[PATCH 1/4] perf, tools: Add support for skipping itrace instructions

[PATCH 1/4] perf, tools: Add support for skipping itrace instructions

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

When using perf script to look at PT traces it is often
useful to ignore the initialization code at the beginning.

On larger traces which may have many millions of instructions
in initialization code doing that in a pipeline can be very
slow, with perf script spending a lot of CPU time calling
printf and writing data.

This patch adds an extension to the --itrace argument
that skips 'n' events (instructions, branches or transactions)
at the beginning. This is much more efficient.

Cc: Adrian Hunter <adrian.hunter@intel.com>

v2:
Add support for BTS (Adrian Hunter)
Document in itrace.txt
Fix branch check
Check transactions and instructions too
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/intel-pt.txt |  7 +++++++
 tools/perf/Documentation/itrace.txt   |  8 ++++++++
 tools/perf/util/auxtrace.c            |  7 +++++++
 tools/perf/util/auxtrace.h            |  2 ++
 tools/perf/util/intel-bts.c           |  5 +++++
 tools/perf/util/intel-pt.c            | 22 ++++++++++++++++++++--
 6 files changed, 49 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index be764f9..c6c8318 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -672,6 +672,7 @@ The letters are:
 	d	create a debug log
 	g	synthesize a call chain (use with i or x)
 	l	synthesize last branch entries (use with i or x)
+	s	skip initial number of events
 
 "Instructions" events look like they were recorded by "perf record -e
 instructions".
@@ -730,6 +731,12 @@ from one sample to the next.
 
 To disable trace decoding entirely, use the option --no-itrace.
 
+It is also possible to skip events generated (instructions, branches, transactions)
+at the beginning. This is useful to ignore initialization code.
+
+	--itrace=i0nss1000000
+
+skips the first million instructions.
 
 dump option
 -----------
diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index 65453f4..e2a4c5e 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -7,6 +7,7 @@
 		d	create a debug log
 		g	synthesize a call chain (use with i or x)
 		l	synthesize last branch entries (use with i or x)
+		s       skip initial number of events
 
 	The default is all events i.e. the same as --itrace=ibxe
 
@@ -24,3 +25,10 @@
 
 	Also the number of last branch entries (default 64, max. 1024) for
 	instructions or transactions events can be specified.
+
+	It is also possible to skip events generated (instructions, branches, transactions)
+	at the beginning. This is useful to ignore initialization code.
+
+	--itrace=i0nss1000000
+
+	skips the first million instructions.
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index ec164fe..c916901 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -940,6 +940,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
 	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
 	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
 	synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
+	synth_opts->initial_skip = 0;
 }
 
 /*
@@ -1064,6 +1065,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				synth_opts->last_branch_sz = val;
 			}
 			break;
+		case 's':
+			synth_opts->initial_skip = strtoul(p, &endptr, 10);
+			if (p == endptr)
+				goto out_err;
+			p = endptr;
+			break;
 		case ' ':
 		case ',':
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index e5a8e2d..8214292 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -68,6 +68,7 @@ enum itrace_period_type {
  * @last_branch_sz: branch context size
  * @period: 'instructions' events period
  * @period_type: 'instructions' events period type
+ * @initial_skip: skip N events at the beginning.
  */
 struct itrace_synth_opts {
 	bool			set;
@@ -86,6 +87,7 @@ struct itrace_synth_opts {
 	unsigned int		last_branch_sz;
 	unsigned long long	period;
 	enum itrace_period_type	period_type;
+	unsigned long		initial_skip;
 };
 
 /**
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index eb0e7f8..e3cc105 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -66,6 +66,7 @@ struct intel_bts {
 	u64				branches_id;
 	size_t				branches_event_size;
 	bool				synth_needs_swap;
+	unsigned long			num_events;
 };
 
 struct intel_bts_queue {
@@ -275,6 +276,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	union perf_event event;
 	struct perf_sample sample = { .ip = 0, };
 
+	if (bts->synth_opts.initial_skip &&
+	    bts->num_events++ <= bts->synth_opts.initial_skip)
+		return 0;
+
 	event.sample.header.type = PERF_RECORD_SAMPLE;
 	event.sample.header.misc = PERF_RECORD_MISC_USER;
 	event.sample.header.size = sizeof(struct perf_event_header);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 05d8158..07f0020 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -100,6 +100,8 @@ struct intel_pt {
 	u64 cyc_bit;
 	u64 noretcomp_bit;
 	unsigned max_non_turbo_ratio;
+
+	unsigned long num_events;
 };
 
 enum switch_state {
@@ -972,6 +974,10 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
 		return 0;
 
+	if (pt->synth_opts.initial_skip &&
+	    pt->num_events++ < pt->synth_opts.initial_skip)
+		return 0;
+
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
 	event->sample.header.size = sizeof(struct perf_event_header);
@@ -1028,6 +1034,10 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 	union perf_event *event = ptq->event_buf;
 	struct perf_sample sample = { .ip = 0, };
 
