[PATCH v2 0/5] perf: script: Intro capstone disasm engine to show instruction trace

[PATCH v2 0/5] perf: script: Intro capstone disasm engine to show instruction trace

[Changbin Du]

This series introduces capstone disassembler engine to print instructions of
Intel PT trace, which was printed via the XED tool.

The advantages compared to XED tool:
    * Support arm, arm64, x86-32, x86_64 (more could be supported),
      xed only for x86_64.
    * More friendly to read. Immediate address operands are shown as symbol+offs.

Display raw instructions:
    $ sudo perf record --event intel_pt//u -- ls
    $ sudo perf script --insn-trace
                perf 17423 [000] 423271.557970005:      7f2d95f16217 __GI___ioctl+0x7 (/lib/x86_64-linux-gnu/libc-2.27.so) insn: 48 3d 01 f0 ff ff
                perf 17423 [000] 423271.557970005:      7f2d95f1621d __GI___ioctl+0xd (/lib/x86_64-linux-gnu/libc-2.27.so) insn: 73 01
                perf 17423 [000] 423271.557970338:      7f2d95f1621f __GI___ioctl+0xf (/lib/x86_64-linux-gnu/libc-2.27.so) insn: c3
                perf 17423 [000] 423271.557970338:      5593ad3346d7 perf_evsel__enable_cpu+0x97 (/work/linux/tools/perf/perf) insn: 85 c0
                perf 17423 [000] 423271.557970338:      5593ad3346d9 perf_evsel__enable_cpu+0x99 (/work/linux/tools/perf/perf) insn: 75 12
                perf 17423 [000] 423271.557970338:      5593ad3346db perf_evsel__enable_cpu+0x9b (/work/linux/tools/perf/perf) insn: 49 8b 84 24 a8 00 00 00
                perf 17423 [000] 423271.557970338:      5593ad3346e3 perf_evsel__enable_cpu+0xa3 (/work/linux/tools/perf/perf) insn: 48 8b 50 20

Display mnemonic instructions:
    $ sudo perf script --insn-trace=disam
                perf 17423 [000] 423271.557970005:      7f2d95f16217 __GI___ioctl+0x7 (/lib/x86_64-linux-gnu/libc-2.27.so) insn: cmpq $-0xfff, %rax
                perf 17423 [000] 423271.557970005:      7f2d95f1621d __GI___ioctl+0xd (/lib/x86_64-linux-gnu/libc-2.27.so) insn: jae __GI___ioctl+0x10
                perf 17423 [000] 423271.557970338:      7f2d95f1621f __GI___ioctl+0xf (/lib/x86_64-linux-gnu/libc-2.27.so) insn: retq
                perf 17423 [000] 423271.557970338:      5593ad3346d7 perf_evsel__enable_cpu+0x97 (/work/linux/tools/perf/perf) insn: testl %eax, %eax
                perf 17423 [000] 423271.557970338:      5593ad3346d9 perf_evsel__enable_cpu+0x99 (/work/linux/tools/perf/perf) insn: jne perf_evsel__enable_cpu+0xad
                perf 17423 [000] 423271.557970338:      5593ad3346db perf_evsel__enable_cpu+0x9b (/work/linux/tools/perf/perf) insn: movq 0xa8(%r12), %rax
                perf 17423 [000] 423271.557970338:      5593ad3346e3 perf_evsel__enable_cpu+0xa3 (/work/linux/tools/perf/perf) insn: movq 0x20(%rax), %rdx
                perf 17423 [000] 423271.557970338:      5593ad3346e7 perf_evsel__enable_cpu+0xa7 (/work/linux/tools/perf/perf) insn: cmpl %edx, %ebx
                perf 17423 [000] 423271.557970338:      5593ad3346e9 perf_evsel__enable_cpu+0xa9 (/work/linux/tools/perf/perf) insn: jl perf_evsel__enable_cpu+0x60
                perf 17423 [000] 423271.557970338:      5593ad3346eb perf_evsel__enable_cpu+0xab (/work/linux/tools/perf/perf) insn: xorl %eax, %eax

v2:
  - add a new field 'insn_disam' instead of changing the default output.
  - preserve the old --xed option.

