[Patch 2/5] x86_emulator: add Src2 decode set

[Patch 2/5] x86_emulator: add Src2 decode set

[Guillaume Thouvenin]

Instruction like shld has three operands, so we need to add a Src2
decode set. We start with Src2None, Src2CL, and Src2ImmByte, Src2One
to support shld/shrd and we will expand it later.

Signed-off-by: Guillaume Thouvenin <guillaume.thouvenin@ext.bull.net>
---
 arch/x86/include/asm/kvm_x86_emulate.h |    1 +
 arch/x86/kvm/x86_emulate.c             |   29 +++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/kvm_x86_emulate.h b/arch/x86/include/asm/kvm_x86_emulate.h
index 16a0026..6a15973 100644
--- a/arch/x86/include/asm/kvm_x86_emulate.h
+++ b/arch/x86/include/asm/kvm_x86_emulate.h
@@ -123,6 +123,7 @@ struct decode_cache {
 	u8 ad_bytes;
 	u8 rex_prefix;
 	struct operand src;
+	struct operand src2;
 	struct operand dst;
 	bool has_seg_override;
 	u8 seg_override;
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index f0c7620..4e8ef29 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -70,6 +70,12 @@
 #define Group       (1<<14)     /* Bits 3:5 of modrm byte extend opcode */
 #define GroupDual   (1<<15)     /* Alternate decoding of mod == 3 */
 #define GroupMask   0xff        /* Group number stored in bits 0:7 */
+/* Source 2 operand type */
+#define Src2None    (0<<29)
+#define Src2CL      (1<<29)
+#define Src2ImmByte (2<<29)
+#define Src2One     (3<<29)
+#define Src2Mask    (7<<29)
 
 enum {
 	Group1_80, Group1_81, Group1_82, Group1_83,
@@ -1043,6 +1049,29 @@ done_prefixes:
 		break;
 	}
 
+	/*
+	 * Decode and fetch the second source operand: register, memory
+	 * or immediate.
+	 */
+	switch (c->d & Src2Mask) {
+	case Src2None:
+		break;
+	case Src2CL:
+		c->src2.bytes = 1;
+		c->src2.val = c->regs[VCPU_REGS_RCX] & 0x8;
+		break;
+	case Src2ImmByte:
+		c->src2.type = OP_IMM;
+		c->src2.ptr = (unsigned long *)c->eip;
+		c->src2.bytes = 1;
+		c->src2.val = insn_fetch(u8, 1, c->eip);
+		break;
+	case Src2One:
+		c->src2.bytes = 1;
+		c->src2.val = 1;
+		break;
+	}
+
 	/* Decode and fetch the destination operand: register or memory. */
 	switch (c->d & DstMask) {
 	case ImplicitOps:
-- 
1.6.0.3.514.g2f91b

[Patch 0/5] x86_emulator: emulate shld and shrd instructions

[Guillaume Thouvenin]

This series of patches emulate instructions shld and shrd. As those
instructions have three operands we introduce a decode set for the Src2
operand. By doing this, the opcode descriptor needs to be extend to 32
bit.

So this series of patches:
 [1/5] extend the opcode descriptor to 32 bits
 [2/5] add Src2 decode set
 [3/5] add a new "implied 1" Src decode type
 [4/5] add the assembler code for three operands (one operand is stored
in EXC) 
 [5/5] add the emulation of shld and shrd instructions

[Patch 1/5] x86_emulator: Extend the opcode descriptor

[Guillaume Thouvenin]

Extend the opcode descriptor to 32 bits. This is needed by the
introduction of a new Src2 operand type.

Signed-off-by: Guillaume Thouvenin <guillaume.thouvenin@ext.bull.net>
---
 arch/x86/kvm/x86_emulate.c |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index 69b330b..7a07ca4 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -76,7 +76,7 @@ enum {
 	Group1A, Group3_Byte, Group3, Group4, Group5, Group7,
 };
 
-static u16 opcode_table[256] = {
+static u32 opcode_table[256] = {
 	/* 0x00 - 0x07 */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
@@ -195,7 +195,7 @@ static u16 opcode_table[256] = {
 	ImplicitOps, ImplicitOps, Group | Group4, Group | Group5,
 };
 
-static u16 twobyte_table[256] = {
+static u32 twobyte_table[256] = {
 	/* 0x00 - 0x0F */
 	0, Group | GroupDual | Group7, 0, 0, 0, 0, ImplicitOps, 0,
 	ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
@@ -253,7 +253,7 @@ static u16 twobyte_table[256] = {
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
 };
 
-static u16 group_table[] = {
+static u32 group_table[] = {
 	[Group1_80*8] =
 	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
 	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
@@ -297,7 +297,7 @@ static u16 group_table[] = {
 	SrcMem16 | ModRM | Mov, SrcMem | ModRM | ByteOp,
 };
 
-static u16 group2_table[] = {
+static u32 group2_table[] = {
 	[Group7*8] =
 	SrcNone | ModRM, 0, 0, 0,
 	SrcNone | ModRM | DstMem | Mov, 0,
-- 
1.6.0.4.623.g171d7

[Patch 2/5] x86_emulator: add Src2 decode set

[Guillaume Thouvenin]

Instruction like shld has three operands, so we need to add a Src2
decode set. We start with Src2None, Src2CL, and Src2ImmByte, Src2One to
support shld/shrd and we will expand it later.