+	if (pt->synth_opts.initial_skip &&
+	    pt->num_events++ < pt->synth_opts.initial_skip)
+		return 0;
+
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
 	event->sample.header.size = sizeof(struct perf_event_header);
@@ -1085,6 +1095,10 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 	union perf_event *event = ptq->event_buf;
 	struct perf_sample sample = { .ip = 0, };
 
+	if (pt->synth_opts.initial_skip &&
+	    pt->num_events++ < pt->synth_opts.initial_skip)
+		return 0;
+
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
 	event->sample.header.size = sizeof(struct perf_event_header);
@@ -1196,14 +1210,18 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	ptq->have_sample = false;
 
 	if (pt->sample_instructions &&
-	    (state->type & INTEL_PT_INSTRUCTION)) {
+	    (state->type & INTEL_PT_INSTRUCTION) &&
+	    (!pt->synth_opts.initial_skip ||
+	     pt->num_events++ >= pt->synth_opts.initial_skip)) {
 		err = intel_pt_synth_instruction_sample(ptq);
 		if (err)
 			return err;
 	}
 
 	if (pt->sample_transactions &&
-	    (state->type & INTEL_PT_TRANSACTION)) {
+	    (state->type & INTEL_PT_TRANSACTION) &&
+	    (!pt->synth_opts.initial_skip ||
+	     pt->num_events++ >= pt->synth_opts.initial_skip)) {
 		err = intel_pt_synth_transaction_sample(ptq);
 		if (err)
 			return err;
-- 
2.5.5

[PATCH 2/4] perf, tools: Add probing for udev86

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add autoprobing for the udev86 disassembler library.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/build/Makefile.feature      | 6 ++++--
 tools/build/feature/Makefile      | 8 ++++++--
 tools/build/feature/test-all.c    | 5 +++++
 tools/build/feature/test-udis86.c | 8 ++++++++
 tools/perf/config/Makefile        | 5 +++++
 5 files changed, 28 insertions(+), 4 deletions(-)
 create mode 100644 tools/build/feature/test-udis86.c

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 6b77072..db4f426 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -55,7 +55,8 @@ FEATURE_TESTS_BASIC :=			\
 	zlib				\
 	lzma				\
 	get_cpuid			\
-	bpf
+	bpf				\
+	udis86
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
 # of all feature tests
@@ -94,7 +95,8 @@ FEATURE_DISPLAY ?=			\
 	zlib				\
 	lzma				\
 	get_cpuid			\
-	bpf
+	bpf				\
+	udis86
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index c5f4c41..d05c312 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -36,7 +36,8 @@ FILES=					\
 	test-zlib.bin			\
 	test-lzma.bin			\
 	test-bpf.bin			\
-	test-get_cpuid.bin
+	test-get_cpuid.bin		\
+	test-udis86.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -51,7 +52,7 @@ __BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFL
 ###############################
 
 $(OUTPUT)test-all.bin:
-	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma
+	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -ludis86
 
 $(OUTPUT)test-hello.bin:
 	$(BUILD)
@@ -97,6 +98,9 @@ $(OUTPUT)test-numa_num_possible_cpus.bin:
 $(OUTPUT)test-libunwind.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-udis86.bin:
+	$(BUILD) -ludis86
+
 $(OUTPUT)test-libunwind-debug-frame.bin:
 	$(BUILD) -lelf
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index e499a36..76b0de3 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -133,6 +133,10 @@
 # include "test-libcrypto.c"
 #undef main
 
+#define main main_test_udis86
+#  include "test-udis86.c"
+#endif
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -163,6 +167,7 @@ int main(int argc, char *argv[])
 	main_test_get_cpuid();
 	main_test_bpf();
 	main_test_libcrypto();
+	main_test_udis86();
 
 	return 0;
 }
diff --git a/tools/build/feature/test-udis86.c b/tools/build/feature/test-udis86.c
new file mode 100644
index 0000000..623c545
--- /dev/null
+++ b/tools/build/feature/test-udis86.c
@@ -0,0 +1,8 @@
+#include <udis86.h>
+
+int main(void)
+{
+	ud_t ud;
+	ud_init(&ud);
+	return 0;
+}
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index f7aeaf3..970d800 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -580,6 +580,11 @@ ifneq ($(filter -lbfd,$(EXTLIBS)),)
   CFLAGS += -DHAVE_LIBBFD_SUPPORT
 endif
 
+ifeq ($(feature-udis86), 1)
+  CFLAGS += -DHAVE_UDIS86
+  EXTLIBS += -ludis86
+endif
+
 ifndef NO_ZLIB
   ifeq ($(feature-zlib), 1)
     CFLAGS += -DHAVE_ZLIB_SUPPORT
-- 
2.5.5

[PATCH 3/4] perf, tools, script: Add support for printing assembler

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

When dumping PT traces with perf script it is very useful to see the
assembler for each sample, so that it is easily possible to follow
the control flow.

As using objdump is difficult and inefficient from perf script this
patch uses the udis86 library to implement assembler output.
The library can be downloaded from http://udis86.sourceforge.net/

The library is probed as an external dependency in the usual way. Then perf
script calls into it when needed, and handles callbacks to resolve
symbols.