Changbin Du (5):
  perf: build: introduce the libcapstone
  perf: util: use capstone disasm engine to show assembly instructions
  perf: script: add field 'insn_disam' to display mnemonic instructions
  perf: script: add raw|disam arguments to --insn-trace option
  perf: script: prefer capstone to XED

 tools/build/Makefile.feature               |   2 +
 tools/build/feature/Makefile               |   4 +
 tools/build/feature/test-all.c             |   4 +
 tools/build/feature/test-libcapstone.c     |  11 ++
 tools/perf/Documentation/perf-intel-pt.txt |  11 +-
 tools/perf/Documentation/perf-script.txt   |  13 ++-
 tools/perf/Makefile.config                 |  21 ++++
 tools/perf/Makefile.perf                   |   3 +
 tools/perf/builtin-script.c                |  33 ++++--
 tools/perf/ui/browsers/res_sample.c        |   2 +-
 tools/perf/ui/browsers/scripts.c           |   2 +-
 tools/perf/util/Build                      |   1 +
 tools/perf/util/print_insn.c               | 123 +++++++++++++++++++++
 tools/perf/util/print_insn.h               |  14 +++
 14 files changed, 220 insertions(+), 24 deletions(-)
 create mode 100644 tools/build/feature/test-libcapstone.c
 create mode 100644 tools/perf/util/print_insn.c
 create mode 100644 tools/perf/util/print_insn.h

-- 
2.25.1

[PATCH v2 1/5] perf: build: introduce the libcapstone

[Changbin Du]

Later we will use libcapstone to disassemble instructions of samples.

Signed-off-by: Changbin Du <changbin.du@huawei.com>
---
 tools/build/Makefile.feature           |  2 ++
 tools/build/feature/Makefile           |  4 ++++
 tools/build/feature/test-all.c         |  4 ++++
 tools/build/feature/test-libcapstone.c | 11 +++++++++++
 tools/perf/Makefile.config             | 21 +++++++++++++++++++++
 tools/perf/Makefile.perf               |  3 +++
 6 files changed, 45 insertions(+)
 create mode 100644 tools/build/feature/test-libcapstone.c

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 934e2777a2db..23bee50aeb0f 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -86,6 +86,7 @@ FEATURE_TESTS_EXTRA :=                  \
          gtk2-infobar                   \
          hello                          \
          libbabeltrace                  \
+         libcapstone                    \
          libbfd-liberty                 \
          libbfd-liberty-z               \
          libopencsd                     \
@@ -133,6 +134,7 @@ FEATURE_DISPLAY ?=              \
          libcrypto              \
          libunwind              \
          libdw-dwarf-unwind     \
+         libcapstone            \
          zlib                   \
          lzma                   \
          get_cpuid              \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index dad79ede4e0a..d6eaade09694 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -53,6 +53,7 @@ FILES=                                          \
          test-timerfd.bin                       \
          test-libdw-dwarf-unwind.bin            \
          test-libbabeltrace.bin                 \
+         test-libcapstone.bin			\
          test-compile-32.bin                    \
          test-compile-x32.bin                   \
          test-zlib.bin                          \
@@ -282,6 +283,9 @@ $(OUTPUT)test-libdw-dwarf-unwind.bin:
 $(OUTPUT)test-libbabeltrace.bin:
 	$(BUILD) # -lbabeltrace provided by $(FEATURE_CHECK_LDFLAGS-libbabeltrace)
 
+$(OUTPUT)test-libcapstone.bin:
+	$(BUILD) # -lcapstone provided by $(FEATURE_CHECK_LDFLAGS-libcapstone)
+
 $(OUTPUT)test-compile-32.bin:
 	$(CC) -m32 -o $@ test-compile.c
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 6f4bf386a3b5..dd0a18c2ef8f 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -134,6 +134,10 @@
 #undef main
 #endif
 
+#define main main_test_libcapstone
+# include "test-libcapstone.c"
+#undef main
+
 #define main main_test_lzma
 # include "test-lzma.c"
 #undef main
diff --git a/tools/build/feature/test-libcapstone.c b/tools/build/feature/test-libcapstone.c
new file mode 100644
index 000000000000..fbe8dba189e9
--- /dev/null
+++ b/tools/build/feature/test-libcapstone.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <capstone/capstone.h>
+
+int main(void)
+{
+	csh handle;
+
+	cs_open(CS_ARCH_X86, CS_MODE_64, &handle);
+	return 0;
+}
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b3e6ed10f40c..7589725ad178 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -191,6 +191,15 @@ endif
 FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
+# for linking with debug library, run like:
+# make DEBUG=1 LIBCAPSTONE_DIR=/opt/capstone/
+ifdef LIBCAPSTONE_DIR
+  LIBCAPSTONE_CFLAGS  := -I$(LIBCAPSTONE_DIR)/include
+  LIBCAPSTONE_LDFLAGS := -L$(LIBCAPSTONE_DIR)/
+endif
+FEATURE_CHECK_CFLAGS-libcapstone := $(LIBCAPSTONE_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libcapstone := $(LIBCAPSTONE_LDFLAGS) -lcapstone
+
 ifdef LIBZSTD_DIR
   LIBZSTD_CFLAGS  := -I$(LIBZSTD_DIR)/lib
   LIBZSTD_LDFLAGS := -L$(LIBZSTD_DIR)/lib
@@ -1089,6 +1098,18 @@ ifndef NO_LIBBABELTRACE
   endif
 endif
 
