x86: AVX instruction set decoder support

Add Intel AVX(Advanced Vector Extensions) instruction set
support to x86 instruction decoder. This adds insn.vex_prefix
field for storing VEX prefixes, and introduces some original
tags for expressing opcodes attributes.
Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: K.Prasad <prasad@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
LKML-Reference: <20091027204226.30545.23451.stgit@harusame>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/include/asm/inat.h

@@ -32,8 +32,8 @@
 
 /* Legacy last prefixes */
 #define INAT_PFX_OPNDSZ	1	/* 0x66 */ /* LPFX1 */
-#define INAT_PFX_REPNE	2	/* 0xF2 */ /* LPFX2 */
-#define INAT_PFX_REPE	3	/* 0xF3 */ /* LPFX3 */
+#define INAT_PFX_REPE	2	/* 0xF3 */ /* LPFX2 */
+#define INAT_PFX_REPNE	3	/* 0xF2 */ /* LPFX3 */
 /* Other Legacy prefixes */
 #define INAT_PFX_LOCK	4	/* 0xF0 */
 #define INAT_PFX_CS	5	/* 0x2E */
@@ -45,6 +45,9 @@
 #define INAT_PFX_ADDRSZ	11	/* 0x67 */
 /* x86-64 REX prefix */
 #define INAT_PFX_REX	12	/* 0x4X */
+/* AVX VEX prefixes */
+#define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
+#define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -84,6 +87,8 @@
 #define INAT_SCNDIMM	(1 << (INAT_FLAG_OFFS + 2))
 #define INAT_MOFFSET	(1 << (INAT_FLAG_OFFS + 3))
 #define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
+#define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
+#define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -98,6 +103,9 @@ extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
 extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
 					    insn_byte_t last_pfx,
 					    insn_attr_t esc_attr);
+extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
+					  insn_byte_t vex_m,
+					  insn_byte_t vex_pp);
 
 /* Attribute checking functions */
 static inline int inat_is_legacy_prefix(insn_attr_t attr)
@@ -129,6 +137,17 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
 		return attr & INAT_PFX_MASK;
 }
 
+static inline int inat_is_vex_prefix(insn_attr_t attr)
+{
+	attr &= INAT_PFX_MASK;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+}
+
+static inline int inat_is_vex3_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3;
+}
+
 static inline int inat_is_escape(insn_attr_t attr)
 {
 	return attr & INAT_ESC_MASK;
@@ -189,4 +208,13 @@ static inline int inat_has_variant(insn_attr_t attr)
 	return attr & INAT_VARIANT;
 }
 
+static inline int inat_accept_vex(insn_attr_t attr)
+{
+	return attr & INAT_VEXOK;
+}
+
+static inline int inat_must_vex(insn_attr_t attr)
+{
+	return attr & INAT_VEXONLY;
+}
 #endif

arch/x86/include/asm/insn.h

@@ -39,6 +39,7 @@ struct insn {
 					 * prefixes.bytes[3]: last prefix
 					 */
 	struct insn_field rex_prefix;	/* REX prefix */
+	struct insn_field vex_prefix;	/* VEX prefix */
 	struct insn_field opcode;	/*
 					 * opcode.bytes[0]: opcode1
 					 * opcode.bytes[1]: opcode2
@@ -80,6 +81,19 @@ struct insn {
 #define X86_REX_X(rex) ((rex) & 2)
 #define X86_REX_B(rex) ((rex) & 1)
 
+/* VEX bit flags  */
+#define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
+#define X86_VEX_R(vex)	((vex) & 0x80)	/* VEX2/3 Byte1 */
+#define X86_VEX_X(vex)	((vex) & 0x40)	/* VEX3 Byte1 */
+#define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
+#define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
+/* VEX bit fields */
+#define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
+#define X86_VEX2_M	1			/* VEX2.M always 1 */
+#define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
+#define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
+
 /* The last prefix is needed for two-byte and three-byte opcodes */
 static inline insn_byte_t insn_last_prefix(struct insn *insn)
 {
@@ -114,15 +128,42 @@ static inline void kernel_insn_init(struct insn *insn, const void *kaddr)
 #endif
 }
 
+static inline int insn_is_avx(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.value != 0);
+}
+
+static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
+		return X86_VEX2_M;
+	else
+		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+}
+
+static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
+		return X86_VEX_P(insn->vex_prefix.bytes[1]);
+	else
+		return X86_VEX_P(insn->vex_prefix.bytes[2]);
+}
+
 /* Offset of each field from kaddr */
 static inline int insn_offset_rex_prefix(struct insn *insn)
 {
 	return insn->prefixes.nbytes;
 }
-static inline int insn_offset_opcode(struct insn *insn)
+static inline int insn_offset_vex_prefix(struct insn *insn)
 {
 	return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes;
 }
+static inline int insn_offset_opcode(struct insn *insn)
+{
+	return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes;
+}
 static inline int insn_offset_modrm(struct insn *insn)
 {
 	return insn_offset_opcode(insn) + insn->opcode.nbytes;

arch/x86/lib/inat.c

@@ -76,3 +76,15 @@ insn_attr_t inat_get_group_attribute(insn_byte_t modrm, insn_byte_t last_pfx,
 	       inat_group_common_attribute(grp_attr);
 }
 
+insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
+				   insn_byte_t vex_p)
+{
+	const insn_attr_t *table;
+	if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
+		return 0;
+	table = inat_avx_tables[vex_m][vex_p];
+	if (!table)
+		return 0;
+	return table[opcode];
+}
+

arch/x86/lib/insn.c

@@ -28,6 +28,9 @@
 #define peek_next(t, insn)	\
 	({t r; r = *(t*)insn->next_byte; r; })
 
+#define peek_nbyte_next(t, insn, n)	\
+	({t r; r = *(t*)((insn)->next_byte + n); r; })
+
 /**
  * insn_init() - initialize struct insn
  * @insn:	&struct insn to be initialized
@@ -107,6 +110,7 @@ void insn_get_prefixes(struct insn *insn)
 		insn->prefixes.bytes[3] = lb;
 	}
 
+	/* Decode REX prefix */
 	if (insn->x86_64) {
 		b = peek_next(insn_byte_t, insn);
 		attr = inat_get_opcode_attribute(b);
@@ -120,6 +124,39 @@ void insn_get_prefixes(struct insn *insn)
 		}
 	}
 	insn->rex_prefix.got = 1;
+
+	/* Decode VEX prefix */
+	b = peek_next(insn_byte_t, insn);
+	attr = inat_get_opcode_attribute(b);
+	if (inat_is_vex_prefix(attr)) {
+		insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
+		if (!insn->x86_64) {
+			/*
+			 * In 32-bits mode, if the [7:6] bits (mod bits of
+			 * ModRM) on the second byte are not 11b, it is
+			 * LDS or LES.
+			 */
+			if (X86_MODRM_MOD(b2) != 3)
+				goto vex_end;
+		}
+		insn->vex_prefix.bytes[0] = b;
+		insn->vex_prefix.bytes[1] = b2;
+		if (inat_is_vex3_prefix(attr)) {
+			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+			insn->vex_prefix.bytes[2] = b2;
+			insn->vex_prefix.nbytes = 3;
+			insn->next_byte += 3;
+			if (insn->x86_64 && X86_VEX_W(b2))
+				/* VEX.W overrides opnd_size */
+				insn->opnd_bytes = 8;
+		} else {
+			insn->vex_prefix.nbytes = 2;
+			insn->next_byte += 2;
+		}
+	}
+vex_end:
+	insn->vex_prefix.got = 1;
+
 	prefixes->got = 1;
 	return;
 }
@@ -147,6 +184,18 @@ void insn_get_opcode(struct insn *insn)
 	op = get_next(insn_byte_t, insn);
 	opcode->bytes[0] = op;
 	opcode->nbytes = 1;
+
+	/* Check if there is VEX prefix or not */
+	if (insn_is_avx(insn)) {
+		insn_byte_t m, p;
+		m = insn_vex_m_bits(insn);
+		p = insn_vex_p_bits(insn);
+		insn->attr = inat_get_avx_attribute(op, m, p);
+		if (!inat_accept_vex(insn->attr))
+			insn->attr = 0;	/* This instruction is bad */
+		goto end;	/* VEX has only 1 byte for opcode */
+	}
+
 	insn->attr = inat_get_opcode_attribute(op);
 	while (inat_is_escape(insn->attr)) {
 		/* Get escaped opcode */
@@ -155,6 +204,9 @@ void insn_get_opcode(struct insn *insn)
 		pfx = insn_last_prefix(insn);
 		insn->attr = inat_get_escape_attribute(op, pfx, insn->attr);
 	}
+	if (inat_must_vex(insn->attr))
+		insn->attr = 0;	/* This instruction is bad */
+end:
 	opcode->got = 1;
 }
 

arch/x86/tools/gen-insn-attr-x86.awk

@@ -13,6 +13,18 @@ function check_awk_implement() {
 	return ""
 }
 
+# Clear working vars
+function clear_vars() {
+	delete table
+	delete lptable2
+	delete lptable1
+	delete lptable3
+	eid = -1 # escape id
+	gid = -1 # group id
+	aid = -1 # AVX id
+	tname = ""
+}
+
 BEGIN {
 	# Implementation error checking
 	awkchecked = check_awk_implement()
@@ -24,11 +36,15 @@ BEGIN {
 
 	# Setup generating tables
 	print "/* x86 opcode map generated from x86-opcode-map.txt */"
-	print "/* Do not change this code. */"
+	print "/* Do not change this code. */\n"
 	ggid = 1
 	geid = 1
+	gaid = 0
+	delete etable
+	delete gtable
+	delete atable
 
-	opnd_expr = "^[[:alpha:]]"
+	opnd_expr = "^[[:alpha:]/]"
 	ext_expr = "^\\("
 	sep_expr = "^\\|$"
 	group_expr = "^Grp[[:alnum:]]+"
@@ -46,19 +62,19 @@ BEGIN {
 	imm_flag["Ob"] = "INAT_MOFFSET"
 	imm_flag["Ov"] = "INAT_MOFFSET"
 