% perf record -e intel_pt//u true
% perf script -F sym,symoff,ip,asm --itrace=i0ns | head
     7fc7188b4190 _start+0x0	mov %rsp, %rdi
     7fc7188b4193 _start+0x3	call _dl_start
     7fc7188b7710 _dl_start+0x0	push %rbp
     7fc7188b7711 _dl_start+0x1	mov %rsp, %rbp
     7fc7188b7714 _dl_start+0x4	push %r15
     7fc7188b7716 _dl_start+0x6	push %r14
     7fc7188b7718 _dl_start+0x8	push %r13
     7fc7188b771a _dl_start+0xa	push %r12
     7fc7188b771c _dl_start+0xc	mov %rdi, %r12
     7fc7188b771f _dl_start+0xf	push %rbx

Current issues:
- Some jump references do not get resolved to symbols.
- udis86 release does not support STAC/CLAC, which are used in the kernel,
but there is a pending patch for it.

Cc: adrian.hunter@intel.com
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-script.txt |   4 +-
 tools/perf/builtin-script.c              | 108 +++++++++++++++++++++++++++++--
 2 files changed, 106 insertions(+), 6 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 382ddfb..c834f4d 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-	srcline, period, iregs, brstack, brstacksym, flags.
+	srcline, period, iregs, brstack, brstacksym, flags, asm.
         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
@@ -185,6 +185,8 @@ OPTIONS
 
 	The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
 
+	When asm is specified the assembler instruction of each sample is printed in disassembled form.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 57f9a7e..706ece8 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -25,6 +25,10 @@
 #include "asm/bug.h"
 #include "util/mem-events.h"
 
+#ifdef HAVE_UDIS86
+#include <udis86.h>
+#endif
+
 static char const		*script_name;
 static char const		*generate_script_lang;
 static bool			debug_mode;
@@ -62,6 +66,7 @@ enum perf_output_field {
 	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
 	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
+	PERF_OUTPUT_ASM		    = 1U << 20,
 };
 
 struct output_option {
@@ -88,6 +93,7 @@ struct output_option {
 	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
 	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
+	{.str = "asm", .field = PERF_OUTPUT_ASM},
 };
 
 /* default set to maintain compatibility with current format */
@@ -282,7 +288,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
 	}
-
+	if (PRINT_FIELD(ASM) && !PRINT_FIELD(IP)) {
+		pr_err("Display of assembler requested but sample IP is not\n"
+		       "selected.\n");
+		return -EINVAL;
+	}
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
 					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
@@ -423,6 +433,89 @@ static void print_sample_iregs(union perf_event *event __maybe_unused,
 	}
 }
 
+#ifdef HAVE_UDIS86
+
+struct perf_ud {
+	ud_t ud_obj;
+	struct thread *thread;
+	u8 cpumode;
+	int cpu;
+};
+
+static const char *dis_resolve(struct ud *u, uint64_t addr, int64_t *off)
+{
+	struct perf_ud *ud = container_of(u, struct perf_ud, ud_obj);
+	struct addr_location al;
+
+	memset(&al, 0, sizeof(struct addr_location));
+
+	thread__find_addr_map(ud->thread, ud->cpumode, MAP__FUNCTION, addr, &al);
+	if (!al.map)
+		thread__find_addr_map(ud->thread, ud->cpumode, MAP__VARIABLE,
+					addr, &al);
+	al.cpu = ud->cpu;
+	al.sym = NULL;
+
+	if (al.map)
+		al.sym = map__find_symbol(al.map, al.addr, NULL);
+
+	if (!al.sym)
+		return NULL;
+
+	if (addr < al.sym->end)
+		*off = addr - al.sym->start;
+	else
+		*off = addr - al.map->start - al.sym->start;
+	return al.sym->name;
+}
+#endif
+
+static void print_sample_asm(union perf_event *event __maybe_unused,
+			     struct perf_sample *sample __maybe_unused,
+			     struct thread *thread __maybe_unused,
+			     struct perf_event_attr *attr __maybe_unused,
+			     struct addr_location *al __maybe_unused,
+			     struct machine *machine __maybe_unused)
+{
+#ifdef HAVE_UDIS86
+	static bool ud_initialized = false;
+	static struct perf_ud ud;
+	u8 buffer[32];
+	int len;
+	u64 offset;
+
+	if (!ud_initialized) {
+		ud_initialized = true;
+		ud_init(&ud.ud_obj);
+		ud_set_syntax(&ud.ud_obj, UD_SYN_ATT);
+		ud_set_sym_resolver(&ud.ud_obj, dis_resolve);
+	}
+	ud.thread = thread;
+	ud.cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	ud.cpu = sample->cpu;
+
+	if (!al->map || !al->map->dso)
+		return;
+	if (al->map->dso->data.status == DSO_DATA_STATUS_ERROR)
+		return;
+
+	/* Load maps to ensure dso->is_64_bit has been updated */
+	map__load(al->map, machine->symbol_filter);
+
+	offset = al->map->map_ip(al->map, sample->ip);
+	len = dso__data_read_offset(al->map->dso, machine,
+				    offset, buffer, 32);
+	if (len <= 0)
+		return;
+
+	ud_set_mode(&ud.ud_obj, al->map->dso->is_64_bit ? 64 : 32);
+	ud_set_pc(&ud.ud_obj, sample->ip);
+	ud_set_input_buffer(&ud.ud_obj, buffer, len);
+	ud_disassemble(&ud.ud_obj);
+	printf("\t%s", ud_insn_asm(&ud.ud_obj));
+#endif
+}
+
 static void print_sample_start(struct perf_sample *sample,
 			       struct thread *thread,
 			       struct perf_evsel *evsel)
@@ -749,7 +842,8 @@ static size_t data_src__printf(u64 data_src)
 