+ifndef NO_CAPSTONE
+  $(call feature_check,libcapstone)
+  ifeq ($(feature-libcapstone), 1)
+    CFLAGS += -DHAVE_LIBCAPSTONE_SUPPORT $(LIBCAPSTONE_CFLAGS)
+    LDFLAGS += $(LICAPSTONE_LDFLAGS)
+    EXTLIBS += -lcapstone
+    $(call detected,CONFIG_LIBCAPSTONE)
+  else
+    msg := $(warning No libcapstone found, disables disasm engine support for 'perf script', please install libcapstone-dev/capstone-devel);
+  endif
+endif
+
 ifndef NO_AUXTRACE
   ifeq ($(SRCARCH),x86)
     ifeq ($(feature-get_cpuid), 0)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 058c9aecf608..236da4f39a63 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -84,6 +84,9 @@ include ../scripts/utilities.mak
 # Define NO_LIBBABELTRACE if you do not want libbabeltrace support
 # for CTF data format.
 #
+# Define NO_CAPSTONE if you do not want libcapstone support
+# for disasm engine.
+#
 # Define NO_LZMA if you do not want to support compressed (xz) kernel modules
 #
 # Define NO_AUXTRACE if you do not want AUX area tracing support
-- 
2.25.1

[PATCH v2 2/5] perf: util: use capstone disasm engine to show assembly instructions

[Changbin Du]

Currently, the instructions of samples are shown as raw hex strings
which are hard to read. x86 has a special option '--xed' to disassemble
the hex string via intel XED tool.

Here we use capstone as our disassembler engine to give more friendly
instructions. We select libcapstone because capstone can provide more
insn details. Perf will fallback to raw instructions if libcapstone is
not available.

The advantages compared to XED tool:
 * Support arm, arm64, x86-32, x86_64 (more could be supported),
   xed only for x86_64.
 * Immediate address operands are shown as symbol+offs.

Signed-off-by: Changbin Du <changbin.du@huawei.com>
---
 tools/perf/builtin-script.c  |   8 +--
 tools/perf/util/Build        |   1 +
 tools/perf/util/print_insn.c | 123 +++++++++++++++++++++++++++++++++++
 tools/perf/util/print_insn.h |  14 ++++
 4 files changed, 141 insertions(+), 5 deletions(-)
 create mode 100644 tools/perf/util/print_insn.c
 create mode 100644 tools/perf/util/print_insn.h

