From 7f662273e476e2d7ff44f411fa9f17c946480100 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Mon, 10 Dec 2012 11:42:30 +0200
Subject: KVM: emulator: implement AAD instruction

Windows2000 uses it during boot. This fixes
https://bugzilla.kernel.org/show_bug.cgi?id=50921

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a27e76371108..47d62e16f9e9 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2852,6 +2852,27 @@ static int em_das(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+static int em_aad(struct x86_emulate_ctxt *ctxt)
+{
+	u8 al = ctxt->dst.val & 0xff;
+	u8 ah = (ctxt->dst.val >> 8) & 0xff;
+
+	al = (al + (ah * ctxt->src.val)) & 0xff;
+
+	ctxt->dst.val = (ctxt->dst.val & 0xffff0000) | al;
+
+	ctxt->eflags &= ~(X86_EFLAGS_PF | X86_EFLAGS_SF | X86_EFLAGS_ZF);
+
+	if (!al)
+		ctxt->eflags |= X86_EFLAGS_ZF;
+	if (!(al & 1))
+		ctxt->eflags |= X86_EFLAGS_PF;
+	if (al & 0x80)
+		ctxt->eflags |= X86_EFLAGS_SF;
+
+	return X86EMUL_CONTINUE;
+}
+
 static int em_call(struct x86_emulate_ctxt *ctxt)
 {
 	long rel = ctxt->src.val;
@@ -3801,7 +3822,7 @@ static const struct opcode opcode_table[256] = {
 	D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret),
 	/* 0xD0 - 0xD7 */
 	D2bv(DstMem | SrcOne | ModRM), D2bv(DstMem | ModRM),
-	N, N, N, N,
+	N, I(DstAcc | SrcImmByte | No64, em_aad), N, N,
 	/* 0xD8 - 0xDF */
 	N, N, N, N, N, N, N, N,
 	/* 0xE0 - 0xE7 */
-- 
cgit v1.2.3


From 5e2c688351f4aee9981918661b6c1679f4155f06 Mon Sep 17 00:00:00 2001
From: Nadav Amit <nadav.amit@gmail.com>
Date: Thu, 6 Dec 2012 21:55:10 -0200
Subject: KVM: x86: fix mov immediate emulation for 64-bit operands

MOV immediate instruction (opcodes 0xB8-0xBF) may take 64-bit operand.
The previous emulation implementation assumes the operand is no longer than 32.
Adding OpImm64 for this matter.

Fixes https://bugzilla.redhat.com/show_bug.cgi?id=881579

Signed-off-by: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 47d62e16f9e9..c7547b3fd527 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -43,7 +43,7 @@
 #define OpCL               9ull  /* CL register (for shifts) */
 #define OpImmByte         10ull  /* 8-bit sign extended immediate */
 #define OpOne             11ull  /* Implied 1 */
-#define OpImm             12ull  /* Sign extended immediate */
+#define OpImm             12ull  /* Sign extended up to 32-bit immediate */
 #define OpMem16           13ull  /* Memory operand (16-bit). */
 #define OpMem32           14ull  /* Memory operand (32-bit). */
 #define OpImmU            15ull  /* Immediate operand, zero extended */
@@ -58,6 +58,7 @@
 #define OpFS              24ull  /* FS */
 #define OpGS              25ull  /* GS */
 #define OpMem8            26ull  /* 8-bit zero extended memory operand */
+#define OpImm64           27ull  /* Sign extended 16/32/64-bit immediate */
 
 #define OpBits             5  /* Width of operand field */
 #define OpMask             ((1ull << OpBits) - 1)
@@ -101,6 +102,7 @@
 #define SrcMemFAddr (OpMemFAddr << SrcShift)
 #define SrcAcc      (OpAcc << SrcShift)
 #define SrcImmU16   (OpImmU16 << SrcShift)
+#define SrcImm64    (OpImm64 << SrcShift)
 #define SrcDX       (OpDX << SrcShift)
 #define SrcMem8     (OpMem8 << SrcShift)
 #define SrcMask     (OpMask << SrcShift)
@@ -3807,7 +3809,7 @@ static const struct opcode opcode_table[256] = {
 	/* 0xB0 - 0xB7 */
 	X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)),
 	/* 0xB8 - 0xBF */
-	X8(I(DstReg | SrcImm | Mov, em_mov)),
+	X8(I(DstReg | SrcImm64 | Mov, em_mov)),
 	/* 0xC0 - 0xC7 */
 	D2bv(DstMem | SrcImmByte | ModRM),
 	I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm),
@@ -3971,6 +3973,9 @@ static int decode_imm(struct x86_emulate_ctxt *ctxt, struct operand *op,
 	case 4:
 		op->val = insn_fetch(s32, ctxt);
 		break;
+	case 8:
+		op->val = insn_fetch(s64, ctxt);
+		break;
 	}
 	if (!sign_extension) {
 		switch (op->bytes) {
@@ -4049,6 +4054,9 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 	case OpImm:
 		rc = decode_imm(ctxt, op, imm_size(ctxt), true);
 		break;
+	case OpImm64:
+		rc = decode_imm(ctxt, op, ctxt->op_bytes, true);
+		break;
 	case OpMem8:
 		ctxt->memop.bytes = 1;
 		goto mem_common;
-- 
cgit v1.2.3


From 3a78a4f46302bfc83602a53dfa4dcbe76a7a1f5f Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 20 Dec 2012 16:57:42 +0200
Subject: KVM: emulator: drop RPL check from linearize() function

According to Intel SDM Vol3 Section 5.5 "Privilege Levels" and 5.6
"Privilege Level Checking When Accessing Data Segments" RPL checking is
done during loading of a segment selector, not during data access. We
already do checking during segment selector loading, so drop the check
during data access. Checking RPL during data access triggers #GP if
after transition from real mode to protected mode RPL bits in a segment
selector are set.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c7547b3fd527..a3d31e3d9875 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -665,7 +665,7 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
 	ulong la;
 	u32 lim;
 	u16 sel;
-	unsigned cpl, rpl;
+	unsigned cpl;
 
 	la = seg_base(ctxt, addr.seg) + addr.ea;
 	switch (ctxt->mode) {
@@ -699,11 +699,6 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
 				goto bad;
 		}
 		cpl = ctxt->ops->cpl(ctxt);
-		if (ctxt->mode == X86EMUL_MODE_REAL)
-			rpl = 0;
-		else
-			rpl = sel & 3;
-		cpl = max(cpl, rpl);
 		if (!(desc.type & 8)) {
 			/* data segment */
 			if (cpl > desc.dpl)
-- 
cgit v1.2.3


From 045a282ca41505184e8fc805335d1f5aae0c8a03 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 20 Dec 2012 16:57:43 +0200
Subject: KVM: emulator: implement fninit, fnstsw, fnstcw

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 126 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 125 insertions(+), 1 deletion(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a3d31e3d9875..53c5ad6851d1 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -115,6 +115,7 @@
 #define GroupDual   (2<<15)     /* Alternate decoding of mod == 3 */
 #define Prefix      (3<<15)     /* Instruction varies with 66/f2/f3 prefix */
 #define RMExt       (4<<15)     /* Opcode extension in ModRM r/m if mod == 3 */
+#define Escape      (5<<15)     /* Escape to coprocessor instruction */
 #define Sse         (1<<18)     /* SSE Vector instruction */
 /* Generic ModRM decode. */
 #define ModRM       (1<<19)
@@ -166,6 +167,7 @@ struct opcode {
 		const struct opcode *group;
 		const struct group_dual *gdual;
 		const struct gprefix *gprefix;
+		const struct escape *esc;
 	} u;
 	int (*check_perm)(struct x86_emulate_ctxt *ctxt);
 };
@@ -182,6 +184,11 @@ struct gprefix {
 	struct opcode pfx_f3;
 };
 