 static void process_event(struct perf_script *script, union perf_event *event,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
-			  struct addr_location *al)
+			  struct addr_location *al,
+			  struct machine *machine)
 {
 	struct thread *thread = al->thread;
 	struct perf_event_attr *attr = &evsel->attr;
@@ -777,7 +871,7 @@ static void process_event(struct perf_script *script, union perf_event *event,
 
 	if (is_bts_event(attr)) {
 		print_sample_bts(event, sample, evsel, thread, al);
-		return;
+		goto print_rest;
 	}
 
 	if (PRINT_FIELD(TRACE))
@@ -806,6 +900,7 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	if (PRINT_FIELD(IREGS))
 		print_sample_iregs(event, sample, thread, attr);
 
+print_rest:
 	if (PRINT_FIELD(BRSTACK))
 		print_sample_brstack(event, sample, thread, attr);
 	else if (PRINT_FIELD(BRSTACKSYM))
@@ -814,6 +909,9 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
 
+	if (PRINT_FIELD(ASM))
+		print_sample_asm(event, sample, thread, attr, al, machine);
+
 	printf("\n");
 }
 
@@ -920,7 +1018,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (scripting_ops)
 		scripting_ops->process_event(event, sample, evsel, &al);
 	else
-		process_event(scr, event, sample, evsel, &al);
+		process_event(scr, event, sample, evsel, &al, machine);
 
 out_put:
 	addr_location__put(&al);
@@ -2020,7 +2118,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period,iregs,brstack,brstacksym,flags", parse_output_fields),
+		     "addr,symoff,period,iregs,brstack,brstacksym,flags,asm", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
-- 
2.5.5

[PATCH 4/4] perf, tools, script: Add brstackasm output for branch stacks

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Implement printing full disassembled sequences for branch stacks in perf
script. This allows to directly print hot paths for individual samples,
together with branch misprediction and even cycle count information.

% perf record -b ...
% perf script -F brstackasm
...
        00007f0668d54e88        movsx (%rsi), %ecx
        00007f0668d54e8b        lea -0x30(%rcx), %eax
        00007f0668d54e8e        cmp $0x9, %al
        00007f0668d54e90        jbe 0x68d54eaf
        00007f0668d54e92        cmp %cl, %dl
        00007f0668d54e94        jnz 0x68d54eb5
        00007f0668d54e96        add $0x1, %rdi
        00007f0668d54e9a        movsx (%rdi), %edx
        00007f0668d54e9d        add $0x1, %rsi
        00007f0668d54ea1        test %dl, %dl
        00007f0668d54ea3        jnz _dl_cache_libcmp+11       # PRED 21 cycles
        00007f0668d54dfb        lea -0x30(%rdx), %eax
        00007f0668d54dfe        cmp $0x9, %al
        00007f0668d54e00        ja _dl_cache_libcmp+152       # PRED 2 cycles
        00007f0668d54e88        movsx (%rsi), %ecx
        00007f0668d54e8b        lea -0x30(%rcx), %eax
        00007f0668d54e8e        cmp $0x9, %al
        00007f0668d54e90        jbe 0x68d54eaf
        00007f0668d54e92        cmp %cl, %dl
        00007f0668d54e94        jnz 0x68d54eb5                # PRED 3 cycles
        00007f0668d54eb5        movsx %dl, %eax
        00007f0668d54eb8        sub %ecx, %eax
        00007f0668d54eba        ret                           # PRED 1 cycles
        00007f0668d54fae        test %eax, %eax
        00007f0668d54fb0        jz _dl_load_cache_lookup+688
        00007f0668d54fb6        jns 0x68d54f70
        00007f0668d54fb8        lea 0x1(%r14), %ebx
        00007f0668d54fbc        cmp %r15d, %ebx
        00007f0668d54fbf        nop
        00007f0668d54fc0        jle 0x68d54f79                # PRED 2 cycles

Open issues:
- Occasionally the path does not reach up to the sample IP, as the LBRs
may be freezed earlier.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-script.txt |   9 +-
 tools/perf/builtin-script.c              | 191 ++++++++++++++++++++++++++++++-
 2 files changed, 195 insertions(+), 5 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index c834f4d..4a30f02 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-	srcline, period, iregs, brstack, brstacksym, flags, asm.
+	srcline, period, iregs, brstack, brstacksym, flags, asm, brstackasm
         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
@@ -176,17 +176,22 @@ OPTIONS
 	i.e., -f "" is not allowed.
 