-	modrm_expr = "^([CDEGMNPQRSUVW][[:lower:]]+|NTA|T[012])"
+	modrm_expr = "^([CDEGMNPQRSUVW/][[:lower:]]+|NTA|T[012])"
 	force64_expr = "\\([df]64\\)"
 	rex_expr = "^REX(\\.[XRWB]+)*"
 	fpu_expr = "^ESC" # TODO
 
 	lprefix1_expr = "\\(66\\)"
-	delete lptable1
-	lprefix2_expr = "\\(F2\\)"
-	delete lptable2
-	lprefix3_expr = "\\(F3\\)"
-	delete lptable3
+	lprefix2_expr = "\\(F3\\)"
+	lprefix3_expr = "\\(F2\\)"
 	max_lprefix = 4
 
+	vexok_expr = "\\(VEX\\)"
+	vexonly_expr = "\\(oVEX\\)"
+
 	prefix_expr = "\\(Prefix\\)"
 	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
 	prefix_num["REPNE"] = "INAT_PFX_REPNE"
@@ -71,12 +87,10 @@ BEGIN {
 	prefix_num["SEG=GS"] = "INAT_PFX_GS"
 	prefix_num["SEG=SS"] = "INAT_PFX_SS"
 	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
+	prefix_num["2bytes-VEX"] = "INAT_PFX_VEX2"
+	prefix_num["3bytes-VEX"] = "INAT_PFX_VEX3"
 
-	delete table
-	delete etable
-	delete gtable
-	eid = -1
-	gid = -1
+	clear_vars()
 }
 
 function semantic_error(msg) {
@@ -97,14 +111,12 @@ function array_size(arr,   i,c) {
 
 /^Table:/ {
 	print "/* " $0 " */"
+	if (tname != "")
+		semantic_error("Hit Table: before EndTable:.");
 }
 
 /^Referrer:/ {
-	if (NF == 1) {
-		# primary opcode table
-		tname = "inat_primary_table"
-		eid = -1
-	} else {
+	if (NF != 1) {
 		# escape opcode table
 		ref = ""
 		for (i = 2; i <= NF; i++)
@@ -114,6 +126,19 @@ function array_size(arr,   i,c) {
 	}
 }
 
+/^AVXcode:/ {
+	if (NF != 1) {
+		# AVX/escape opcode table
+		aid = $2
+		if (gaid <= aid)
+			gaid = aid + 1
+		if (tname == "")	# AVX only opcode table
+			tname = sprintf("inat_avx_table_%d", $2)
+	}
+	if (aid == -1 && eid == -1)	# primary opcode table
+		tname = "inat_primary_table"
+}
+
 /^GrpTable:/ {
 	print "/* " $0 " */"
 	if (!($2 in group))
@@ -162,30 +187,33 @@ function print_table(tbl,name,fmt,n)
 			print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]",
 				    "0x%02x", 256)
 			etable[eid,0] = tname
+			if (aid >= 0)
+				atable[aid,0] = tname
 		}
 		if (array_size(lptable1) != 0) {
 			print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]",
 				    "0x%02x", 256)
 			etable[eid,1] = tname "_1"
+			if (aid >= 0)
+				atable[aid,1] = tname "_1"
 		}
 		if (array_size(lptable2) != 0) {
 			print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]",
 				    "0x%02x", 256)
 			etable[eid,2] = tname "_2"
+			if (aid >= 0)
+				atable[aid,2] = tname "_2"
 		}
 		if (array_size(lptable3) != 0) {
 			print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]",
 				    "0x%02x", 256)
 			etable[eid,3] = tname "_3"
+			if (aid >= 0)
+				atable[aid,3] = tname "_3"
 		}
 	}
 	print ""
-	delete table
-	delete lptable1
-	delete lptable2
-	delete lptable3
-	gid = -1
-	eid = -1
+	clear_vars()
 }
 
 function add_flags(old,new) {
@@ -284,6 +312,14 @@ function convert_operands(opnd,       i,imm,mod)
 		if (match(opcode, fpu_expr))
 			flags = add_flags(flags, "INAT_MODRM")
 
+		# check VEX only code
+		if (match(ext, vexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
+
+		# check VEX only code
+		if (match(ext, vexok_expr))
+			flags = add_flags(flags, "INAT_VEXOK")
+
 		# check prefixes
 		if (match(ext, prefix_expr)) {
 			if (!prefix_num[opcode])
@@ -330,5 +366,15 @@ END {
 		for (j = 0; j < max_lprefix; j++)
 			if (gtable[i,j])
 				print "	["i"]["j"] = "gtable[i,j]","
+	print "};\n"
+	# print AVX opcode map's array
+	print "/* AVX opcode map array */"
+	print "const insn_attr_t const *inat_avx_tables[X86_VEX_M_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < gaid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (atable[i,j])
+				print "	["i"]["j"] = "atable[i,j]","
 	print "};"
 }
+