+struct escape {
+	struct opcode op[8];
+	struct opcode high[64];
+};
+
 /* EFLAGS bit definitions. */
 #define EFLG_ID (1<<21)
 #define EFLG_VIP (1<<20)
@@ -991,6 +998,53 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	ctxt->ops->put_fpu(ctxt);
 }
 
+static int em_fninit(struct x86_emulate_ctxt *ctxt)
+{
+	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+		return emulate_nm(ctxt);
+
+	ctxt->ops->get_fpu(ctxt);
+	asm volatile("fninit");
+	ctxt->ops->put_fpu(ctxt);
+	return X86EMUL_CONTINUE;
+}
+
+static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
+{
+	u16 fcw;
+
+	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+		return emulate_nm(ctxt);
+
+	ctxt->ops->get_fpu(ctxt);
+	asm volatile("fnstcw %0": "+m"(fcw));
+	ctxt->ops->put_fpu(ctxt);
+
+	/* force 2 byte destination */
+	ctxt->dst.bytes = 2;
+	ctxt->dst.val = fcw;
+
+	return X86EMUL_CONTINUE;
+}
+
+static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
+{
+	u16 fsw;
+
+	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+		return emulate_nm(ctxt);
+
+	ctxt->ops->get_fpu(ctxt);
+	asm volatile("fnstsw %0": "+m"(fsw));
+	ctxt->ops->put_fpu(ctxt);
+
+	/* force 2 byte destination */
+	ctxt->dst.bytes = 2;
+	ctxt->dst.val = fsw;
+
+	return X86EMUL_CONTINUE;
+}
+
 static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
 				    struct operand *op)
 {
@@ -3590,6 +3644,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 #define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) }
 #define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) }
 #define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) }
+#define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) }
 #define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
 #define II(_f, _e, _i) \
 	{ .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i }
@@ -3725,6 +3780,69 @@ static const struct gprefix pfx_vmovntpx = {
 	I(0, em_mov), N, N, N,
 };
 
+static const struct escape escape_d9 = { {
+	N, N, N, N, N, N, N, I(DstMem, em_fnstcw),
+}, {
+	/* 0xC0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xC8 - 0xCF */
+	N, N, N, N, N, N, N, N,
+	/* 0xD0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xD8 - 0xDF */
+	N, N, N, N, N, N, N, N,
+	/* 0xE0 - 0xE7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xE8 - 0xEF */
+	N, N, N, N, N, N, N, N,
+	/* 0xF0 - 0xF7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xF8 - 0xFF */
+	N, N, N, N, N, N, N, N,
+} };
+
+static const struct escape escape_db = { {
+	N, N, N, N, N, N, N, N,
+}, {
+	/* 0xC0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xC8 - 0xCF */
+	N, N, N, N, N, N, N, N,
+	/* 0xD0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xD8 - 0xDF */
+	N, N, N, N, N, N, N, N,
+	/* 0xE0 - 0xE7 */
+	N, N, N, I(ImplicitOps, em_fninit), N, N, N, N,
+	/* 0xE8 - 0xEF */
+	N, N, N, N, N, N, N, N,
+	/* 0xF0 - 0xF7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xF8 - 0xFF */
+	N, N, N, N, N, N, N, N,
+} };
+
+static const struct escape escape_dd = { {
+	N, N, N, N, N, N, N, I(DstMem, em_fnstsw),
+}, {
+	/* 0xC0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xC8 - 0xCF */
+	N, N, N, N, N, N, N, N,
+	/* 0xD0 - 0xC7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xD8 - 0xDF */
+	N, N, N, N, N, N, N, N,
+	/* 0xE0 - 0xE7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xE8 - 0xEF */
+	N, N, N, N, N, N, N, N,
+	/* 0xF0 - 0xF7 */
+	N, N, N, N, N, N, N, N,
+	/* 0xF8 - 0xFF */
+	N, N, N, N, N, N, N, N,
+} };
+
 static const struct opcode opcode_table[256] = {
 	/* 0x00 - 0x07 */
 	I6ALU(Lock, em_add),
@@ -3821,7 +3939,7 @@ static const struct opcode opcode_table[256] = {
 	D2bv(DstMem | SrcOne | ModRM), D2bv(DstMem | ModRM),
 	N, I(DstAcc | SrcImmByte | No64, em_aad), N, N,
 	/* 0xD8 - 0xDF */
-	N, N, N, N, N, N, N, N,
+	N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,
 	/* 0xE0 - 0xE7 */
 	X3(I(SrcImmByte, em_loop)),
 	I(SrcImmByte, em_jcxz),
@@ -4246,6 +4364,12 @@ done_prefixes:
 			case 0xf3: opcode = opcode.u.gprefix->pfx_f3; break;
 			}
 			break;
+		case Escape:
+			if (ctxt->modrm > 0xbf)
+				opcode = opcode.u.esc->high[ctxt->modrm - 0xc0];
+			else
+				opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
+			break;
 		default:
 			return EMULATION_FAILED;
 		}
-- 
cgit v1.2.3


From e28bbd44dad134046ef9463cbb8c1cf81f53de5e Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Fri, 4 Jan 2013 16:18:48 +0200
Subject: KVM: x86 emulator: framework for streamlining arithmetic opcodes

We emulate arithmetic opcodes by executing a "similar" (same operation,
different operands) on the cpu.  This ensures accurate emulation, esp. wrt.
eflags.  However, the prologue and epilogue around the opcode is fairly long,
consisting of a switch (for the operand size) and code to load and save the
operands.  This is repeated for every opcode.

This patch introduces an alternative way to emulate arithmetic opcodes.
Instead of the above, we have four (three on i386) functions consisting
of just the opcode and a ret; one for each operand size.  For example:

   .align 8
   em_notb:
	not %al
	ret

   .align 8
   em_notw:
	not %ax
	ret

   .align 8
   em_notl:
	not %eax
	ret

   .align 8
   em_notq:
	not %rax
	ret

The prologue and epilogue are shared across all opcodes.  Note the functions
use a special calling convention; notably eflags is an input/output parameter
and is not clobbered.  Rather than dispatching the four functions through a
jump table, the functions are declared as a constant size (8) so their address
can be calculated.