 	The brstack output includes branch related information with raw addresses using the
-	/v/v/v/v/ syntax in the following order:
+	/v/v/v/v/cycles syntax in the following order:
 	FROM: branch source instruction
 	TO  : branch target instruction
         M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported
 	X/- : X=branch inside a transactional region, -=not in transaction region or not supported
 	A/- : A=TSX abort entry, -=not aborted region or not supported
+	cycles
 
 	The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
 
 	When asm is specified the assembler instruction of each sample is printed in disassembled form.
 
+	When brstackasm is specified the full assembler sequences of branch sequences for each sample
+	is printed. This is the full execution path leading to the sample. This is only supported when the
+	sample was recorded with perf record -b or -j any.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 706ece8..766242b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -42,6 +42,7 @@ static bool			nanosecs;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 static struct perf_stat_config	stat_config;
+static int 			max_blocks;
 
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
 
@@ -67,6 +68,7 @@ enum perf_output_field {
 	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
 	PERF_OUTPUT_ASM		    = 1U << 20,
+	PERF_OUTPUT_BRSTACKASM	    = 1U << 21,
 };
 
 struct output_option {
@@ -94,6 +96,7 @@ struct output_option {
 	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
 	{.str = "asm", .field = PERF_OUTPUT_ASM},
+	{.str = "brstackasm", .field = PERF_OUTPUT_BRSTACKASM},
 };
 
 /* default set to maintain compatibility with current format */
@@ -293,6 +296,13 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected.\n");
 		return -EINVAL;
 	}
+	if (PRINT_FIELD(BRSTACKASM) &&
+	    !(perf_evlist__combined_branch_type(session->evlist) &
+	      PERF_SAMPLE_BRANCH_ANY)) {
+		pr_err("Display of branch stack assembler requested, but non all-branch filter set\n");
+		return -EINVAL;
+	}
+
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
 					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
@@ -462,10 +472,10 @@ static const char *dis_resolve(struct ud *u, uint64_t addr, int64_t *off)
 	if (!al.sym)
 		return NULL;
 
-	if (addr < al.sym->end)
-		*off = addr - al.sym->start;
+	if (al.addr < al.sym->end)
+		*off = al.addr - al.sym->start;
 	else
-		*off = addr - al.map->start - al.sym->start;
+		*off = al.addr - al.map->start - al.sym->start;
 	return al.sym->name;
 }
 #endif
@@ -630,6 +640,176 @@ static void print_sample_brstacksym(union perf_event *event __maybe_unused,
 	}
 }
 
