perf script: Support insn and insnlen

When looking at Intel PT traces with perf script it is useful to have
some indication of the instruction. Dump the instruction bytes and
instruction length, which can be used for simple pattern analysis in
scripts.

% perf record -e intel_pt// foo
% perf script --itrace=i0ns -F ip,insn,insnlen
 ffffffff8101232f ilen: 5 insn: 0f 1f 44 00 00
 ffffffff81012334 ilen: 1 insn: 5b
 ffffffff81012335 ilen: 1 insn: 5d
 ffffffff81012336 ilen: 1 insn: c3
 ffffffff810123e3 ilen: 1 insn: 5b
 ffffffff810123e4 ilen: 2 insn: 41 5c
 ffffffff810123e6 ilen: 1 insn: 5d
 ffffffff810123e7 ilen: 1 insn: c3
 ffffffff810124a6 ilen: 2 insn: 31 c0
 ffffffff810124a8 ilen: 9 insn: 41 83 bc 24 a8 01 00 00 01
 ffffffff810124b1 ilen: 2 insn: 75 87
...

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/r/1475847747-30994-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-script.txt

@@ -117,7 +117,7 @@ OPTIONS
         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,
-        callindent. Field list can be prepended with the type, trace, sw or hw,
+        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
 
@@ -181,6 +181,10 @@ OPTIONS
 	Instruction Trace decoding. For calls and returns, it will display the
 	name of the symbol indented with spaces to reflect the stack depth.
 
+	When doing instruction trace decoding insn and insnlen give the
+	instruction bytes and the instruction length of the current
+	instruction.
+
 	Finally, a user may not set fields to none for all event types.
 	i.e., -F "" is not allowed.
 

tools/perf/builtin-script.c

@@ -66,6 +66,8 @@ enum perf_output_field {
 	PERF_OUTPUT_WEIGHT	    = 1U << 18,
 	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
 	PERF_OUTPUT_CALLINDENT	    = 1U << 20,
+	PERF_OUTPUT_INSN	    = 1U << 21,
+	PERF_OUTPUT_INSNLEN	    = 1U << 22,
 };
 
 struct output_option {
@@ -93,6 +95,8 @@ struct output_option {
 	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
 	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
 	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
+	{.str = "insn", .field = PERF_OUTPUT_INSN},
+	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
 };
 
 /* default set to maintain compatibility with current format */
@@ -624,6 +628,20 @@ 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)
+{
+	if (PRINT_FIELD(INSNLEN))
+		printf(" ilen: %d", sample->insn_len);
+	if (PRINT_FIELD(INSN)) {
+		int i;
+
+		printf(" insn:");
+		for (i = 0; i < sample->insn_len; i++)
+			printf(" %02x", (unsigned char)sample->insn[i]);
+	}
+}
+
 static void print_sample_bts(struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct thread *thread,
@@ -668,6 +686,8 @@ 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);
+
 	printf("\n");
 }
 
@@ -911,7 +931,7 @@ 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);
 	printf("\n");
 }
 
@@ -2124,7 +2144,7 @@ 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", parse_output_fields),
+		     "bpf-output,callindent,insn,insnlen", 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...]",