Acked-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 53c5ad6851d1..dd71567d7c71 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -149,6 +149,7 @@
 #define Aligned     ((u64)1 << 41)  /* Explicitly aligned (e.g. MOVDQA) */
 #define Unaligned   ((u64)1 << 42)  /* Explicitly unaligned (e.g. MOVDQU) */
 #define Avx         ((u64)1 << 43)  /* Advanced Vector Extensions */
+#define Fastop      ((u64)1 << 44)  /* Use opcode::u.fastop */
 
 #define X2(x...) x, x
 #define X3(x...) X2(x), x
@@ -159,6 +160,27 @@
 #define X8(x...) X4(x), X4(x)
 #define X16(x...) X8(x), X8(x)
 
+#define NR_FASTOP (ilog2(sizeof(ulong)) + 1)
+#define FASTOP_SIZE 8
+
+/*
+ * fastop functions have a special calling convention:
+ *
+ * dst:    [rdx]:rax  (in/out)
+ * src:    rbx        (in/out)
+ * src2:   rcx        (in)
+ * flags:  rflags     (in/out)
+ *
+ * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
+ * different operand sizes can be reached by calculation, rather than a jump
+ * table (which would be bigger than the code).
+ *
+ * fastop functions are declared as taking a never-defined fastop parameter,
+ * so they can't be called from C directly.
+ */
+
+struct fastop;
+
 struct opcode {
 	u64 flags : 56;
 	u64 intercept : 8;
@@ -168,6 +190,7 @@ struct opcode {
 		const struct group_dual *gdual;
 		const struct gprefix *gprefix;
 		const struct escape *esc;
+		void (*fastop)(struct fastop *fake);
 	} u;
 	int (*check_perm)(struct x86_emulate_ctxt *ctxt);
 };
@@ -3646,6 +3669,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 #define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) }
 #define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) }
 #define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
+#define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) }
 #define II(_f, _e, _i) \
 	{ .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i }
 #define IIP(_f, _e, _i, _p) \
@@ -4502,6 +4526,16 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt,
 		read_mmx_reg(ctxt, &op->mm_val, op->addr.mm);
 }
 
+static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
+{
+	ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
+	fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE;
+	asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
+	    : "+a"(ctxt->dst.val), "+b"(ctxt->src.val), [flags]"+D"(flags)
+	: "c"(ctxt->src2.val), [fastop]"S"(fop));
+	ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
+	return X86EMUL_CONTINUE;
+}
 
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 {
@@ -4631,6 +4665,13 @@ special_insn:
 	}
 
 	if (ctxt->execute) {
+		if (ctxt->d & Fastop) {
+			void (*fop)(struct fastop *) = (void *)ctxt->execute;
+			rc = fastop(ctxt, fop);
+			if (rc != X86EMUL_CONTINUE)
+				goto done;
+			goto writeback;
+		}
 		rc = ctxt->execute(ctxt);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
-- 
cgit v1.2.3


From b7d491e7f065b5b957a27a65c9e7cd3ef96b2736 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Fri, 4 Jan 2013 16:18:49 +0200
Subject: KVM: x86 emulator: Support for declaring single operand fastops

Acked-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index dd71567d7c71..42c53c8071be 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -24,6 +24,7 @@
 #include "kvm_cache_regs.h"
 #include <linux/module.h>
 #include <asm/kvm_emulate.h>
+#include <linux/stringify.h>
 
 #include "x86.h"
 #include "tss.h"
@@ -439,6 +440,30 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 		}							\
 	} while (0)
 
+#define FOP_ALIGN ".align " __stringify(FASTOP_SIZE) " \n\t"
+#define FOP_RET   "ret \n\t"
+
+#define FOP_START(op) \
+	extern void em_##op(struct fastop *fake); \
+	asm(".pushsection .text, \"ax\" \n\t" \
+	    ".global em_" #op " \n\t" \
+            FOP_ALIGN \
+	    "em_" #op ": \n\t"
+
+#define FOP_END \
+	    ".popsection")
+
+#define FOP1E(op,  dst) \
+	FOP_ALIGN #op " %" #dst " \n\t" FOP_RET
+
+#define FASTOP1(op) \
+	FOP_START(op) \
+	FOP1E(op##b, al) \
+	FOP1E(op##w, ax) \
+	FOP1E(op##l, eax) \
+	ON64(FOP1E(op##q, rax))	\
+	FOP_END
+
 #define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex)			\
 	do {								\
 		unsigned long _tmp;					\
-- 
cgit v1.2.3


From b6744dc3fb55fda7cfcb53beecfa056f02415e6d Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Fri, 4 Jan 2013 16:18:50 +0200
Subject: KVM: x86 emulator: introduce NoWrite flag

Instead of disabling writeback via OP_NONE, just specify NoWrite.

Acked-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 42c53c8071be..fe113fbb3737 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -151,6 +151,7 @@
 #define Unaligned   ((u64)1 << 42)  /* Explicitly unaligned (e.g. MOVDQU) */
 #define Avx         ((u64)1 << 43)  /* Advanced Vector Extensions */
 #define Fastop      ((u64)1 << 44)  /* Use opcode::u.fastop */
+#define NoWrite     ((u64)1 << 45)  /* No writeback */
 
 #define X2(x...) x, x
 #define X3(x...) X2(x), x
@@ -1633,6 +1634,9 @@ static int writeback(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 
+	if (ctxt->d & NoWrite)
+		return X86EMUL_CONTINUE;
+
 	switch (ctxt->dst.type) {
 	case OP_REG:
 		write_register_operand(&ctxt->dst);
-- 
cgit v1.2.3


From 75f728456f368140e6b34b6a79f3408774076325 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Fri, 4 Jan 2013 16:18:51 +0200
Subject: KVM: x86 emulator: mark CMP, CMPS, SCAS, TEST as NoWrite

Acked-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index fe113fbb3737..2af0c4475605 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3069,16 +3069,12 @@ static int em_xor(struct x86_emulate_ctxt *ctxt)
 static int em_cmp(struct x86_emulate_ctxt *ctxt)
 {
 	emulate_2op_SrcV(ctxt, "cmp");
-	/* Disable writeback. */
-	ctxt->dst.type = OP_NONE;
 	return X86EMUL_CONTINUE;
 }
 
 static int em_test(struct x86_emulate_ctxt *ctxt)
 {
 	emulate_2op_SrcV(ctxt, "test");
-	/* Disable writeback. */
-	ctxt->dst.type = OP_NONE;
 	return X86EMUL_CONTINUE;
 }
 
@@ -3747,7 +3743,7 @@ static const struct opcode group1[] = {
 	I(Lock | PageTable, em_and),
 	I(Lock, em_sub),
 	I(Lock, em_xor),
-	I(0, em_cmp),
+	I(NoWrite, em_cmp),
 };
 
 static const struct opcode group1A[] = {
@@ -3755,8 +3751,8 @@ static const struct opcode group1A[] = {
 };
 
 static const struct opcode group3[] = {
-	I(DstMem | SrcImm, em_test),
-	I(DstMem | SrcImm, em_test),
+	I(DstMem | SrcImm | NoWrite, em_test),
+	I(DstMem | SrcImm | NoWrite, em_test),
 	I(DstMem | SrcNone | Lock, em_not),
 	I(DstMem | SrcNone | Lock, em_neg),
 	I(SrcMem, em_mul_ex),
@@ -3920,7 +3916,7 @@ static const struct opcode opcode_table[256] = {
 	/* 0x30 - 0x37 */
 	I6ALU(Lock, em_xor), N, N,
 	/* 0x38 - 0x3F */
-	I6ALU(0, em_cmp), N, N,
+	I6ALU(NoWrite, em_cmp), N, N,
 	/* 0x40 - 0x4F */
 	X16(D(DstReg)),
 	/* 0x50 - 0x57 */
@@ -3946,7 +3942,7 @@ static const struct opcode opcode_table[256] = {
 	G(DstMem | SrcImm, group1),
 	G(ByteOp | DstMem | SrcImm | No64, group1),
 	G(DstMem | SrcImmByte, group1),
-	I2bv(DstMem | SrcReg | ModRM, em_test),
+	I2bv(DstMem | SrcReg | ModRM | NoWrite, em_test),
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg),
 	/* 0x88 - 0x8F */
 	I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov),
@@ -3966,12 +3962,12 @@ static const struct opcode opcode_table[256] = {
 	I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
 	I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
 	I2bv(SrcSI | DstDI | Mov | String, em_mov),
-	I2bv(SrcSI | DstDI | String, em_cmp),
+	I2bv(SrcSI | DstDI | String | NoWrite, em_cmp),
 	/* 0xA8 - 0xAF */
-	I2bv(DstAcc | SrcImm, em_test),
+	I2bv(DstAcc | SrcImm | NoWrite, em_test),
 	I2bv(SrcAcc | DstDI | Mov | String, em_mov),
 	I2bv(SrcSI | DstAcc | Mov | String, em_mov),
-	I2bv(SrcAcc | DstDI | String, em_cmp),
+	I2bv(SrcAcc | DstDI | String | NoWrite, em_cmp),
 	/* 0xB0 - 0xB7 */
 	X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)),
 	/* 0xB8 - 0xBF */
-- 
cgit v1.2.3