Signed-off-by: Guillaume Thouvenin <guillaume.thouvenin@ext.bull.net>
---
 arch/x86/include/asm/kvm_x86_emulate.h |    1 +
 arch/x86/kvm/x86_emulate.c             |   29 +++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 0 deletions(-)

diff --git a/arch/x86/include/asm/kvm_x86_emulate.h b/arch/x86/include/asm/kvm_x86_emulate.h
index 16a0026..6a15973 100644
--- a/arch/x86/include/asm/kvm_x86_emulate.h
+++ b/arch/x86/include/asm/kvm_x86_emulate.h
@@ -123,6 +123,7 @@ struct decode_cache {
 	u8 ad_bytes;
 	u8 rex_prefix;
 	struct operand src;
+	struct operand src2;
 	struct operand dst;
 	bool has_seg_override;
 	u8 seg_override;
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index 7a07ca4..7f5cd62 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -70,6 +70,12 @@
 #define Group       (1<<14)     /* Bits 3:5 of modrm byte extend opcode */
 #define GroupDual   (1<<15)     /* Alternate decoding of mod == 3 */
 #define GroupMask   0xff        /* Group number stored in bits 0:7 */
+/* Source 2 operand type */
+#define Src2None    (0<<29)
+#define Src2CL      (1<<29)
+#define Src2ImmByte (2<<29)
+#define Src2One     (3<<29)
+#define Src2Mask    (7<<29)
 
 enum {
 	Group1_80, Group1_81, Group1_82, Group1_83,
@@ -1000,6 +1006,29 @@ done_prefixes:
 		break;
 	}
 
+	/*
+	 * Decode and fetch the second source operand: register, memory
+	 * or immediate.
+	 */
+	switch (c->d & Src2Mask) {
+	case Src2None:
+		break;
+	case Src2CL:
+		c->src2.bytes = 1;
+		c->src2.val = c->regs[VCPU_REGS_RCX] & 0x8;
+		break;
+	case Src2ImmByte:
+		c->src2.type = OP_IMM;
+		c->src2.ptr = (unsigned long *)c->eip;
+		c->src2.bytes = 1;
+		c->src2.val = insn_fetch(u8, 1, c->eip);
+		break;
+	case Src2One:
+		c->src2.bytes = 1;
+		c->src2.val = 1;
+		break;
+	}
+
 	/* Decode and fetch the destination operand: register or memory. */
 	switch (c->d & DstMask) {
 	case ImplicitOps:
-- 
1.6.0.4.623.g171d7

[Patch 3/5] x86_emulator: add a new "implied 1" Src decode type

[Guillaume Thouvenin]

Add SrcOne operand type when we need to decode an implied '1' like with
regular shift instruction

Signed-off-by: Guillaume Thouvenin <guillaume.thouvenin@ext.bull.net>
---
 arch/x86/kvm/x86_emulate.c |    5 +++++
 1 files changed, 5 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index 7f5cd62..0c75306 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -58,6 +58,7 @@
 #define SrcMem32    (4<<4)	/* Memory operand (32-bit). */
 #define SrcImm      (5<<4)	/* Immediate operand. */
 #define SrcImmByte  (6<<4)	/* 8-bit sign-extended immediate operand. */
+#define SrcOne      (7<<4)	/* Implied '1' */
 #define SrcMask     (7<<4)
 /* Generic ModRM decode. */
 #define ModRM       (1<<7)
@@ -1004,6 +1005,10 @@ done_prefixes:
 		c->src.bytes = 1;
 		c->src.val = insn_fetch(s8, 1, c->eip);
 		break;
+	case SrcOne:
+		c->src.bytes = 1;
+		c->src.val = 1;
+		break;
 	}
 
 	/*
-- 
1.6.0.4.623.g171d7

[Patch 4/5] x86_emulator: add the assembler code for three operands

[Guillaume Thouvenin]

Add the assembler code for instruction with three operands and one
operand is stored in ECX register

Signed-off-by: Guillaume Thouvenin <guillaume.thouvenin@ext.bull.net>
---
 arch/x86/kvm/x86_emulate.c |   39 +++++++++++++++++++++++++++++++++++++++
 1 files changed, 39 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index 0c75306..9ae6d5b 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -431,6 +431,45 @@ static u32 group2_table[] = {
 	__emulate_2op_nobyte(_op, _src, _dst, _eflags,			\
 			     "w", "r", _LO32, "r", "", "r")
 
