summaryrefslogtreecommitdiff
path: root/arch/x86/tools
diff options
context:
space:
mode:
authorMasami Hiramatsu <mhiramat@redhat.com>2009-08-14 00:34:13 +0400
committerFrederic Weisbecker <fweisbec@gmail.com>2009-08-27 02:35:56 +0400
commiteb13296cfaf6c699566473669a96a38a90562384 (patch)
tree466c44bf0a747effaf85ec13dbf75ae857449bfd /arch/x86/tools
parent35dce1a99d010f3d738af4ce1b9b77302fdfe69c (diff)
downloadlinux-eb13296cfaf6c699566473669a96a38a90562384.tar.xz
x86: Instruction decoder API
Add x86 instruction decoder to arch-specific libraries. This decoder can decode x86 instructions used in kernel into prefix, opcode, modrm, sib, displacement and immediates. This can also show the length of instructions. This version introduces instruction attributes for decoding instructions. The instruction attribute tables are generated from the opcode map file (x86-opcode-map.txt) by the generator script(gen-insn-attr-x86.awk). Currently, the opcode maps are based on opcode maps in Intel(R) 64 and IA-32 Architectures Software Developers Manual Vol.2: Appendix.A, and consist of below two types of opcode tables. 1-byte/2-bytes/3-bytes opcodes, which has 256 elements, are written as below; Table: table-name Referrer: escaped-name opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] (or) opcode: escape # escaped-name EndTable Group opcodes, which has 8 elements, are written as below; GrpTable: GrpXXX reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] EndTable These opcode maps include a few SSE and FP opcodes (for setup), because those opcodes are used in the kernel. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Signed-off-by: Jim Keniston <jkenisto@us.ibm.com> Acked-by: H. Peter Anvin <hpa@zytor.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Avi Kivity <avi@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jason Baron <jbaron@redhat.com> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Przemysław Pawełczyk <przemyslaw@pawelczyk.it> Cc: Roland McGrath <roland@redhat.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Vegard Nossum <vegard.nossum@gmail.com> LKML-Reference: <20090813203413.31965.49709.stgit@localhost.localdomain> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Diffstat (limited to 'arch/x86/tools')
-rw-r--r--arch/x86/tools/gen-insn-attr-x86.awk314
1 files changed, 314 insertions, 0 deletions
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
new file mode 100644
index 000000000000..93b62c92d044
--- /dev/null
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -0,0 +1,314 @@
+#!/bin/awk -f
+# gen-insn-attr-x86.awk: Instruction attribute table generator
+# Written by Masami Hiramatsu <mhiramat@redhat.com>
+#
+# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c
+
+BEGIN {
+ print "/* x86 opcode map generated from x86-opcode-map.txt */"
+ print "/* Do not change this code. */"
+ ggid = 1
+ geid = 1
+
+ opnd_expr = "^[[:alpha:]]"
+ ext_expr = "^\\("
+ sep_expr = "^\\|$"
+ group_expr = "^Grp[[:alnum:]]+"
+
+ imm_expr = "^[IJAO][[:lower:]]"
+ imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+ imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+ imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
+ imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)"
+ imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)"
+ imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)"
+ imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+ imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+ imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
+ imm_flag["Ob"] = "INAT_MOFFSET"
+ imm_flag["Ov"] = "INAT_MOFFSET"
+
+ 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
+ max_lprefix = 4
+
+ prefix_expr = "\\(Prefix\\)"
+ prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
+ prefix_num["REPNE"] = "INAT_PFX_REPNE"
+ prefix_num["REP/REPE"] = "INAT_PFX_REPE"
+ prefix_num["LOCK"] = "INAT_PFX_LOCK"
+ prefix_num["SEG=CS"] = "INAT_PFX_CS"
+ prefix_num["SEG=DS"] = "INAT_PFX_DS"
+ prefix_num["SEG=ES"] = "INAT_PFX_ES"
+ prefix_num["SEG=FS"] = "INAT_PFX_FS"
+ prefix_num["SEG=GS"] = "INAT_PFX_GS"
+ prefix_num["SEG=SS"] = "INAT_PFX_SS"
+ prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
+
+ delete table
+ delete etable
+ delete gtable
+ eid = -1
+ gid = -1
+}
+
+function semantic_error(msg) {
+ print "Semantic error at " NR ": " msg > "/dev/stderr"
+ exit 1
+}
+
+function debug(msg) {
+ print "DEBUG: " msg
+}
+
+function array_size(arr, i,c) {
+ c = 0
+ for (i in arr)
+ c++
+ return c
+}
+
+/^Table:/ {
+ print "/* " $0 " */"
+}
+
+/^Referrer:/ {
+ if (NF == 1) {
+ # primary opcode table
+ tname = "inat_primary_table"
+ eid = -1
+ } else {
+ # escape opcode table
+ ref = ""
+ for (i = 2; i <= NF; i++)
+ ref = ref $i
+ eid = escape[ref]
+ tname = sprintf("inat_escape_table_%d", eid)
+ }
+}
+
+/^GrpTable:/ {
+ print "/* " $0 " */"
+ if (!($2 in group))
+ semantic_error("No group: " $2 )
+ gid = group[$2]
+ tname = "inat_group_table_" gid
+}
+
+function print_table(tbl,name,fmt,n)
+{
+ print "const insn_attr_t " name " = {"
+ for (i = 0; i < n; i++) {
+ id = sprintf(fmt, i)
+ if (tbl[id])
+ print " [" id "] = " tbl[id] ","
+ }
+ print "};"
+}
+
+/^EndTable/ {
+ if (gid != -1) {
+ # print group tables
+ if (array_size(table) != 0) {
+ print_table(table, tname "[INAT_GROUP_TABLE_SIZE]",
+ "0x%x", 8)
+ gtable[gid,0] = tname
+ }
+ if (array_size(lptable1) != 0) {
+ print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]",
+ "0x%x", 8)
+ gtable[gid,1] = tname "_1"
+ }
+ if (array_size(lptable2) != 0) {
+ print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]",
+ "0x%x", 8)
+ gtable[gid,2] = tname "_2"
+ }
+ if (array_size(lptable3) != 0) {
+ print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]",
+ "0x%x", 8)
+ gtable[gid,3] = tname "_3"
+ }
+ } else {
+ # print primary/escaped tables
+ if (array_size(table) != 0) {
+ print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]",
+ "0x%02x", 256)
+ etable[eid,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 (array_size(lptable2) != 0) {
+ print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]",
+ "0x%02x", 256)
+ etable[eid,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"
+ }
+ }
+ print ""
+ delete table
+ delete lptable1
+ delete lptable2
+ delete lptable3
+ gid = -1
+ eid = -1
+}
+
+function add_flags(old,new) {
+ if (old && new)
+ return old " | " new
+ else if (old)
+ return old
+ else
+ return new
+}
+
+# convert operands to flags.