From 45a1467d7edff741d97a8be28342440ee65aa03c Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Fri, 4 Jan 2013 16:18:52 +0200
Subject: KVM: x86 emulator: convert NOT, NEG to fastop

Acked-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2af0c4475605..09dbdc5a99e1 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2050,17 +2050,8 @@ static int em_grp2(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static int em_not(struct x86_emulate_ctxt *ctxt)
-{
-	ctxt->dst.val = ~ctxt->dst.val;
-	return X86EMUL_CONTINUE;
-}
-
-static int em_neg(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_1op(ctxt, "neg");
-	return X86EMUL_CONTINUE;
-}
+FASTOP1(not);
+FASTOP1(neg);
 
 static int em_mul_ex(struct x86_emulate_ctxt *ctxt)
 {
@@ -3753,8 +3744,8 @@ static const struct opcode group1A[] = {
 static const struct opcode group3[] = {
 	I(DstMem | SrcImm | NoWrite, em_test),
 	I(DstMem | SrcImm | NoWrite, em_test),
-	I(DstMem | SrcNone | Lock, em_not),
-	I(DstMem | SrcNone | Lock, em_neg),
+	F(DstMem | SrcNone | Lock, em_not),
+	F(DstMem | SrcNone | Lock, em_neg),
 	I(SrcMem, em_mul_ex),
 	I(SrcMem, em_imul_ex),
 	I(SrcMem, em_div_ex),
-- 
cgit v1.2.3


From f7857f35dbf8e7ca36ebff3f43888fd3fb0f0e70 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Fri, 4 Jan 2013 16:18:53 +0200
Subject: KVM: x86 emulator: add macros for defining 2-operand fastop emulation

Acked-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 09dbdc5a99e1..3b5d4dd6750a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -465,6 +465,17 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 	ON64(FOP1E(op##q, rax))	\
 	FOP_END
 
+#define FOP2E(op,  dst, src)	   \
+	FOP_ALIGN #op " %" #src ", %" #dst " \n\t" FOP_RET
+
+#define FASTOP2(op) \
+	FOP_START(op) \
+	FOP2E(op##b, al, bl) \
+	FOP2E(op##w, ax, bx) \
+	FOP2E(op##l, eax, ebx) \
+	ON64(FOP2E(op##q, rax, rbx)) \
+	FOP_END
+
 #define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex)			\
 	do {								\
 		unsigned long _tmp;					\
@@ -3696,6 +3707,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 #define D2bv(_f)      D((_f) | ByteOp), D(_f)
 #define D2bvIP(_f, _i, _p) DIP((_f) | ByteOp, _i, _p), DIP(_f, _i, _p)
 #define I2bv(_f, _e)  I((_f) | ByteOp, _e), I(_f, _e)
+#define F2bv(_f, _e)  F((_f) | ByteOp, _e), F(_f, _e)
 #define I2bvIP(_f, _e, _i, _p) \
 	IIP((_f) | ByteOp, _e, _i, _p), IIP(_f, _e, _i, _p)
 
-- 
cgit v1.2.3


From fb864fbc72fd4e2175fb64072fe9134d3a3ab89a Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Fri, 4 Jan 2013 16:18:54 +0200
Subject: KVM: x86 emulator: convert basic ALU ops to fastop

Opcodes:
	TEST
	CMP
	ADD
	ADC
	SUB
	SBB
	XOR
	OR
	AND

Acked-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 112 +++++++++++++++----------------------------------
 1 file changed, 34 insertions(+), 78 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 3b5d4dd6750a..619a33d0ee0a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3026,59 +3026,15 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static int em_add(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "add");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_or(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "or");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_adc(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "adc");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_sbb(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "sbb");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_and(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "and");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_sub(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "sub");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_xor(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "xor");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_cmp(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "cmp");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_test(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV(ctxt, "test");
-	return X86EMUL_CONTINUE;
-}
+FASTOP2(add);
+FASTOP2(or);
+FASTOP2(adc);
+FASTOP2(sbb);
+FASTOP2(and);
+FASTOP2(sub);
+FASTOP2(xor);
+FASTOP2(cmp);
+FASTOP2(test);
 
 static int em_xchg(struct x86_emulate_ctxt *ctxt)
 {
@@ -3711,9 +3667,9 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 #define I2bvIP(_f, _e, _i, _p) \
 	IIP((_f) | ByteOp, _e, _i, _p), IIP(_f, _e, _i, _p)
 
-#define I6ALU(_f, _e) I2bv((_f) | DstMem | SrcReg | ModRM, _e),		\
-		I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e),	\
-		I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
+#define F6ALU(_f, _e) F2bv((_f) | DstMem | SrcReg | ModRM, _e),		\
+		F2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e),	\
+		F2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
 
 static const struct opcode group7_rm1[] = {
 	DI(SrcNone | Priv, monitor),
@@ -3739,14 +3695,14 @@ static const struct opcode group7_rm7[] = {
 };
 
 static const struct opcode group1[] = {
-	I(Lock, em_add),
-	I(Lock | PageTable, em_or),
-	I(Lock, em_adc),
-	I(Lock, em_sbb),
-	I(Lock | PageTable, em_and),
-	I(Lock, em_sub),
-	I(Lock, em_xor),
-	I(NoWrite, em_cmp),
+	F(Lock, em_add),
+	F(Lock | PageTable, em_or),
+	F(Lock, em_adc),
+	F(Lock, em_sbb),
+	F(Lock | PageTable, em_and),
+	F(Lock, em_sub),
+	F(Lock, em_xor),
+	F(NoWrite, em_cmp),
 };
 
 static const struct opcode group1A[] = {
@@ -3754,8 +3710,8 @@ static const struct opcode group1A[] = {
 };
 
 static const struct opcode group3[] = {
-	I(DstMem | SrcImm | NoWrite, em_test),
-	I(DstMem | SrcImm | NoWrite, em_test),
+	F(DstMem | SrcImm | NoWrite, em_test),
+	F(DstMem | SrcImm | NoWrite, em_test),
 	F(DstMem | SrcNone | Lock, em_not),
 	F(DstMem | SrcNone | Lock, em_neg),
 	I(SrcMem, em_mul_ex),
@@ -3897,29 +3853,29 @@ static const struct escape escape_dd = { {
 