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b1f57401ff23..4817a37f16e2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -34,6 +34,7 @@
 #include "util/event.h"
 #include "ui/ui.h"
 #include "print_binary.h"
+#include "print_insn.h"
 #include "archinsn.h"
 #include <linux/bitmap.h>
 #include <linux/kernel.h>
@@ -1511,11 +1512,8 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
 	if (PRINT_FIELD(INSNLEN))
 		printed += fprintf(fp, " ilen: %d", sample->insn_len);
 	if (PRINT_FIELD(INSN) && sample->insn_len) {
-		int i;
-
-		printed += fprintf(fp, " insn:");
-		for (i = 0; i < sample->insn_len; i++)
-			printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]);
+		printed += fprintf(fp, " insn: ");
+		printed += sample__fprintf_insn_raw(sample, fp);
 	}
 	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN))
 		printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 988473bf907a..c33aab53d8dd 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -32,6 +32,7 @@ perf-y += perf_regs.o
 perf-y += perf-regs-arch/
 perf-y += path.o
 perf-y += print_binary.o
+perf-y += print_insn.o
 perf-y += rlimit.o
 perf-y += argv_split.o
 perf-y += rbtree.o
diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c
new file mode 100644
index 000000000000..fe035efe8cf6
--- /dev/null
+++ b/tools/perf/util/print_insn.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Instruction binary disassembler based on capstone.
+ *
+ * Author(s): Changbin Du <changbin.du@huawei.com>
+ */
+#include "print_insn.h"
+#include <stdlib.h>
+#include <string.h>
+#include <stdbool.h>
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "machine.h"
+
+size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
+{
+	int printed = 0;
+
+	for (int i = 0; i < sample->insn_len; i++)
+		printed += fprintf(fp, "%02x ", (unsigned char)sample->insn[i]);
+	return printed;
+}
+
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+#include <capstone/capstone.h>
+
+static int capstone_init(struct machine *machine, csh *cs_handle)
+{
+	cs_arch arch;
+	cs_mode mode;
+
+	if (machine__is(machine, "x86_64")) {
+		arch = CS_ARCH_X86;
+		mode = CS_MODE_64;
+	} else if (machine__normalized_is(machine, "x86")) {
+		arch = CS_ARCH_X86;
+		mode = CS_MODE_32;
+	} else if (machine__normalized_is(machine, "arm64")) {
+		arch = CS_ARCH_ARM64;
+		mode = CS_MODE_ARM;
+	} else if (machine__normalized_is(machine, "arm")) {
+		arch = CS_ARCH_ARM;
+		mode = CS_MODE_ARM + CS_MODE_V8;
+	} else if (machine__normalized_is(machine, "s390x")) {
+		arch = CS_ARCH_SYSZ;
+		mode = CS_MODE_BIG_ENDIAN;
+	} else {
+		return -1;
+	}
+
+	if (cs_open(arch, mode, cs_handle) != CS_ERR_OK) {
+		pr_warning_once("cs_open failed\n");
+		return -1;
+	}
+
+	cs_option(*cs_handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT);
+	if (machine__normalized_is(machine, "x86"))
+		cs_option(*cs_handle, CS_OPT_DETAIL, CS_OPT_ON);
+
+	return 0;
+}
+
+static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,
+			     cs_insn *insn, FILE *fp)
+{
+	struct addr_location al;
+	size_t printed = 0;
+
+	if (insn->detail && insn->detail->x86.op_count == 1) {
+		cs_x86_op *op = &insn->detail->x86.operands[0];
+
+		addr_location__init(&al);
+
+		/* TODO: Add support for other ISAs */
+		if (op->type == X86_OP_IMM &&
+		    thread__find_symbol(thread, sample->cpumode, op->imm, &al)) {
+			printed += fprintf(fp, "%s ", insn[0].mnemonic);
+			printed += symbol__fprintf_symname_offs(al.sym, &al, fp);
+			return printed;
+		}
+	}
+
+	printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
+	return printed;
+}
+
+size_t sample__fprintf_insn(struct perf_sample *sample, struct thread *thread,
+			    struct machine *machine, FILE *fp)
+{
+	static csh cs_handle;
+	cs_insn *insn;
+	size_t count;
+	size_t printed = 0;
+	int ret;
+
+	ret = capstone_init(machine, &cs_handle);
+	if (ret < 0) {
+		/* fallback */
+		return sample__fprintf_insn_raw(sample, fp);
+	}
+
+	count = cs_disasm(cs_handle, (uint8_t *)sample->insn, sample->insn_len,
+			  sample->ip, 1, &insn);
+	if (count > 0) {
+		if (machine__normalized_is(machine, "x86"))
+			printed += print_insn_x86(sample, thread, &insn[0], fp);
+		else
+			printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
+		cs_free(insn, count);
+	} else {
+		printed += fprintf(fp, "illegal instruction");
+	}
+
+	cs_close(&cs_handle);
+	return printed;
+}
+#else
+size_t sample__fprintf_insn(struct perf_sample *sample, struct thread *thread __maybe_unused,
+			    struct machine *machine __maybe_unused, FILE *fp)
+{
+	return sample__fprintf_insn_raw(sample, fp);
+}
+#endif
diff --git a/tools/perf/util/print_insn.h b/tools/perf/util/print_insn.h
new file mode 100644
index 000000000000..af8fa5d01fb7
--- /dev/null
+++ b/tools/perf/util/print_insn.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_PRINT_ISNS_H
+#define PERF_PRINT_ISNS_H
+
+#include <stddef.h>
+#include <stdio.h>
+#include "event.h"
+#include "util/thread.h"
+
+size_t sample__fprintf_insn(struct perf_sample *sample, struct thread *thread,
+			    struct machine *machine, FILE *fp);
+size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp);
+
+#endif /* PERF_PRINT_ISNS_H */
-- 
2.25.1

[PATCH v2 3/5] perf: script: add field 'insn_disam' to display mnemonic instructions

[Changbin Du]

In addition to the 'insn' field, this adds a new field 'insn_disam' to
display mnemonic instructions instead of the raw code.

$ sudo perf script -F +insn_disam
       perf-exec 1443864 [006] 2275506.209848:          psb:  psb offs: 0                                      0 [unknown] ([unknown])
       perf-exec 1443864 [006] 2275506.209848:          cbr:  cbr: 41 freq: 4100 MHz (114%)                    0 [unknown] ([unknown])
              ls 1443864 [006] 2275506.209905:          1  branches:uH:      7f216b426100 _start+0x0 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: movq %rsp, %rdi
              ls 1443864 [006] 2275506.209908:          1  branches:uH:      7f216b426103 _start+0x3 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: callq _dl_start+0x0