+function convert_operands(opnd, i,imm,mod)
+{
+ imm = null
+ mod = null
+ for (i in opnd) {
+ i = opnd[i]
+ if (match(i, imm_expr) == 1) {
+ if (!imm_flag[i])
+ semantic_error("Unknown imm opnd: " i)
+ if (imm) {
+ if (i != "Ib")
+ semantic_error("Second IMM error")
+ imm = add_flags(imm, "INAT_SCNDIMM")
+ } else
+ imm = imm_flag[i]
+ } else if (match(i, modrm_expr))
+ mod = "INAT_MODRM"
+ }
+ return add_flags(imm, mod)
+}
+
+/^[0-9a-f]+\:/ {
+ if (NR == 1)
+ next
+ # get index
+ idx = "0x" substr($1, 1, index($1,":") - 1)
+ if (idx in table)
+ semantic_error("Redefine " idx " in " tname)
+
+ # check if escaped opcode
+ if ("escape" == $2) {
+ if ($3 != "#")
+ semantic_error("No escaped name")
+ ref = ""
+ for (i = 4; i <= NF; i++)
+ ref = ref $i
+ if (ref in escape)
+ semantic_error("Redefine escape (" ref ")")
+ escape[ref] = geid
+ geid++
+ table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")"
+ next
+ }
+
+ variant = null
+ # converts
+ i = 2
+ while (i <= NF) {
+ opcode = $(i++)
+ delete opnds
+ ext = null
+ flags = null
+ opnd = null
+ # parse one opcode
+ if (match($i, opnd_expr)) {
+ opnd = $i
+ split($(i++), opnds, ",")
+ flags = convert_operands(opnds)
+ }
+ if (match($i, ext_expr))
+ ext = $(i++)
+ if (match($i, sep_expr))
+ i++
+ else if (i < NF)
+ semantic_error($i " is not a separator")
+
+ # check if group opcode
+ if (match(opcode, group_expr)) {
+ if (!(opcode in group)) {
+ group[opcode] = ggid
+ ggid++
+ }
+ flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")")
+ }
+ # check force(or default) 64bit
+ if (match(ext, force64_expr))
+ flags = add_flags(flags, "INAT_FORCE64")
+
+ # check REX prefix
+ if (match(opcode, rex_expr))
+ flags = add_flags(flags, "INAT_REXPFX")
+
+ # check coprocessor escape : TODO
+ if (match(opcode, fpu_expr))
+ flags = add_flags(flags, "INAT_MODRM")
+
+ # check prefixes
+ if (match(ext, prefix_expr)) {
+ if (!prefix_num[opcode])
+ semantic_error("Unknown prefix: " opcode)
+ flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")")
+ }
+ if (length(flags) == 0)
+ continue
+ # check if last prefix
+ if (match(ext, lprefix1_expr)) {
+ lptable1[idx] = add_flags(lptable1[idx],flags)
+ variant = "INAT_VARIANT"
+ } else if (match(ext, lprefix2_expr)) {
+ lptable2[idx] = add_flags(lptable2[idx],flags)
+ variant = "INAT_VARIANT"
+ } else if (match(ext, lprefix3_expr)) {
+ lptable3[idx] = add_flags(lptable3[idx],flags)
+ variant = "INAT_VARIANT"
+ } else {
+ table[idx] = add_flags(table[idx],flags)
+ }
+ }
+ if (variant)
+ table[idx] = add_flags(table[idx],variant)
+}
+
+END {
+ # print escape opcode map's array
+ print "/* Escape opcode map array */"
+ print "const insn_attr_t const *inat_escape_tables[INAT_ESC_MAX + 1]" \
+ "[INAT_LPREFIX_MAX + 1] = {"
+ for (i = 0; i < geid; i++)
+ for (j = 0; j < max_lprefix; j++)
+ if (etable[i,j])
+ print " ["i"]["j"] = "etable[i,j]","
+ print "};\n"
+ # print group opcode map's array
+ print "/* Group opcode map array */"
+ print "const insn_attr_t const *inat_group_tables[INAT_GRP_MAX + 1]"\
+ "[INAT_LPREFIX_MAX + 1] = {"
+ for (i = 0; i < ggid; i++)
+ for (j = 0; j < max_lprefix; j++)
+ if (gtable[i,j])
+ print " ["i"]["j"] = "gtable[i,j]","
+ print "};"
+}