 static const struct opcode opcode_table[256] = {
 	/* 0x00 - 0x07 */
-	I6ALU(Lock, em_add),
+	F6ALU(Lock, em_add),
 	I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg),
 	/* 0x08 - 0x0F */
-	I6ALU(Lock | PageTable, em_or),
+	F6ALU(Lock | PageTable, em_or),
 	I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg),
 	N,
 	/* 0x10 - 0x17 */
-	I6ALU(Lock, em_adc),
+	F6ALU(Lock, em_adc),
 	I(ImplicitOps | Stack | No64 | Src2SS, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2SS, em_pop_sreg),
 	/* 0x18 - 0x1F */
-	I6ALU(Lock, em_sbb),
+	F6ALU(Lock, em_sbb),
 	I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg),
 	I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg),
 	/* 0x20 - 0x27 */
-	I6ALU(Lock | PageTable, em_and), N, N,
+	F6ALU(Lock | PageTable, em_and), N, N,
 	/* 0x28 - 0x2F */
-	I6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das),
+	F6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das),
 	/* 0x30 - 0x37 */
-	I6ALU(Lock, em_xor), N, N,
+	F6ALU(Lock, em_xor), N, N,
 	/* 0x38 - 0x3F */
-	I6ALU(NoWrite, em_cmp), N, N,
+	F6ALU(NoWrite, em_cmp), N, N,
 	/* 0x40 - 0x4F */
 	X16(D(DstReg)),
 	/* 0x50 - 0x57 */
@@ -3945,7 +3901,7 @@ static const struct opcode opcode_table[256] = {
 	G(DstMem | SrcImm, group1),
 	G(ByteOp | DstMem | SrcImm | No64, group1),
 	G(DstMem | SrcImmByte, group1),
-	I2bv(DstMem | SrcReg | ModRM | NoWrite, em_test),
+	F2bv(DstMem | SrcReg | ModRM | NoWrite, em_test),
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg),
 	/* 0x88 - 0x8F */
 	I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov),
@@ -3965,12 +3921,12 @@ static const struct opcode opcode_table[256] = {
 	I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
 	I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
 	I2bv(SrcSI | DstDI | Mov | String, em_mov),
-	I2bv(SrcSI | DstDI | String | NoWrite, em_cmp),
+	F2bv(SrcSI | DstDI | String | NoWrite, em_cmp),
 	/* 0xA8 - 0xAF */
-	I2bv(DstAcc | SrcImm | NoWrite, em_test),
+	F2bv(DstAcc | SrcImm | NoWrite, em_test),
 	I2bv(SrcAcc | DstDI | Mov | String, em_mov),
 	I2bv(SrcSI | DstAcc | Mov | String, em_mov),
-	I2bv(SrcAcc | DstDI | String | NoWrite, em_cmp),
+	F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp),
 	/* 0xB0 - 0xB7 */
 	X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)),
 	/* 0xB8 - 0xBF */
-- 
cgit v1.2.3


From 0bdea06892e33afddbdc5da6df305e9fe9c41365 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Sat, 19 Jan 2013 19:51:50 +0200
Subject: KVM: x86 emulator: Convert SHLD, SHRD to fastop

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 33 +++++++++++++++++++++------------
 1 file changed, 21 insertions(+), 12 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 619a33d0ee0a..a21773f22107 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -454,6 +454,8 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 #define FOP_END \
 	    ".popsection")
 
+#define FOPNOP() FOP_ALIGN FOP_RET
+
 #define FOP1E(op,  dst) \
 	FOP_ALIGN #op " %" #dst " \n\t" FOP_RET
 
@@ -476,6 +478,18 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 	ON64(FOP2E(op##q, rax, rbx)) \
 	FOP_END
 
+#define FOP3E(op,  dst, src, src2) \
+	FOP_ALIGN #op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
+
+/* 3-operand, word-only, src2=cl */
+#define FASTOP3WCL(op) \
+	FOP_START(op) \
+	FOPNOP() \
+	FOP3E(op##w, ax, bx, cl) \
+	FOP3E(op##l, eax, ebx, cl) \
+	ON64(FOP3E(op##q, rax, rbx, cl)) \
+	FOP_END
+
 #define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex)			\
 	do {								\
 		unsigned long _tmp;					\
@@ -3036,6 +3050,9 @@ FASTOP2(xor);
 FASTOP2(cmp);
 FASTOP2(test);
 
+FASTOP3WCL(shld);
+FASTOP3WCL(shrd);
+
 static int em_xchg(struct x86_emulate_ctxt *ctxt)
 {
 	/* Write back the register source. */
@@ -4015,14 +4032,14 @@ static const struct opcode twobyte_table[256] = {
 	/* 0xA0 - 0xA7 */
 	I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg),
 	II(ImplicitOps, em_cpuid, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt),
-	D(DstMem | SrcReg | Src2ImmByte | ModRM),
-	D(DstMem | SrcReg | Src2CL | ModRM), N, N,
+	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld),
+	F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N,
 	/* 0xA8 - 0xAF */
 	I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg),
 	DI(ImplicitOps, rsm),
 	I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
-	D(DstMem | SrcReg | Src2ImmByte | ModRM),
-	D(DstMem | SrcReg | Src2CL | ModRM),
+	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
+	F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
 	D(ModRM), I(DstReg | SrcMem | ModRM, em_imul),
 	/* 0xB0 - 0xB7 */
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_cmpxchg),
@@ -4834,14 +4851,6 @@ twobyte_insn:
 	case 0x90 ... 0x9f:     /* setcc r/m8 */
 		ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags);
 		break;
-	case 0xa4: /* shld imm8, r, r/m */
-	case 0xa5: /* shld cl, r, r/m */
-		emulate_2op_cl(ctxt, "shld");
-		break;
-	case 0xac: /* shrd imm8, r, r/m */
-	case 0xad: /* shrd cl, r, r/m */
-		emulate_2op_cl(ctxt, "shrd");
-		break;
 	case 0xae:              /* clflush */
 		break;
 	case 0xb6 ... 0xb7:	/* movzx */
-- 
cgit v1.2.3


From 007a3b547512d69f67ceb9641796d64552bd337e Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Sat, 19 Jan 2013 19:51:51 +0200
Subject: KVM: x86 emulator: convert shift/rotate instructions to fastop

SHL, SHR, ROL, ROR, RCL, RCR, SAR, SAL

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 72 ++++++++++++++++++++++----------------------------
 1 file changed, 31 insertions(+), 41 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a21773f22107..a94b1d76f799 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -478,6 +478,15 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 	ON64(FOP2E(op##q, rax, rbx)) \
 	FOP_END
 
+/* 2 operand, src is CL */
+#define FASTOP2CL(op) \
+	FOP_START(op) \
+	FOP2E(op##b, al, cl) \
+	FOP2E(op##w, ax, cl) \
+	FOP2E(op##l, eax, cl) \
+	ON64(FOP2E(op##q, rax, cl)) \
+	FOP_END
+
 #define FOP3E(op,  dst, src, src2) \
 	FOP_ALIGN #op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
 
@@ -2046,38 +2055,17 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static int em_grp2(struct x86_emulate_ctxt *ctxt)
-{
-	switch (ctxt->modrm_reg) {
-	case 0:	/* rol */
-		emulate_2op_SrcB(ctxt, "rol");
-		break;
-	case 1:	/* ror */
-		emulate_2op_SrcB(ctxt, "ror");
-		break;
-	case 2:	/* rcl */
-		emulate_2op_SrcB(ctxt, "rcl");
-		break;
-	case 3:	/* rcr */
-		emulate_2op_SrcB(ctxt, "rcr");
-		break;
-	case 4:	/* sal/shl */
-	case 6:	/* sal/shl */
-		emulate_2op_SrcB(ctxt, "sal");
-		break;
-	case 5:	/* shr */
-		emulate_2op_SrcB(ctxt, "shr");
-		break;
-	case 7:	/* sar */
-		emulate_2op_SrcB(ctxt, "sar");
-		break;
-	}
-	return X86EMUL_CONTINUE;
-}
-
 FASTOP1(not);
 FASTOP1(neg);
 