+#ifdef HAVE_UDIS86
+#define MAXBB 16384UL
+#define MAXINSN 16
+
+static int grab_bb(char *buffer, u64 start, u64 end,
+		    struct machine *machine, struct thread *thread,
+		    bool *is64bit, u8 *cpumode)
+{
+	int offset, len;
+	struct addr_location al;
+	bool kernel;
+
+	if (!start || !end)
+		return 0;
+
+	kernel = machine__kernel_ip(machine, start);
+	if (kernel)
+		*cpumode = PERF_RECORD_MISC_KERNEL;
+	else
+		*cpumode = PERF_RECORD_MISC_USER;
+	if (kernel != machine__kernel_ip(machine, end))
+		return 0;
+
+	memset(&al, 0, sizeof(al));
+	if (end - start > MAXBB - MAXINSN) {
+		pr_debug("\tbasic block %" PRIx64 "-%" PRIx64 " (%ld) too long to dump\n",
+		       start, end, end - start);
+		return 0;
+	}
+
+	thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
+	if (!al.map || !al.map->dso) {
+		printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n",
+				start, end);
+		return 0;
+	}
+	if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) {
+		printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n",
+				start, end);
+		return 0;
+	}
+
+	/* Load maps to ensure dso->is_64_bit has been updated */
+	map__load(al.map, machine->symbol_filter);
+
+	offset = al.map->map_ip(al.map, start);
+	len = dso__data_read_offset(al.map->dso, machine,
+				    offset, (u8 *)buffer,
+				    end - start + MAXINSN);
+
+	*is64bit = al.map->dso->is_64_bit;
+	return len;
+}
+#endif
+
+static void print_sample_brstackasm(union perf_event *event __maybe_unused,
+				    struct perf_sample *sample,
+				    struct thread *thread __maybe_unused,
+				    struct perf_event_attr *attr __maybe_unused,
+				    struct machine *machine __maybe_unused)
+{
+#ifdef HAVE_UDIS86
+	struct branch_stack *br = sample->branch_stack;
+	u64 start, end;
+	int i;
+	static bool ud_initialized = false;
+	static struct perf_ud ud;
+	char buffer[MAXBB];
+	int len;
+	bool last;
+	bool is64bit;
+	int nr;
+
+	if (!(br && br->nr))
+		return;
+	nr = br->nr;
+	if (max_blocks && nr > max_blocks + 1)
+		nr = max_blocks + 1;
+
+	if (!ud_initialized) {
+		ud_initialized = true;
+		ud_init(&ud.ud_obj);
+		ud_set_syntax(&ud.ud_obj, UD_SYN_ATT);
+		ud_set_sym_resolver(&ud.ud_obj, dis_resolve);
+	}
+	ud.thread = thread;
+	ud.cpu = sample->cpu;
+
+	putchar('\n');
+	for (i = nr - 2; i >= 0; i--) {
+		if (br->entries[i].from || br->entries[i].to)
+			printf("%d: %lx-%lx\n", i,
+				br->entries[i].from,
+				br->entries[i].to);
+		start = br->entries[i + 1].to;
+		end = br->entries[i].from;
+
+		/*
+		 * Leave extra bytes for the final jump instruction for
+		 * which we don't know the length
+		 */
+		len = grab_bb(buffer, start, end + MAXINSN,
+				machine, thread, &is64bit,
+				&ud.cpumode);
+		if (len <= 0)
+			continue;
+
+		ud_set_mode(&ud.ud_obj, is64bit ? 64 : 32);
+		ud_set_pc(&ud.ud_obj, start);
+		ud_set_input_buffer(&ud.ud_obj, (uint8_t *)buffer, len);
+		last = false;
+		while (ud_disassemble(&ud.ud_obj) && !last) {
+			if (ud_insn_ptr(&ud.ud_obj) ==
+					(uint8_t *)buffer + end - start) {
+				printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s\n",
+					ud_insn_off(&ud.ud_obj),
+					ud_insn_asm(&ud.ud_obj),
+					br->entries[i].flags.predicted ? " PRED" : "",
+					br->entries[i].flags.mispred ? " MISPRED" : "",
+					br->entries[i].flags.in_tx ? " INTX" : "",
+					br->entries[i].flags.abort ? " ABORT" : "");
+				if (br->entries[i].flags.cycles)
+					printf(" %d cycles", br->entries[i].flags.cycles);
+				last = true;
+			} else {
+				printf("\t%016" PRIx64 "\t%s\n",
+						ud_insn_off(&ud.ud_obj),
+					ud_insn_asm(&ud.ud_obj));
+			}
+		}
+	}
+
+	/*
+	 * Hit the branch? In this case we are already done, and the target
+	 * has not been executed yet.
+	 */
+	if (br->entries[0].from == sample->ip)
+		return;
+	if (br->entries[0].flags.abort)
+		return;
+
+	/*
+	 * Print final block upto sample
+	 */
+	start = br->entries[0].to;
+	end = sample->ip;
+	len = grab_bb(buffer, start, end, machine, thread, &is64bit,
+			&ud.cpumode);
+	ud_set_input_buffer(&ud.ud_obj, (uint8_t *)buffer, len);
+	if (len <= 0) {
+		/* Print at least last IP if basic block did not work */
+		len = grab_bb(buffer, sample->ip, sample->ip + MAXINSN,
+				machine, thread, &is64bit, &ud.cpumode);
+		if (len <= 0)
+			return;
+		ud_set_mode(&ud.ud_obj, is64bit ? 64 : 32);
+		ud_set_pc(&ud.ud_obj, sample->ip);
+		if (ud_disassemble(&ud.ud_obj))
+			printf("\t%016" PRIx64 "\t%s\n", ud_insn_off(&ud.ud_obj),
+			       ud_insn_asm(&ud.ud_obj));
+		return;
+	}
+	ud_set_mode(&ud.ud_obj, is64bit ? 64 : 32);
+	ud_set_pc(&ud.ud_obj, start);
+	while (ud_disassemble(&ud.ud_obj) &&
+		ud_insn_ptr(&ud.ud_obj) <= (uint8_t *)buffer + end - start)
+		printf("\t%016" PRIx64 "\t%s\n", ud_insn_off(&ud.ud_obj),
+			       ud_insn_asm(&ud.ud_obj));
+#endif
+}
 
 static void print_sample_addr(union perf_event *event,
 			  struct perf_sample *sample,
@@ -909,6 +1089,9 @@ print_rest:
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
 
+	if (PRINT_FIELD(BRSTACKASM))
+		print_sample_brstackasm(event, sample, thread, attr,
+					machine);
 	if (PRINT_FIELD(ASM))
 		print_sample_asm(event, sample, thread, attr, al, machine);
 
@@ -2140,6 +2323,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show the mmap events"),
 	OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
 		    "Show context switch events (if recorded)"),
+	OPT_INTEGER(0, "max-blocks", &max_blocks,
+		    "Maximum number of code blocks to dump with brstackasm"),
 	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
-- 
2.5.5

Re: [PATCH 3/4] perf, tools, script: Add support for printing assembler

[Jiri Olsa]