Signed-off-by: Changbin Du <changbin.du@huawei.com>
---
 tools/perf/Documentation/perf-script.txt | 7 ++++---
 tools/perf/builtin-script.c              | 8 +++++++-
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index ff9a52e44688..1b0b62dd3145 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -132,9 +132,10 @@ OPTIONS
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, dsoff, addr, symoff,
         srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
-        brstackinsn, brstackinsnlen, brstackoff, callindent, insn, insnlen, synth,
-        phys_addr, metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat,
-        machine_pid, vcpu, cgroup, retire_lat.
+        brstackinsn, brstackinsnlen, brstackoff, callindent, insn, insn_disam,
+        insnlen, synth, phys_addr, metric, misc, srccode, ipc, data_page_size,
+        code_page_size, ins_lat, machine_pid, vcpu, cgroup, retire_lat.
+
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 4817a37f16e2..33f7dff6d066 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -135,6 +135,7 @@ enum perf_output_field {
 	PERF_OUTPUT_CGROUP          = 1ULL << 39,
 	PERF_OUTPUT_RETIRE_LAT      = 1ULL << 40,
 	PERF_OUTPUT_DSOFF           = 1ULL << 41,
+	PERF_OUTPUT_INSN_DISAM      = 1ULL << 42,
 };
 
 struct perf_script {
@@ -190,6 +191,7 @@ struct output_option {
 	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
 	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
+	{.str = "insn_disam", .field = PERF_OUTPUT_INSN_DISAM},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
 	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
 	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
@@ -1515,6 +1517,10 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
 		printed += fprintf(fp, " insn: ");
 		printed += sample__fprintf_insn_raw(sample, fp);
 	}
+	if (PRINT_FIELD(INSN_DISAM) && sample->insn_len) {
+		printed += fprintf(fp, " insn: ");
+		printed += sample__fprintf_insn(sample, thread, machine, fp);
+	}
 	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN))
 		printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
 
@@ -3900,7 +3906,7 @@ int cmd_script(int argc, const char **argv)
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff,"
 		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
 		     "brstacksym,flags,data_src,weight,bpf-output,brstackinsn,"
-		     "brstackinsnlen,brstackoff,callindent,insn,insnlen,synth,"
+		     "brstackinsnlen,brstackoff,callindent,insn,insn_disam,insnlen,synth,"
 		     "phys_addr,metric,misc,srccode,ipc,tod,data_page_size,"
 		     "code_page_size,ins_lat,machine_pid,vcpu,cgroup,retire_lat",
 		     parse_output_fields),
-- 
2.25.1

[PATCH v2 4/5] perf: script: add raw|disam arguments to --insn-trace option

[Changbin Du]

Now '--insn-trace' accept a argument to specify the output format:
  - raw: display raw instructions.
  - disam: display mnemonic instructions (if capstone is installed).

$ sudo perf script --insn-trace=raw
              ls 1443864 [006] 2275506.209908875:      7f216b426100 _start+0x0 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: 48 89 e7
              ls 1443864 [006] 2275506.209908875:      7f216b426103 _start+0x3 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: e8 e8 0c 00 00
              ls 1443864 [006] 2275506.209908875:      7f216b426df0 _dl_start+0x0 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: f3 0f 1e fa

$ sudo perf script --insn-trace=disam
              ls 1443864 [006] 2275506.209908875:      7f216b426100 _start+0x0 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: movq %rsp, %rdi
              ls 1443864 [006] 2275506.209908875:      7f216b426103 _start+0x3 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: callq _dl_start+0x0
              ls 1443864 [006] 2275506.209908875:      7f216b426df0 _dl_start+0x0 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: illegal instruction
              ls 1443864 [006] 2275506.209908875:      7f216b426df4 _dl_start+0x4 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: pushq %rbp
              ls 1443864 [006] 2275506.209908875:      7f216b426df5 _dl_start+0x5 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: movq %rsp, %rbp
              ls 1443864 [006] 2275506.209908875:      7f216b426df8 _dl_start+0x8 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) insn: pushq %r15

Signed-off-by: Changbin Du <changbin.du@huawei.com>
---
 tools/perf/Documentation/perf-script.txt |  6 +++---
 tools/perf/builtin-script.c              | 17 +++++++++++++----
 2 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 1b0b62dd3145..7061f607709c 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -442,9 +442,9 @@ include::itrace.txt[]
 	will be printed. Each entry has function name and file/line. Enabled by
 	default, disable with --no-inline.
 
---insn-trace::
-	Show instruction stream for intel_pt traces. Combine with --xed to
-	show disassembly.
+--insn-trace[=<raw|disam>]::
+	Show raw or mnemonic instruction stream for intel_pt traces. You can
+	also combine raw instructions with --xed to show disassembly.
 