+FASTOP2CL(rol);
+FASTOP2CL(ror);
+FASTOP2CL(rcl);
+FASTOP2CL(rcr);
+FASTOP2CL(shl);
+FASTOP2CL(shr);
+FASTOP2CL(sar);
+
 static int em_mul_ex(struct x86_emulate_ctxt *ctxt)
 {
 	u8 ex = 0;
@@ -3726,6 +3714,17 @@ static const struct opcode group1A[] = {
 	I(DstMem | SrcNone | Mov | Stack, em_pop), N, N, N, N, N, N, N,
 };
 
+static const struct opcode group2[] = {
+	F(DstMem | ModRM, em_rol),
+	F(DstMem | ModRM, em_ror),
+	F(DstMem | ModRM, em_rcl),
+	F(DstMem | ModRM, em_rcr),
+	F(DstMem | ModRM, em_shl),
+	F(DstMem | ModRM, em_shr),
+	F(DstMem | ModRM, em_shl),
+	F(DstMem | ModRM, em_sar),
+};
+
 static const struct opcode group3[] = {
 	F(DstMem | SrcImm | NoWrite, em_test),
 	F(DstMem | SrcImm | NoWrite, em_test),
@@ -3949,7 +3948,7 @@ static const struct opcode opcode_table[256] = {
 	/* 0xB8 - 0xBF */
 	X8(I(DstReg | SrcImm64 | Mov, em_mov)),
 	/* 0xC0 - 0xC7 */
-	D2bv(DstMem | SrcImmByte | ModRM),
+	G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2),
 	I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm),
 	I(ImplicitOps | Stack, em_ret),
 	I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg),
@@ -3961,7 +3960,8 @@ static const struct opcode opcode_table[256] = {
 	D(ImplicitOps), DI(SrcImmByte, intn),
 	D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret),
 	/* 0xD0 - 0xD7 */
-	D2bv(DstMem | SrcOne | ModRM), D2bv(DstMem | ModRM),
+	G(Src2One | ByteOp, group2), G(Src2One, group2),
+	G(Src2CL | ByteOp, group2), G(Src2CL, group2),
 	N, I(DstAcc | SrcImmByte | No64, em_aad), N, N,
 	/* 0xD8 - 0xDF */
 	N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,
@@ -4713,9 +4713,6 @@ special_insn:
 		case 8: ctxt->dst.val = (s32)ctxt->dst.val; break;
 		}
 		break;
-	case 0xc0 ... 0xc1:
-		rc = em_grp2(ctxt);
-		break;
 	case 0xcc:		/* int3 */
 		rc = emulate_int(ctxt, 3);
 		break;
@@ -4726,13 +4723,6 @@ special_insn:
 		if (ctxt->eflags & EFLG_OF)
 			rc = emulate_int(ctxt, 4);
 		break;
-	case 0xd0 ... 0xd1:	/* Grp2 */
-		rc = em_grp2(ctxt);
-		break;
-	case 0xd2 ... 0xd3:	/* Grp2 */
-		ctxt->src.val = reg_read(ctxt, VCPU_REGS_RCX);
-		rc = em_grp2(ctxt);
-		break;
 	case 0xe9: /* jmp rel */
 	case 0xeb: /* jmp rel short */
 		jmp_rel(ctxt, ctxt->src.val);
-- 
cgit v1.2.3


From 9ae9febae9500a0a6f5ce29ee4b8d942b5332529 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Sat, 19 Jan 2013 19:51:52 +0200
Subject: KVM: x86 emulator: covert SETCC to fastop

This is a bit of a special case since we don't have the usual
byte/word/long/quad switch; instead we switch on the condition code embedded
in the instruction.

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 60 ++++++++++++++++++++++++--------------------------
 1 file changed, 29 insertions(+), 31 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a94b1d76f799..e13138dd073e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -499,6 +499,28 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 	ON64(FOP3E(op##q, rax, rbx, cl)) \
 	FOP_END
 
+/* Special case for SETcc - 1 instruction per cc */
+#define FOP_SETCC(op) ".align 4; " #op " %al; ret \n\t"
+
+FOP_START(setcc)
+FOP_SETCC(seto)
+FOP_SETCC(setno)
+FOP_SETCC(setc)
+FOP_SETCC(setnc)
+FOP_SETCC(setz)
+FOP_SETCC(setnz)
+FOP_SETCC(setbe)
+FOP_SETCC(setnbe)
+FOP_SETCC(sets)
+FOP_SETCC(setns)
+FOP_SETCC(setp)
+FOP_SETCC(setnp)
+FOP_SETCC(setl)
+FOP_SETCC(setnl)
+FOP_SETCC(setle)
+FOP_SETCC(setnle)
+FOP_END;
+
 #define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex)			\
 	do {								\
 		unsigned long _tmp;					\
@@ -939,39 +961,15 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt,
 	return rc;
 }
 
-static int test_cc(unsigned int condition, unsigned int flags)
+static u8 test_cc(unsigned int condition, unsigned long flags)
 {
-	int rc = 0;
+	u8 rc;
+	void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf);
 
-	switch ((condition & 15) >> 1) {
-	case 0: /* o */
-		rc |= (flags & EFLG_OF);
-		break;
-	case 1: /* b/c/nae */
-		rc |= (flags & EFLG_CF);
-		break;
-	case 2: /* z/e */
-		rc |= (flags & EFLG_ZF);
-		break;
-	case 3: /* be/na */
-		rc |= (flags & (EFLG_CF|EFLG_ZF));
-		break;
-	case 4: /* s */
-		rc |= (flags & EFLG_SF);
-		break;
-	case 5: /* p/pe */
-		rc |= (flags & EFLG_PF);
-		break;
-	case 7: /* le/ng */
-		rc |= (flags & EFLG_ZF);
-		/* fall through */
-	case 6: /* l/nge */
-		rc |= (!(flags & EFLG_SF) != !(flags & EFLG_OF));
-		break;
-	}
-
-	/* Odd condition identifiers (lsb == 1) have inverted sense. */
-	return (!!rc ^ (condition & 1));
+	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
+	asm("pushq %[flags]; popf; call *%[fastop]"
+	    : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags));
+	return rc;
 }
 
 static void fetch_register_operand(struct operand *op)
-- 
cgit v1.2.3


From 95413dc41398fec2518abf4e0449503b1306dcbc Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Sat, 19 Jan 2013 19:51:53 +0200
Subject: KVM: x86 emulator: convert INC/DEC to fastop

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 24 +++++++-----------------
 1 file changed, 7 insertions(+), 17 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e13138dd073e..edb09e9c111c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2055,6 +2055,8 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 
 FASTOP1(not);
 FASTOP1(neg);
+FASTOP1(inc);
+FASTOP1(dec);
 