On Fri, Mar 25, 2016 at 04:02:37PM -0700, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> When dumping PT traces with perf script it is very useful to see the
> assembler for each sample, so that it is easily possible to follow
> the control flow.
> 
> As using objdump is difficult and inefficient from perf script this
> patch uses the udis86 library to implement assembler output.
> The library can be downloaded from http://udis86.sourceforge.net/
> 
> The library is probed as an external dependency in the usual way. Then perf
> script calls into it when needed, and handles callbacks to resolve
> symbols.
> 
> % perf record -e intel_pt//u true
> % perf script -F sym,symoff,ip,asm --itrace=i0ns | head
>      7fc7188b4190 _start+0x0	mov %rsp, %rdi
>      7fc7188b4193 _start+0x3	call _dl_start
>      7fc7188b7710 _dl_start+0x0	push %rbp
>      7fc7188b7711 _dl_start+0x1	mov %rsp, %rbp
>      7fc7188b7714 _dl_start+0x4	push %r15
>      7fc7188b7716 _dl_start+0x6	push %r14
>      7fc7188b7718 _dl_start+0x8	push %r13
>      7fc7188b771a _dl_start+0xa	push %r12
>      7fc7188b771c _dl_start+0xc	mov %rdi, %r12
>      7fc7188b771f _dl_start+0xf	push %rbx
> 
> Current issues:
> - Some jump references do not get resolved to symbols.
> - udis86 release does not support STAC/CLAC, which are used in the kernel,
> but there is a pending patch for it.

can't apply this on latest Arnaldo's tree:

patching file Documentation/perf-script.txt
patching file builtin-script.c
Hunk #5 succeeded at 431 (offset -2 lines).
Hunk #6 succeeded at 832 with fuzz 2 (offset -10 lines).
Hunk #7 FAILED at 871.
Hunk #8 succeeded at 890 with fuzz 2 (offset -10 lines).
Hunk #9 succeeded at 899 (offset -10 lines).
Hunk #10 FAILED at 1018.
Hunk #11 succeeded at 2108 (offset -10 lines).
2 out of 11 hunks FAILED -- saving rejects to file builtin-script.c.rej


jirka

Re: [PATCH 2/4] perf, tools: Add probing for udev86

[Jiri Olsa]

On Fri, Mar 25, 2016 at 04:02:36PM -0700, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Add autoprobing for the udev86 disassembler library.
> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>

Acked-by: Jiri Olsa <jolsa@kernel.org>

thanks,
jirka

Re: [PATCH 3/4] perf, tools, script: Add support for printing assembler

[Andi Kleen]

> > Current issues:
> > - Some jump references do not get resolved to symbols.
> > - udis86 release does not support STAC/CLAC, which are used in the kernel,
> > but there is a pending patch for it.
> 
> can't apply this on latest Arnaldo's tree:

This is due to which is only in Arnaldo's tree

commit a3dff304ca50cbfbe3f0e76ee49c439990932ed5
Author: Arnaldo Carvalho de Melo <acme@redhat.com>
Date:   Wed Mar 23 11:55:24 2016 -0300

    perf script: Remove lots of unused arguments
        
But the asm printer actually needs the "event" argument,
so that change would break my patchkit.

Arnaldo, can you undo the patch or at least keep "event" ?

-Andi

[PATCH 3/4] perf, tools, script: Add support for printing assembler

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

When dumping PT traces with perf script it is very useful to see the
assembler for each sample, so that it is easily possible to follow
the control flow.

As using objdump is difficult and inefficient from perf script this
patch uses the Intel xed library to implement assembler output.
The library can be downloaded from http://github.com/intelxed/xed

The previous version of this patch used udis86, but was
rejected because udis86 was unmaintained and a runtime dependency.
Using the recently released xed avoids both of these problems:
- XED is well maintained and used by many Intel tools
- XED is linked statically so there is no runtime dependency.

The library is probed as an external dependency in the usual way. Then perf
script calls into it when needed, and handles callbacks to resolve
symbols.

% perf record -e intel_pt//u true
% perf script -F sym,symoff,ip,asm --itrace=i0ns | head
     7fc7188b4190 _start+0x0	mov %rsp, %rdi
     7fc7188b4193 _start+0x3	call _dl_start
     7fc7188b7710 _dl_start+0x0	push %rbp
     7fc7188b7711 _dl_start+0x1	mov %rsp, %rbp
     7fc7188b7714 _dl_start+0x4	push %r15
     7fc7188b7716 _dl_start+0x6	push %r14
     7fc7188b7718 _dl_start+0x8	push %r13
     7fc7188b771a _dl_start+0xa	push %r12
     7fc7188b771c _dl_start+0xc	mov %rdi, %r12
     7fc7188b771f _dl_start+0xf	push %rbx

v2:
Converted to use XED instead of udis86.
Separate disassembler interface into separate arch specific file.
Lots of cleanups and improvements.