 --xed::
 	Run xed disassembler on output. Requires installing the xed disassembler.
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 33f7dff6d066..01c83e45def1 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3769,10 +3769,19 @@ static int perf_script__process_auxtrace_info(struct perf_session *session,
 #endif
 
 static int parse_insn_trace(const struct option *opt __maybe_unused,
-			    const char *str __maybe_unused,
-			    int unset __maybe_unused)
+			    const char *str, int unset __maybe_unused)
 {
-	parse_output_fields(NULL, "+insn,-event,-period", 0);
+	const char *fields = "+insn,-event,-period";
+
+	if (str) {
+		if (strcmp(str, "disam") == 0)
+			fields = "+insn_disam,-event,-period";
+		else if (strlen(str) != 0 && strcmp(str, "raw") != 0) {
+			fprintf(stderr, "Only accept raw|disam\n");
+			return -EINVAL;
+		}
+	}
+	parse_output_fields(NULL, fields, 0);
 	itrace_parse_synth_opts(opt, "i0ns", 0);
 	symbol_conf.nanosecs = true;
 	return 0;
@@ -3918,7 +3927,7 @@ int cmd_script(int argc, const char **argv)
 		   "only consider these symbols"),
 	OPT_INTEGER(0, "addr-range", &symbol_conf.addr_range,
 		    "Use with -S to list traced records within address range"),
-	OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL,
+	OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, "raw|disam",
 			"Decode instructions from itrace", parse_insn_trace),
 	OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
 			"Run xed disassembler on output", parse_xed),
-- 
2.25.1

[PATCH v2 5/5] perf: script: prefer capstone to XED

[Changbin Du]

Now perf can show assembly instructions with libcapstone for x86, and the
capstone is better in general.

Signed-off-by: Changbin Du <changbin.du@huawei.com>
---
 tools/perf/Documentation/perf-intel-pt.txt | 11 +++++------
 tools/perf/ui/browsers/res_sample.c        |  2 +-
 tools/perf/ui/browsers/scripts.c           |  2 +-
 3 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 2109690b0d5f..13a02d568267 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -115,9 +115,8 @@ toggle respectively.
 
 perf script also supports higher level ways to dump instruction traces:
 
-	perf script --insn-trace --xed
+	perf script --insn-trace=disam
 
-Dump all instructions. This requires installing the xed tool (see XED below)
 Dumping all instructions in a long trace can be fairly slow. It is usually better
 to start with higher level decoding, like
 
@@ -130,12 +129,12 @@ or
 and then select a time range of interest. The time range can then be examined
 in detail with
 
-	perf script --time starttime,stoptime --insn-trace --xed
+	perf script --time starttime,stoptime --insn-trace=disam
 
 While examining the trace it's also useful to filter on specific CPUs using
 the -C option
 
-	perf script --time starttime,stoptime --insn-trace --xed -C 1
+	perf script --time starttime,stoptime --insn-trace=disam -C 1
 
 Dump all instructions in time range on CPU 1.
 
@@ -1306,7 +1305,7 @@ Without timestamps, --per-thread must be specified to distinguish threads.
 
 perf script can be used to provide an instruction trace
 
- $ perf script --guestkallsyms $KALLSYMS --insn-trace --xed -F+ipc | grep -C10 vmresume | head -21
+ $ perf script --guestkallsyms $KALLSYMS --insn-trace=disam -F+ipc | grep -C10 vmresume | head -21
        CPU 0/KVM  1440  ffffffff82133cdd __vmx_vcpu_run+0x3d ([kernel.kallsyms])                movq  0x48(%rax), %r9
        CPU 0/KVM  1440  ffffffff82133ce1 __vmx_vcpu_run+0x41 ([kernel.kallsyms])                movq  0x50(%rax), %r10
        CPU 0/KVM  1440  ffffffff82133ce5 __vmx_vcpu_run+0x45 ([kernel.kallsyms])                movq  0x58(%rax), %r11
@@ -1407,7 +1406,7 @@ There were none.
 
 'perf script' can be used to provide an instruction trace showing timestamps
 
- $ perf script -i perf.data.kvm --guestkallsyms $KALLSYMS --insn-trace --xed -F+ipc | grep -C10 vmresume | head -21
+ $ perf script -i perf.data.kvm --guestkallsyms $KALLSYMS --insn-trace=disam -F+ipc | grep -C10 vmresume | head -21
        CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133cdd __vmx_vcpu_run+0x3d ([kernel.kallsyms])                 movq  0x48(%rax), %r9
        CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133ce1 __vmx_vcpu_run+0x41 ([kernel.kallsyms])                 movq  0x50(%rax), %r10
        CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133ce5 __vmx_vcpu_run+0x45 ([kernel.kallsyms])                 movq  0x58(%rax), %r11
diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c
index 7cb2d6678039..0eb2029014a0 100644
--- a/tools/perf/ui/browsers/res_sample.c
+++ b/tools/perf/ui/browsers/res_sample.c
@@ -83,7 +83,7 @@ int res_sample_browse(struct res_sample *res_samples, int num_res,
 		     r->tid ? "--tid " : "",
 		     r->tid ? (sprintf(tidbuf, "%d", r->tid), tidbuf) : "",
 		     extra_format,
-		     rstype == A_ASM ? "-F +insn --xed" :
+		     rstype == A_ASM ? "-F +insn_disam" :
 		     rstype == A_SOURCE ? "-F +srcline,+srccode" : "",
 		     symbol_conf.inline_name ? "--inline" : "",
 		     "--show-lost-events ",
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index 47d2c7a8cbe1..a01b729f4ddc 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -107,7 +107,7 @@ static int list_scripts(char *script_name, bool *custom,
 	if (evsel)
 		attr_to_script(scriptc.extra_format, &evsel->core.attr);
 	add_script_option("Show individual samples", "", &scriptc);
-	add_script_option("Show individual samples with assembler", "-F +insn --xed",
+	add_script_option("Show individual samples with assembler", "-F +insn_disam",
 			  &scriptc);
 	add_script_option("Show individual samples with source", "-F +srcline,+srccode",
 			  &scriptc);
-- 
2.25.1