 FASTOP2CL(rol);
 FASTOP2CL(ror);
@@ -2105,12 +2107,6 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt)
 	int rc = X86EMUL_CONTINUE;
 
 	switch (ctxt->modrm_reg) {
-	case 0:	/* inc */
-		emulate_1op(ctxt, "inc");
-		break;
-	case 1:	/* dec */
-		emulate_1op(ctxt, "dec");
-		break;
 	case 2: /* call near abs */ {
 		long int old_eip;
 		old_eip = ctxt->_eip;
@@ -3735,14 +3731,14 @@ static const struct opcode group3[] = {
 };
 
 static const struct opcode group4[] = {
-	I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
-	I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
+	F(ByteOp | DstMem | SrcNone | Lock, em_inc),
+	F(ByteOp | DstMem | SrcNone | Lock, em_dec),
 	N, N, N, N, N, N,
 };
 
 static const struct opcode group5[] = {
-	I(DstMem | SrcNone | Lock,		em_grp45),
-	I(DstMem | SrcNone | Lock,		em_grp45),
+	F(DstMem | SrcNone | Lock,		em_inc),
+	F(DstMem | SrcNone | Lock,		em_dec),
 	I(SrcMem | Stack,			em_grp45),
 	I(SrcMemFAddr | ImplicitOps | Stack,	em_call_far),
 	I(SrcMem | Stack,			em_grp45),
@@ -3891,7 +3887,7 @@ static const struct opcode opcode_table[256] = {
 	/* 0x38 - 0x3F */
 	F6ALU(NoWrite, em_cmp), N, N,
 	/* 0x40 - 0x4F */
-	X16(D(DstReg)),
+	X8(F(DstReg, em_inc)), X8(F(DstReg, em_dec)),
 	/* 0x50 - 0x57 */
 	X8(I(SrcReg | Stack, em_push)),
 	/* 0x58 - 0x5F */
@@ -4681,12 +4677,6 @@ special_insn:
 		goto twobyte_insn;
 
 	switch (ctxt->b) {
-	case 0x40 ... 0x47: /* inc r16/r32 */
-		emulate_1op(ctxt, "inc");
-		break;
-	case 0x48 ... 0x4f: /* dec r16/r32 */
-		emulate_1op(ctxt, "dec");
-		break;
 	case 0x63:		/* movsxd */
 		if (ctxt->mode != X86EMUL_MODE_PROT64)
 			goto cannot_emulate;
-- 
cgit v1.2.3


From 11c363ba8f8eb163c275920b4a27697eb43da6e9 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Sat, 19 Jan 2013 19:51:54 +0200
Subject: KVM: x86 emulator: convert BT/BTS/BTR/BTC/BSF/BSR to fastop

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 76 +++++++++++++++++---------------------------------
 1 file changed, 26 insertions(+), 50 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index edb09e9c111c..62014dca9e26 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -478,6 +478,15 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 	ON64(FOP2E(op##q, rax, rbx)) \
 	FOP_END
 
+/* 2 operand, word only */
+#define FASTOP2W(op) \
+	FOP_START(op) \
+	FOPNOP() \
+	FOP2E(op##w, ax, bx) \
+	FOP2E(op##l, eax, ebx) \
+	ON64(FOP2E(op##q, rax, rbx)) \
+	FOP_END
+
 /* 2 operand, src is CL */
 #define FASTOP2CL(op) \
 	FOP_START(op) \
@@ -2066,6 +2075,13 @@ FASTOP2CL(shl);
 FASTOP2CL(shr);
 FASTOP2CL(sar);
 
+FASTOP2W(bsf);
+FASTOP2W(bsr);
+FASTOP2W(bt);
+FASTOP2W(bts);
+FASTOP2W(btr);
+FASTOP2W(btc);
+
 static int em_mul_ex(struct x86_emulate_ctxt *ctxt)
 {
 	u8 ex = 0;
@@ -3377,47 +3393,6 @@ static int em_sti(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static int em_bt(struct x86_emulate_ctxt *ctxt)
-{
-	/* Disable writeback. */
-	ctxt->dst.type = OP_NONE;
-	/* only subword offset */
-	ctxt->src.val &= (ctxt->dst.bytes << 3) - 1;
-
-	emulate_2op_SrcV_nobyte(ctxt, "bt");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_bts(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "bts");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_btr(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "btr");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_btc(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "btc");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_bsf(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "bsf");
-	return X86EMUL_CONTINUE;
-}
-
-static int em_bsr(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "bsr");
-	return X86EMUL_CONTINUE;
-}
-
 static int em_cpuid(struct x86_emulate_ctxt *ctxt)
 {
 	u32 eax, ebx, ecx, edx;
@@ -3773,10 +3748,10 @@ static const struct group_dual group7 = { {
 
 static const struct opcode group8[] = {
 	N, N, N, N,
-	I(DstMem | SrcImmByte,				em_bt),
-	I(DstMem | SrcImmByte | Lock | PageTable,	em_bts),
-	I(DstMem | SrcImmByte | Lock,			em_btr),
-	I(DstMem | SrcImmByte | Lock | PageTable,	em_btc),
+	F(DstMem | SrcImmByte | NoWrite,		em_bt),
+	F(DstMem | SrcImmByte | Lock | PageTable,	em_bts),
+	F(DstMem | SrcImmByte | Lock,			em_btr),
+	F(DstMem | SrcImmByte | Lock | PageTable,	em_btc),
 };
 
 static const struct group_dual group9 = { {
@@ -4025,28 +4000,29 @@ static const struct opcode twobyte_table[256] = {
 	X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)),
 	/* 0xA0 - 0xA7 */
 	I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg),
-	II(ImplicitOps, em_cpuid, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt),
+	II(ImplicitOps, em_cpuid, cpuid),
+	F(DstMem | SrcReg | ModRM | BitOp | NoWrite, em_bt),
 	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld),
 	F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N,
 	/* 0xA8 - 0xAF */
 	I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg),
 	DI(ImplicitOps, rsm),
-	I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
+	F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
 	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
 	F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
 	D(ModRM), I(DstReg | SrcMem | ModRM, em_imul),
 	/* 0xB0 - 0xB7 */
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_cmpxchg),
 	I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg),
-	I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr),
+	F(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr),
 	I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg),
 	I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg),
 	D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xB8 - 0xBF */
 	N, N,
 	G(BitOp, group8),
-	I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc),
-	I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr),
+	F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc),
+	F(DstReg | SrcMem | ModRM, em_bsf), F(DstReg | SrcMem | ModRM, em_bsr),
 	D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
 	/* 0xC0 - 0xC7 */
 	D2bv(DstMem | SrcReg | ModRM | Lock),
-- 
cgit v1.2.3


From 4d7583493e1777f42cc0fda9573d312e4753aa3c Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Sat, 19 Jan 2013 19:51:55 +0200
Subject: KVM: x86 emulator: convert 2-operand IMUL to fastop

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 62014dca9e26..45ddec8b7566 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -441,6 +441,8 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 		}							\
 	} while (0)
 
+static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
+
 #define FOP_ALIGN ".align " __stringify(FASTOP_SIZE) " \n\t"
 #define FOP_RET   "ret \n\t"
 
@@ -3051,6 +3053,8 @@ FASTOP2(test);
 FASTOP3WCL(shld);
 FASTOP3WCL(shrd);
 
+FASTOP2W(imul);
+
 static int em_xchg(struct x86_emulate_ctxt *ctxt)
 {
 	/* Write back the register source. */
@@ -3063,16 +3067,10 @@ static int em_xchg(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static int em_imul(struct x86_emulate_ctxt *ctxt)
-{
-	emulate_2op_SrcV_nobyte(ctxt, "imul");
-	return X86EMUL_CONTINUE;
-}
-
 static int em_imul_3op(struct x86_emulate_ctxt *ctxt)
 {
 	ctxt->dst.val = ctxt->src2.val;
-	return em_imul(ctxt);
+	return fastop(ctxt, em_imul);
 }
 
 static int em_cwd(struct x86_emulate_ctxt *ctxt)
@@ -4010,7 +4008,7 @@ static const struct opcode twobyte_table[256] = {
 	F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
 	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
 	F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
-	D(ModRM), I(DstReg | SrcMem | ModRM, em_imul),
+	D(ModRM), F(DstReg | SrcMem | ModRM, em_imul),
 	/* 0xB0 - 0xB7 */
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_cmpxchg),
 	I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg),
-- 
cgit v1.2.3


From 34b77652b9e98b5796b3a69df600e1717572e51d Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Sat, 19 Jan 2013 19:51:56 +0200
Subject: KVM: x86 emulator: rearrange fastop definitions

Make fastop opcodes usable in other emulations.