Cc: adrian.hunter@intel.com
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-script.txt |  4 +-
 tools/perf/builtin-script.c              | 72 +++++++++++++++++++++++++++-----
 2 files changed, 64 insertions(+), 12 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5dc5c6a09ac4..863579b4d2e2 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,7 +116,7 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, asm.
         callindent, insn, insnlen. 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
@@ -198,6 +198,8 @@ OPTIONS
 
 	The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
 
+	When asm is specified the assembler instruction of each sample is printed in disassembled form.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2f3ff69fc4e7..e96668b1cc63 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -28,6 +28,7 @@
 #include <linux/time64.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
+#include "util/dis.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -69,6 +70,7 @@ enum perf_output_field {
 	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
 	PERF_OUTPUT_INSN	    = 1U << 21,
 	PERF_OUTPUT_INSNLEN	    = 1U << 22,
+	PERF_OUTPUT_ASM		    = 1U << 23,
 };
 
 struct output_option {
@@ -98,6 +100,7 @@ struct output_option {
 	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
+	{.str = "asm", .field = PERF_OUTPUT_ASM},
 };
 
 /* default set to maintain compatibility with current format */
@@ -292,7 +295,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
 	}
-
+	if (PRINT_FIELD(ASM) && !PRINT_FIELD(IP)) {
+		pr_err("Display of assembler requested but sample IP is not\n"
+		       "selected.\n");
+		return -EINVAL;
+	}
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
 					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
@@ -436,6 +443,39 @@ static void print_sample_iregs(struct perf_sample *sample,
 	}
 }
 
+static void print_sample_asm(union perf_event *event,
+			     struct perf_sample *sample,
+			     struct thread *thread,
+			     struct addr_location *al,
+			     struct machine *machine)
+{
+	struct perf_dis x;
+	u8 buffer[32];
+	int len;
+	u64 offset;
+
+	x.thread = thread;
+	x.cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	x.cpu = sample->cpu;
+
+	if (!al->map || !al->map->dso)
+		return;
+	if (al->map->dso->data.status == DSO_DATA_STATUS_ERROR)
+		return;
+
+	/* Load maps to ensure dso->is_64_bit has been updated */
+	map__load(al->map);
+	x.is64bit = al->map->dso->is_64_bit;
+
+	offset = al->map->map_ip(al->map, sample->ip);
+	len = dso__data_read_offset(al->map->dso, machine,
+				    offset, buffer, MAXINSN);
+	if (len <= 0)
+		return;
+
+	printf("\t%s", disas_inst(&x, sample->ip, buffer, len, NULL));
+}
+
 static void print_sample_start(struct perf_sample *sample,
 			       struct thread *thread,
 			       struct perf_evsel *evsel)
@@ -631,8 +671,12 @@ static void print_sample_callindent(struct perf_sample *sample,
 		printf("%*s", spacing - len, "");
 }
 
-static void print_insn(struct perf_sample *sample,
-		       struct perf_event_attr *attr)
+static void print_insn(union perf_event *event,
+		       struct perf_sample *sample,
+		       struct perf_event_attr *attr,
+		       struct thread *thread,
+		       struct addr_location *al,
+		       struct machine *machine)
 {
 	if (PRINT_FIELD(INSNLEN))
 		printf(" ilen: %d", sample->insn_len);
@@ -643,12 +687,16 @@ static void print_insn(struct perf_sample *sample,
 		for (i = 0; i < sample->insn_len; i++)
 			printf(" %02x", (unsigned char)sample->insn[i]);
 	}
+	if (PRINT_FIELD(ASM))
+		print_sample_asm(event, sample, thread, al, machine);
 }
 
-static void print_sample_bts(struct perf_sample *sample,
+static void print_sample_bts(union perf_event *event,
+			     struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
-			     struct addr_location *al)
+			     struct addr_location *al,
+			     struct machine *machine)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	bool print_srcline_last = false;
@@ -689,7 +737,7 @@ static void print_sample_bts(struct perf_sample *sample,
 	if (print_srcline_last)
 		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 
-	print_insn(sample, attr);
+	print_insn(event, sample, attr, thread, al, machine);
 
 	printf("\n");
 }
@@ -871,7 +919,9 @@ static size_t data_src__printf(u64 data_src)
 
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
-			  struct addr_location *al)
+			  struct addr_location *al,
+			  struct machine *machine,
+			  union perf_event *event)
 {
 	struct thread *thread = al->thread;
 	struct perf_event_attr *attr = &evsel->attr;
@@ -898,7 +948,7 @@ static void process_event(struct perf_script *script,
 		print_sample_flags(sample->flags);
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(sample, evsel, thread, al);
+		print_sample_bts(event, sample, evsel, thread, al, machine);
 		return;
 	}
 
@@ -936,7 +986,7 @@ static void process_event(struct perf_script *script,
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
-	print_insn(sample, attr);
+	print_insn(event, sample, attr, thread, al, machine);
 	printf("\n");
 }
 
@@ -1046,7 +1096,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (scripting_ops)
 		scripting_ops->process_event(event, sample, evsel, &al);
 	else
-		process_event(scr, sample, evsel, &al);
+		process_event(scr, sample, evsel, &al, machine, event);
 
 out_put:
 	addr_location__put(&al);
@@ -2152,7 +2202,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen", parse_output_fields),
+		     "bpf-output,callindent,insn,insnlen,asm", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
-- 
2.9.3