Re: [PATCH v2 2/5] perf: util: use capstone disasm engine to show assembly instructions

[Thomas Richter]

On 1/17/24 06:11, Changbin Du wrote:
> Currently, the instructions of samples are shown as raw hex strings
> which are hard to read. x86 has a special option '--xed' to disassemble
> the hex string via intel XED tool.
> 
> Here we use capstone as our disassembler engine to give more friendly
> instructions. We select libcapstone because capstone can provide more
> insn details. Perf will fallback to raw instructions if libcapstone is
> not available.
> 
> The advantages compared to XED tool:
>  * Support arm, arm64, x86-32, x86_64 (more could be supported),
>    xed only for x86_64.
>  * Immediate address operands are shown as symbol+offs.
> 
> Signed-off-by: Changbin Du <changbin.du@huawei.com>
> ---
>  tools/perf/builtin-script.c  |   8 +--
>  tools/perf/util/Build        |   1 +
>  tools/perf/util/print_insn.c | 123 +++++++++++++++++++++++++++++++++++
>  tools/perf/util/print_insn.h |  14 ++++
>  4 files changed, 141 insertions(+), 5 deletions(-)
>  create mode 100644 tools/perf/util/print_insn.c
>  create mode 100644 tools/perf/util/print_insn.h> 
...

> diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c
> new file mode 100644
> index 000000000000..fe035efe8cf6
> --- /dev/null
> +++ b/tools/perf/util/print_insn.c
> @@ -0,0 +1,123 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Instruction binary disassembler based on capstone.
> + *
> + * Author(s): Changbin Du <changbin.du@huawei.com>
> + */
> +#include "print_insn.h"
> +#include <stdlib.h>
> +#include <string.h>
> +#include <stdbool.h>
> +#include "util/debug.h"
> +#include "util/symbol.h"
> +#include "machine.h"
> +
> +size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
> +{
> +	int printed = 0;
> +
> +	for (int i = 0; i < sample->insn_len; i++)
> +		printed += fprintf(fp, "%02x ", (unsigned char)sample->insn[i]);
> +	return printed;
> +}
> +
> +#ifdef HAVE_LIBCAPSTONE_SUPPORT
> +#include <capstone/capstone.h>
> +
> +static int capstone_init(struct machine *machine, csh *cs_handle)
> +{
> +	cs_arch arch;
> +	cs_mode mode;
> +
> +	if (machine__is(machine, "x86_64")) {
> +		arch = CS_ARCH_X86;
> +		mode = CS_MODE_64;
> +	} else if (machine__normalized_is(machine, "x86")) {
> +		arch = CS_ARCH_X86;
> +		mode = CS_MODE_32;
> +	} else if (machine__normalized_is(machine, "arm64")) {
> +		arch = CS_ARCH_ARM64;
> +		mode = CS_MODE_ARM;
> +	} else if (machine__normalized_is(machine, "arm")) {
> +		arch = CS_ARCH_ARM;
> +		mode = CS_MODE_ARM + CS_MODE_V8;
> +	} else if (machine__normalized_is(machine, "s390x")) {

        } else if (machine__normalized_is(machine, "s390")) {                 

> +		arch = CS_ARCH_SYSZ;
> +		mode = CS_MODE_BIG_ENDIAN;
> +	} else {
> +		return -1;
> +	}

I have debugged your reworked patch this morning and discovered that
it was not working. The issue turned out to be function machine__normalized_is().
The first parameter is passed to several functions before the comparison.
The calls executed are

   machine__normhalized_is()
   +--> perf_env__arch() --> called for first parameter.
        +--> normalize_arch() --> always returns "s390"

We need to change the second parameter to "s390" without the trailing x
as indicated above. Sorry for the confusion.