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 70 +++++++++++++++++++++++++-------------------------
 1 file changed, 35 insertions(+), 35 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 45ddec8b7566..d06354d9a16a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -972,6 +972,41 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt,
 	return rc;
 }
 
+FASTOP2(add);
+FASTOP2(or);
+FASTOP2(adc);
+FASTOP2(sbb);
+FASTOP2(and);
+FASTOP2(sub);
+FASTOP2(xor);
+FASTOP2(cmp);
+FASTOP2(test);
+
+FASTOP3WCL(shld);
+FASTOP3WCL(shrd);
+
+FASTOP2W(imul);
+
+FASTOP1(not);
+FASTOP1(neg);
+FASTOP1(inc);
+FASTOP1(dec);
+
+FASTOP2CL(rol);
+FASTOP2CL(ror);
+FASTOP2CL(rcl);
+FASTOP2CL(rcr);
+FASTOP2CL(shl);
+FASTOP2CL(shr);
+FASTOP2CL(sar);
+
+FASTOP2W(bsf);
+FASTOP2W(bsr);
+FASTOP2W(bt);
+FASTOP2W(bts);
+FASTOP2W(btr);
+FASTOP2W(btc);
+
 static u8 test_cc(unsigned int condition, unsigned long flags)
 {
 	u8 rc;
@@ -2064,26 +2099,6 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-FASTOP1(not);
-FASTOP1(neg);
-FASTOP1(inc);
-FASTOP1(dec);
-
-FASTOP2CL(rol);
-FASTOP2CL(ror);
-FASTOP2CL(rcl);
-FASTOP2CL(rcr);
-FASTOP2CL(shl);
-FASTOP2CL(shr);
-FASTOP2CL(sar);
-
-FASTOP2W(bsf);
-FASTOP2W(bsr);
-FASTOP2W(bt);
-FASTOP2W(bts);
-FASTOP2W(btr);
-FASTOP2W(btc);
-
 static int em_mul_ex(struct x86_emulate_ctxt *ctxt)
 {
 	u8 ex = 0;
@@ -3040,21 +3055,6 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-FASTOP2(add);
-FASTOP2(or);
-FASTOP2(adc);
-FASTOP2(sbb);
-FASTOP2(and);
-FASTOP2(sub);
-FASTOP2(xor);
-FASTOP2(cmp);
-FASTOP2(test);
-
-FASTOP3WCL(shld);
-FASTOP3WCL(shrd);
-
-FASTOP2W(imul);
-
 static int em_xchg(struct x86_emulate_ctxt *ctxt)
 {
 	/* Write back the register source. */
-- 
cgit v1.2.3


From 158de57f905ed97ea0f993feac1c40a40f5c7a04 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Sat, 19 Jan 2013 19:51:57 +0200
Subject: KVM: x86 emulator: convert a few freestanding emulations to fastop

Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d06354d9a16a..e99fb72cd4c5 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2209,7 +2209,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
 	/* Save real source value, then compare EAX against destination. */
 	ctxt->src.orig_val = ctxt->src.val;
 	ctxt->src.val = reg_read(ctxt, VCPU_REGS_RAX);
-	emulate_2op_SrcV(ctxt, "cmp");
+	fastop(ctxt, em_cmp);
 
 	if (ctxt->eflags & EFLG_ZF) {
 		/* Success: write back to memory. */
@@ -2977,7 +2977,7 @@ static int em_das(struct x86_emulate_ctxt *ctxt)
 	ctxt->src.type = OP_IMM;
 	ctxt->src.val = 0;
 	ctxt->src.bytes = 1;
-	emulate_2op_SrcV(ctxt, "or");
+	fastop(ctxt, em_or);
 	ctxt->eflags &= ~(X86_EFLAGS_AF | X86_EFLAGS_CF);
 	if (cf)
 		ctxt->eflags |= X86_EFLAGS_CF;
@@ -4816,7 +4816,7 @@ twobyte_insn:
 							(s16) ctxt->src.val;
 		break;
 	case 0xc0 ... 0xc1:	/* xadd */
-		emulate_2op_SrcV(ctxt, "add");
+		fastop(ctxt, em_add);
 		/* Write back the register source. */
 		ctxt->src.val = ctxt->dst.orig_val;
 		write_register_operand(&ctxt->src);
-- 
cgit v1.2.3


From 3f0c3d0bb2bcc4b88b22452a7cf0073ee9a0f1e6 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi.kivity@gmail.com>
Date: Sat, 26 Jan 2013 23:56:04 +0200
Subject: KVM: x86 emulator: fix test_cc() build failure on i386

'pushq' doesn't exist on i386.  Replace with 'push', which should work
since the operand is a register.

Signed-off-by: Avi Kivity <avi.kivity@gmail.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 arch/x86/kvm/emulate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e99fb72cd4c5..2b11318151a4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1013,7 +1013,7 @@ static u8 test_cc(unsigned int condition, unsigned long flags)
 	void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf);
 
 	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
-	asm("pushq %[flags]; popf; call *%[fastop]"
+	asm("push %[flags]; popf; call *%[fastop]"
 	    : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags));
 	return rc;
 }
-- 
cgit v1.2.3


From f583c29b7913fa32b0b1b7f43038d6a7d9f71b6f Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Wed, 13 Feb 2013 17:50:39 +0200
Subject: x86 emulator: fix parity calculation for AAD instruction

Reported-by: Paolo Bonzini <pbonzini@redhat.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 arch/x86/kvm/emulate.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2b11318151a4..a335cc6cde72 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2995,14 +2995,11 @@ static int em_aad(struct x86_emulate_ctxt *ctxt)
 
 	ctxt->dst.val = (ctxt->dst.val & 0xffff0000) | al;
 
-	ctxt->eflags &= ~(X86_EFLAGS_PF | X86_EFLAGS_SF | X86_EFLAGS_ZF);
-
-	if (!al)
-		ctxt->eflags |= X86_EFLAGS_ZF;
-	if (!(al & 1))
-		ctxt->eflags |= X86_EFLAGS_PF;
-	if (al & 0x80)
-		ctxt->eflags |= X86_EFLAGS_SF;
+	/* Set PF, ZF, SF */
+	ctxt->src.type = OP_IMM;
+	ctxt->src.val = 0;
+	ctxt->src.bytes = 1;
+	fastop(ctxt, em_or);
 
 	return X86EMUL_CONTINUE;
 }
-- 
cgit v1.2.3