perf script: Add 'brstackinsnlen' for branch stacks

When analyzing with 'perf script', it's useful to understand the
captured instruction and the next sequential instruction.

To calculate the address of the next sequential instruction, the length
of the captured instruction is required.

For example, you can’t know the next sequential instruction after an
unconditional branch unless you calculate that based on its length.

For branch stacks, 'perf script' only prints the instruction bytes with
'brstackinsn', but lacks the instruction length.

Add 'brstackinsnlen' to print the instruction length.

  $ perf script -F ip,brstackinsn,brstackinsnlen --xed
     7fa555be8f75
        _start:
        00007fa555be8090    mov %rsp, %rdi              ilen: 3
        00007fa555be8093    callq  0x7fa555be8ea0       ilen: 5 # PRED 102 cycles [102] 0.02 IPC
        _dl_start+38:
        00007fa555be8ec6    movq  %rdx,0x227853(%rip)   ilen: 7
        00007fa555be8ecd    leaq  0x227f94(%rip),%rdx   ilen: 7
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Ahmad Yasin <ahmad.yasin@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/1647871212-184070-1-git-send-email-kan.liang@linux.intel.com
[ Added the new field to tools/perf/Documentation/perf-script.txt ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-script.txt

@@ -129,8 +129,8 @@ 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, uregs, brstack, brstacksym, flags, bpf-output,
-        brstackinsn, brstackoff, callindent, insn, insnlen, synth, phys_addr,
-        metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat.
+        brstackinsn, brstackinsnlen, brstackoff, callindent, insn, insnlen, synth,
+        phys_addr, metric, misc, srccode, ipc, data_page_size, code_page_size, ins_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
@@ -241,6 +241,10 @@ OPTIONS
 	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.
 
+	Use brstackinsnlen to print the brstackinsn lenght. For example, you
+	can’t know the next sequential instruction after an unconditional branch unless
+	you calculate that based on its length.
+
 	The brstackoff field will print an offset into a specific dso/binary.
 
 	With the metric option perf script can compute metrics for

tools/perf/builtin-script.c

@@ -124,6 +124,7 @@ enum perf_output_field {
 	PERF_OUTPUT_DATA_PAGE_SIZE  = 1ULL << 33,
 	PERF_OUTPUT_CODE_PAGE_SIZE  = 1ULL << 34,
 	PERF_OUTPUT_INS_LAT         = 1ULL << 35,
+	PERF_OUTPUT_BRSTACKINSNLEN  = 1ULL << 36,
 };
 
 struct perf_script {
@@ -191,6 +192,7 @@ struct output_option {
 	{.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE},
 	{.str = "code_page_size", .field = PERF_OUTPUT_CODE_PAGE_SIZE},
 	{.str = "ins_lat", .field = PERF_OUTPUT_INS_LAT},
+	{.str = "brstackinsnlen", .field = PERF_OUTPUT_BRSTACKINSNLEN},
 };
 
 enum {
@@ -488,7 +490,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
 	}
-	if (PRINT_FIELD(BRSTACKINSN) && !allow_user_set &&
+	if ((PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN)) && !allow_user_set &&
 	    !(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"
 		       "Hint: run 'perf record -b ...'\n");
@@ -1120,10 +1122,17 @@ static int print_srccode(struct thread *thread, u8 cpumode, uint64_t addr)
 
 static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct perf_insn *x, u8 *inbuf, int len,
-			    int insn, FILE *fp, int *total_cycles)
+			    int insn, FILE *fp, int *total_cycles,
+			    struct perf_event_attr *attr)
 {
-	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
-			      dump_insn(x, ip, inbuf, len, NULL),
+	int ilen = 0;
+	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t", ip,
+			      dump_insn(x, ip, inbuf, len, &ilen));
+
+	if (PRINT_FIELD(BRSTACKINSNLEN))
+		printed += fprintf(fp, "ilen: %d\t", ilen);
+
+	printed += fprintf(fp, "#%s%s%s%s",
 			      en->flags.predicted ? " PRED" : "",
 			      en->flags.mispred ? " MISPRED" : "",
 			      en->flags.in_tx ? " INTX" : "",
@@ -1209,7 +1218,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		printed += ip__fprintf_sym(entries[nr - 1].from, thread,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
 		printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1],
-					    &x, buffer, len, 0, fp, &total_cycles);
+					    &x, buffer, len, 0, fp, &total_cycles,
+					    attr);
 		if (PRINT_FIELD(SRCCODE))
 			printed += print_srccode(thread, x.cpumode, entries[nr - 1].from);
 	}
@@ -1240,14 +1250,17 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
 				printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp,
-							    &total_cycles);
+							    &total_cycles, attr);
 				if (PRINT_FIELD(SRCCODE))
 					printed += print_srccode(thread, x.cpumode, ip);
 				break;
 			} else {
 				ilen = 0;
-				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
+				printed += fprintf(fp, "\t%016" PRIx64 "\t%s", ip,
 						   dump_insn(&x, ip, buffer + off, len - off, &ilen));
+				if (PRINT_FIELD(BRSTACKINSNLEN))
+					printed += fprintf(fp, "\tilen: %d", ilen);
+				printed += fprintf(fp, "\n");
 				if (ilen == 0)
 					break;
 				if (PRINT_FIELD(SRCCODE))
@@ -1290,16 +1303,23 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			      machine, thread, &x.is64bit, &x.cpumode, false);
 		if (len <= 0)
 			goto out;
-		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip,
-			dump_insn(&x, sample->ip, buffer, len, NULL));
+		ilen = 0;
+		printed += fprintf(fp, "\t%016" PRIx64 "\t%s", sample->ip,
+			dump_insn(&x, sample->ip, buffer, len, &ilen));
+		if (PRINT_FIELD(BRSTACKINSNLEN))
+			printed += fprintf(fp, "\tilen: %d", ilen);
+		printed += fprintf(fp, "\n");
 		if (PRINT_FIELD(SRCCODE))
 			print_srccode(thread, x.cpumode, sample->ip);
 		goto out;
 	}
 	for (off = 0; off <= end - start; off += ilen) {
 		ilen = 0;
-		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off,
+		printed += fprintf(fp, "\t%016" PRIx64 "\t%s", start + off,
 				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+		if (PRINT_FIELD(BRSTACKINSNLEN))
+			printed += fprintf(fp, "\tilen: %d", ilen);
+		printed += fprintf(fp, "\n");
 		if (ilen == 0)
 			break;
 		if (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) {
@@ -1457,7 +1477,7 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
 		for (i = 0; i < sample->insn_len; i++)
 			printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]);
 	}
-	if (PRINT_FIELD(BRSTACKINSN))
+	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN))
 		printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
 
 	return printed;
@@ -3776,7 +3796,7 @@ int cmd_script(int argc, const char **argv)
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
-		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+		     "brstacksym,flags,bpf-output,brstackinsn,brstackinsnlen,brstackoff,"
 		     "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod,"
 		     "data_page_size,code_page_size,ins_lat",
 		     parse_output_fields),