imm, rd >> 2);
+		goto instr_done;
+
+	case 11:	/* cmpi */
+		imm = (short) instr;
+		val = regs->gpr[ra];
+#ifdef __powerpc64__
+		if ((rd & 1) == 0)
+			val = (int) val;
+#endif
+		do_cmp_signed(regs, val, imm, rd >> 2);
+		goto instr_done;
+
+	case 12:	/* addic */
+		imm = (short) instr;
+		add_with_carry(regs, rd, regs->gpr[ra], imm, 0);
+		goto instr_done;
+
+	case 13:	/* addic. */
+		imm = (short) instr;
+		add_with_carry(regs, rd, regs->gpr[ra], imm, 0);
+		set_cr0(regs, rd);
+		goto instr_done;
+
+	case 14:	/* addi */
+		imm = (short) instr;
+		if (ra)
+			imm += regs->gpr[ra];
+		regs->gpr[rd] = imm;
+		goto instr_done;
+
+	case 15:	/* addis */
+		imm = ((short) instr) << 16;
+		if (ra)
+			imm += regs->gpr[ra];
+		regs->gpr[rd] = imm;
+		goto instr_done;
+
+	case 20:	/* rlwimi */
+		mb = (instr >> 6) & 0x1f;
+		me = (instr >> 1) & 0x1f;
+		val = DATA32(regs->gpr[rd]);
+		imm = MASK32(mb, me);
+		regs->gpr[ra] = (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]);
+		regs->gpr[ra] = 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]);
+		regs->gpr[ra] = ROTATE(val, rb) & MASK32(mb, me);
+		goto logical_done;
+
+	case 24:	/* ori */
+		imm = (unsigned short) instr;
+		regs->gpr[ra] = regs->gpr[rd] | imm;
+		goto instr_done;
+
+	case 25:	/* oris */
+		imm = (unsigned short) instr;
+		regs->gpr[ra] = regs->gpr[rd] | (imm << 16);
+		goto instr_done;
+
+	case 26:	/* xori */
+		imm = (unsigned short) instr;
+		regs->gpr[ra] = regs->gpr[rd] ^ imm;
+		goto instr_done;
+
+	case 27:	/* xoris */
+		imm = (unsigned short) instr;
+		regs->gpr[ra] = regs->gpr[rd] ^ (imm << 16);
+		goto instr_done;
+
+	case 28:	/* andi. */
+		imm = (unsigned short) instr;
+		regs->gpr[ra] = regs->gpr[rd] & imm;
+		set_cr0(regs, ra);
+		goto instr_done;
+
+	case 29:	/* andis. */
+		imm = (unsigned short) instr;
+		regs->gpr[ra] = regs->gpr[rd] & (imm << 16);
+		set_cr0(regs, ra);
+		goto instr_done;
+
+#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 */
+				regs->gpr[ra] = val & MASK64_L(mb);
+				goto logical_done;
+			case 1:		/* rldicr */
+				regs->gpr[ra] = val & MASK64_R(mb);
+				goto logical_done;
+			case 2:		/* rldic */
+				regs->gpr[ra] = val & MASK64(mb, 63 - sh);
+				goto logical_done;
+			case 3:		/* rldimi */
+				imm = MASK64(mb, 63 - sh);
+				regs->gpr[ra] = (regs->gpr[ra] & ~imm) |
+					(val & imm);
+				goto logical_done;
+			}
+		} else {
+			sh = regs->gpr[rb] & 0x3f;
+			val = ROTATE(val, sh);
+			switch ((instr >> 1) & 7) {
+			case 0:		/* rldcl */
+				regs->gpr[ra] = val & MASK64_L(mb);
+				goto logical_done;
+			case 1:		/* rldcr */
+				regs->gpr[ra] = val & MASK64_R(mb);
+				goto logical_done;
+			}
 		}
+#endif
+
 	case 31:
-		rd = (instr >> 21) & 0x1f;
-		switch (instr & 0x7fe) {
-		case 0xa6:	/* mfmsr */
+		switch ((instr >> 1) & 0x3ff) {
+		case 83:	/* mfmsr */
+			if (regs->msr & MSR_PR)
+				break;
 			regs->gpr[rd] = regs->msr & MSR_MASK;
-			regs->nip += 4;
-			if ((regs->msr & MSR_SF) == 0)
-				regs->nip &= 0xffffffffUL;
-			return 1;
-		case 0x124:	/* mtmsr */
+			goto instr_done;
+		case 146:	/* mtmsr */
+			if (regs->msr & MSR_PR)
+				break;
 			imm = regs->gpr[rd];
 			if ((imm & MSR_RI) == 0)
 				/* can't step mtmsr that would clear MSR_RI */
 				return -1;
 			regs->msr = imm;
-			regs->nip += 4;
-			return 1;
+			goto instr_done;
 #ifdef CONFIG_PPC64
-		case 0x164:	/* mtmsrd */
+		case 178:	/* mtmsrd */
 			/* only MSR_EE and MSR_RI get changed if bit 15 set */
 			/* mtmsrd doesn't change MSR_HV and MSR_ME */
+			if (regs->msr & MSR_PR)
+				break;
 			imm = (instr & 0x10000)? 0x8002: 0xefffffffffffefffUL;
 			imm = (regs->msr & MSR_MASK & ~imm)
 				| (regs->gpr[rd] & imm);
@@ -147,5