perf tools: Add Intel PT instruction decoder

Add support for decoding instructions for Intel Processor Trace.  The
kernel x86 instruction decoder is copied for this.

This essentially provides intel_pt_get_insn() which takes a binary
buffer, uses the kernel's x86 instruction decoder to get details of the
instruction and then categorizes it for consumption by an Intel PT
decoder.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1439450095-30122-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

12 files changed, 2803 insertions, 3 deletions

diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index faca2bf6a430..8120af9c0341 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -57,6 +57,8 @@ quiet_cmd_cc_i_c = CPP      $@
 quiet_cmd_cc_s_c = AS       $@
       cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $<
 
+quiet_cmd_gen = GEN      $@
+
 # Link agregate command
 # If there's nothing to link, create empty $@ object.
 quiet_cmd_ld_multi = LD       $@
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 09db62ba5786..3d1bb802dbf4 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -29,3 +29,4 @@ config.mak.autogen
 *.pyc
 *.pyo
 .config-detected
+util/intel-pt-decoder/inat-tables.c
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 4b58daeff881..d9863cb96f59 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -76,6 +76,12 @@ include config/utilities.mak
 #
 # Define NO_AUXTRACE if you do not want AUX area tracing support
 
+# As per kernel Makefile, avoid funny character set dependencies
+unexport LC_ALL
+LC_COLLATE=C
+LC_NUMERIC=C
+export LC_COLLATE LC_NUMERIC
+
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
@@ -135,6 +141,7 @@ INSTALL = install
 FLEX    = flex
 BISON   = bison
 STRIP   = strip
+AWK     = awk
 
 LIB_DIR          = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
@@ -289,7 +296,7 @@ strip: $(PROGRAMS) $(OUTPUT)perf
 
 PERF_IN := $(OUTPUT)perf-in.o
 
-export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX
+export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK
 build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
 $(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE
@@ -565,7 +572,8 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
         $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
         $(Q)$(RM) $(OUTPUT).config-detected
         $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
-        $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
+        $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
+                $(OUTPUT)util/intel-pt-decoder/inat-tables.c
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
         $(python-clean)
 
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 9d67381a9bd3..5a46ce13c1f8 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -1 +1,11 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o
+
+inat_tables_script = util/intel-pt-decoder/gen-insn-attr-x86.awk
+inat_tables_maps = util/intel-pt-decoder/x86-opcode-map.txt
+
+$(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+        @$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
+
+$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+
+CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init
diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
new file mode 100644
index 000000000000..517567347aac
--- /dev/null
+++ b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
@@ -0,0 +1,386 @@
+#!/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
+
+# Awk implementation sanity check
+function check_awk_implement() {
+        if (sprintf("%x", 0) != "0")
+                return "Your awk has a printf-format problem."
+        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()
+        if (awkchecked != "") {
+                print "Error: " awkchecked > "/dev/stderr"
+                print "Please try to use gawk." > "/dev/stderr"
+                exit 1
+        }
+
+        # Setup generating tables
+        print "/* x86 opcode map generated from x86-opcode-map.txt */"
+        print "/* Do not change this code. */\n"
+        ggid = 1
+        geid = 1
+        gaid = 0
+        delete etable
+        delete gtable
+        delete atable
+
+        opnd_expr = "^[A-Za-z/]"
+        ext_expr = "^\\("
+        sep_expr = "^\\|$"
+        group_expr = "^Grp[0-9A-Za-z]+"
+
+        imm_expr = "^[IJAOL][a-z]"
+        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"
+        imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+
+        modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
+        force64_expr = "\\([df]64\\)"
+        rex_expr = "^REX(\\.[XRWB]+)*"
+        fpu_expr = "^ESC" # TODO
+
+        lprefix1_expr = "\\((66|!F3)\\)"
+        lprefix2_expr = "\\(F3\\)"
+        lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
+        lprefix_expr = "\\((66|F2|F3)\\)"
+        max_lprefix = 4
+
+        # All opcodes starting with lower-case 'v' or with (v1) superscript
+        # accepts VEX prefix
+        vexok_opcode_expr = "^v.*"
+        vexok_expr = "\\(v1\\)"
+        # All opcodes with (v) superscript supports *only* VEX prefix
+        vexonly_expr = "\\(v\\)"
+
+        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["XACQUIRE"] = "INAT_PFX_REPNE"
+        prefix_num["XRELEASE"] = "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"