+/* Instruction has three operands and one operand is stored in ECX register */
+#define __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, _suffix, _type) 	\
+	do {									\
+		unsigned long _tmp;						\
+		_type _clv  = (_cl).val;  					\
+		_type _srcv = (_src).val;    					\
+		_type _dstv = (_dst).val;					\
+										\
+		__asm__ __volatile__ (						\
+			_PRE_EFLAGS("0", "5", "2")				\
+			_op _suffix " %4,%1 \n"					\
+			_POST_EFLAGS("0", "5", "2")				\
+			: "=m" (_eflags), "+r" (_dstv), "=&r" (_tmp)		\
+			: "c" (_clv) , "r" (_srcv), "i" (EFLAGS_MASK)		\
+			); 							\
+										\
+		(_cl).val  = (unsigned long) _clv;				\
+		(_src).val = (unsigned long) _srcv;				\
+		(_dst).val = (unsigned long) _dstv;				\
+	} while (0)
+
+#define emulate_2op_cl(_op, _cl, _src, _dst, _eflags)				\
+	do {									\
+		switch ((_dst).bytes) {						\
+		case 2:								\
+			__emulate_2op_cl(_op, _cl, _src, _dst, _eflags,  	\
+						"w", unsigned short);         	\
+			break;							\
+		case 4: 							\
+			__emulate_2op_cl(_op, _cl, _src, _dst, _eflags,  	\
+						"l", unsigned int);           	\
+			break;							\
+		case 8:								\
+			ON64(__emulate_2op_cl(_op, _cl, _src, _dst, _eflags,	\
+						"q", unsigned long));  		\
+			break;							\
+		}								\
+	} while (0)
+
 #define __emulate_1op(_op, _dst, _eflags, _suffix)			\
 	do {								\
 		unsigned long _tmp;					\
-- 
1.6.0.4.623.g171d7

[Patch 5/5] x86_emulator: add the emulation of shld and shrd instructions

[Guillaume Thouvenin]

Add emulation of shld and shrd instructions

Signed-off-by: Guillaume Thouvenin <guillaume.thouvenin@ext.bull.net>
---
 arch/x86/kvm/x86_emulate.c |   17 +++++++++++++++--
 1 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index 9ae6d5b..219dc31 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -237,9 +237,14 @@ static u32 twobyte_table[256] = {
 	/* 0x90 - 0x9F */
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xA0 - 0xA7 */
-	0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, 0, 0,
+	0, 0, 0, DstMem | SrcReg | ModRM | BitOp,
+	DstMem | SrcReg | Src2ImmByte | ModRM,
+	DstMem | SrcReg | Src2CL | ModRM, 0, 0,
 	/* 0xA8 - 0xAF */
-	0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, ModRM, 0,
+	0, 0, 0, DstMem | SrcReg | ModRM | BitOp,
+	DstMem | SrcReg | Src2ImmByte | ModRM,
+	DstMem | SrcReg | Src2CL | ModRM,
+	ModRM, 0,
 	/* 0xB0 - 0xB7 */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, 0,
 	    DstMem | SrcReg | ModRM | BitOp,
@@ -2037,12 +2042,20 @@ twobyte_insn:
 		c->src.val &= (c->dst.bytes << 3) - 1;
 		emulate_2op_SrcV_nobyte("bt", c->src, c->dst, ctxt->eflags);
 		break;
+	case 0xa4: /* shld imm8, r, r/m */
+	case 0xa5: /* shld cl, r, r/m */
+		emulate_2op_cl("shld", c->src2, c->src, c->dst, ctxt->eflags);
+		break;
 	case 0xab:
 	      bts:		/* bts */
 		/* only subword offset */
 		c->src.val &= (c->dst.bytes << 3) - 1;
 		emulate_2op_SrcV_nobyte("bts", c->src, c->dst, ctxt->eflags);
 		break;
+	case 0xac: /* shrd imm8, r, r/m */
+	case 0xad: /* shrd cl, r, r/m */
+		emulate_2op_cl("shrd", c->src2, c->src, c->dst, ctxt->eflags);
+		break;
 	case 0xae:              /* clflush */
 		break;
 	case 0xb0 ... 0xb1:	/* cmpxchg */
-- 
1.6.0.4.623.g171d7

Re: [Patch 0/5] x86_emulator: emulate shld and shrd instructions

[Avi Kivity]

Guillaume Thouvenin wrote:
> This series of patches emulate instructions shld and shrd. As those
> instructions have three operands we introduce a decode set for the Src2
> operand. By doing this, the opcode descriptor needs to be extend to 32
> bit.
>
> So this series of patches:
>  [1/5] extend the opcode descriptor to 32 bits
>  [2/5] add Src2 decode set
>  [3/5] add a new "implied 1" Src decode type
>  [4/5] add the assembler code for three operands (one operand is stored
> in EXC) 
>  [5/5] add the emulation of shld and shrd instructions
>   

Applied, thanks.

-- 
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.