Thanks a lot.
Thomas Richter, Dept 3303, IBM s390 Linux Development, Boeblingen, Germany
--
IBM Deutschland Research & Development GmbH

Vorsitzender des Aufsichtsrats: Wolfgang Wendt

Geschäftsführung: David Faller

Sitz der Gesellschaft: Böblingen / Registergericht: Amtsgericht Stuttgart, HRB 243294

Re: [PATCH v2 2/5] perf: util: use capstone disasm engine to show assembly instructions

[Changbin Du]

On Wed, Jan 17, 2024 at 09:54:59AM +0100, Thomas Richter wrote:
> On 1/17/24 06:11, Changbin Du wrote:
> > Currently, the instructions of samples are shown as raw hex strings
> > which are hard to read. x86 has a special option '--xed' to disassemble
> > the hex string via intel XED tool.
> > 
> > Here we use capstone as our disassembler engine to give more friendly
> > instructions. We select libcapstone because capstone can provide more
> > insn details. Perf will fallback to raw instructions if libcapstone is
> > not available.
> > 
> > The advantages compared to XED tool:
> >  * Support arm, arm64, x86-32, x86_64 (more could be supported),
> >    xed only for x86_64.
> >  * Immediate address operands are shown as symbol+offs.
> > 
> > Signed-off-by: Changbin Du <changbin.du@huawei.com>
> > ---
> >  tools/perf/builtin-script.c  |   8 +--
> >  tools/perf/util/Build        |   1 +
> >  tools/perf/util/print_insn.c | 123 +++++++++++++++++++++++++++++++++++
> >  tools/perf/util/print_insn.h |  14 ++++
> >  4 files changed, 141 insertions(+), 5 deletions(-)
> >  create mode 100644 tools/perf/util/print_insn.c
> >  create mode 100644 tools/perf/util/print_insn.h> 
> ...
> 
> > diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c
> > new file mode 100644
> > index 000000000000..fe035efe8cf6
> > --- /dev/null
> > +++ b/tools/perf/util/print_insn.c
> > @@ -0,0 +1,123 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * Instruction binary disassembler based on capstone.
> > + *
> > + * Author(s): Changbin Du <changbin.du@huawei.com>
> > + */
> > +#include "print_insn.h"
> > +#include <stdlib.h>
> > +#include <string.h>
> > +#include <stdbool.h>
> > +#include "util/debug.h"
> > +#include "util/symbol.h"
> > +#include "machine.h"
> > +
> > +size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
> > +{
> > +	int printed = 0;
> > +
> > +	for (int i = 0; i < sample->insn_len; i++)
> > +		printed += fprintf(fp, "%02x ", (unsigned char)sample->insn[i]);
> > +	return printed;
> > +}
> > +
> > +#ifdef HAVE_LIBCAPSTONE_SUPPORT
> > +#include <capstone/capstone.h>
> > +
> > +static int capstone_init(struct machine *machine, csh *cs_handle)
> > +{
> > +	cs_arch arch;
> > +	cs_mode mode;
> > +
> > +	if (machine__is(machine, "x86_64")) {
> > +		arch = CS_ARCH_X86;
> > +		mode = CS_MODE_64;
> > +	} else if (machine__normalized_is(machine, "x86")) {
> > +		arch = CS_ARCH_X86;
> > +		mode = CS_MODE_32;
> > +	} else if (machine__normalized_is(machine, "arm64")) {
> > +		arch = CS_ARCH_ARM64;
> > +		mode = CS_MODE_ARM;
> > +	} else if (machine__normalized_is(machine, "arm")) {
> > +		arch = CS_ARCH_ARM;
> > +		mode = CS_MODE_ARM + CS_MODE_V8;
> > +	} else if (machine__normalized_is(machine, "s390x")) {
> 
>         } else if (machine__normalized_is(machine, "s390")) {                 
> 
> > +		arch = CS_ARCH_SYSZ;
> > +		mode = CS_MODE_BIG_ENDIAN;
> > +	} else {
> > +		return -1;
> > +	}
> 
> I have debugged your reworked patch this morning and discovered that
> it was not working. The issue turned out to be function machine__normalized_is().
> The first parameter is passed to several functions before the comparison.
> The calls executed are
> 
>    machine__normhalized_is()
>    +--> perf_env__arch() --> called for first parameter.
>         +--> normalize_arch() --> always returns "s390"
> 
> We need to change the second parameter to "s390" without the trailing x
> as indicated above. Sorry for the confusion.
>
ok, will fix it later. Thanks.

> Thanks a lot.
> Thomas Richter, Dept 3303, IBM s390 Linux Development, Boeblingen, Germany
> --
> IBM Deutschland Research & Development GmbH
> 
> Vorsitzender des Aufsichtsrats: Wolfgang Wendt
> 
> Geschäftsführung: David Faller
> 
> Sitz der Gesellschaft: Böblingen / Registergericht: Amtsgericht Stuttgart, HRB 243294
> 

-- 
Cheers,
Changbin Du