perf tools: Support 'srccode' output

When looking at PT or brstackinsn traces with 'perf script' it can be
very useful to see the source code. This adds a simple facility to print
them with 'perf script', if the information is available through dwarf

  % perf record ...
  % perf script -F insn,ip,sym,srccode
  ...

            4004c6 main
  5               for (i = 0; i < 10000000; i++)
             4004cd main
  5               for (i = 0; i < 10000000; i++)
             4004c6 main
  5               for (i = 0; i < 10000000; i++)
             4004cd main
  5               for (i = 0; i < 10000000; i++)
             4004cd main
  5               for (i = 0; i < 10000000; i++)
             4004cd main
  5               for (i = 0; i < 10000000; i++)
             4004cd main
  5               for (i = 0; i < 10000000; i++)
             4004cd main
  5               for (i = 0; i < 10000000; i++)
             4004b3 main
  6                       v++;

  % perf record -b ...
  % perf script -F insn,ip,sym,srccode,brstackinsn

  ...
         main+22:
          0000000000400543        insn: e8 ca ff ff ff            # PRED
  |18                     f1();
          f1:
          0000000000400512        insn: 55
  |10       {
          0000000000400513        insn: 48 89 e5
          0000000000400516        insn: b8 00 00 00 00
  |11             f2();
          000000000040051b        insn: e8 d6 ff ff ff            # PRED
          f2:
          00000000004004f6        insn: 55
  |5        {
          00000000004004f7        insn: 48 89 e5
          00000000004004fa        insn: 8b 05 2c 0b 20 00
  |6              c = a / b;
          0000000000400500        insn: 8b 0d 2a 0b 20 00
          0000000000400506        insn: 99
          0000000000400507        insn: f7 f9
          0000000000400509        insn: 89 05 29 0b 20 00
          000000000040050f        insn: 90
  |7        }
          0000000000400510        insn: 5d
          0000000000400511        insn: c3                        # PRED
          f1+14:
          0000000000400520        insn: b8 00 00 00 00
  |12             f2();
          0000000000400525        insn: e8 cc ff ff ff            # PRED
          f2:
          00000000004004f6        insn: 55
  |5        {
          00000000004004f7        insn: 48 89 e5
          00000000004004fa        insn: 8b 05 2c 0b 20 00
  |6              c = a / b;

Not supported for callchains currently, would need some layout changes
there.

Committer notes:

Fixed the build on Alpine Linux (3.4 .. 3.8) by addressing this
warning:

  In file included from util/srccode.c:19:0:
  /usr/include/sys/fcntl.h:1:2: error: #warning redirecting incorrect #include <sys/fcntl.h> to <fcntl.h> [-Werror=cpp]
   #warning redirecting incorrect #include <sys/fcntl.h> to <fcntl.h>
    ^~~~~~~
  cc1: all warnings being treated as errors

Signed-off-by: Andi Kleen <[email protected]>
Tested-by: Jiri Olsa <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: Andi Kleen

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, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
-        brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc.
+        brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode.
         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

tools/perf/builtin-script.c

@@ -96,6 +96,7 @@ enum perf_output_field {
 	PERF_OUTPUT_UREGS	    = 1U << 27,
 	PERF_OUTPUT_METRIC	    = 1U << 28,
 	PERF_OUTPUT_MISC            = 1U << 29,
+	PERF_OUTPUT_SRCCODE	    = 1U << 30,
 };
 
 struct output_option {
@@ -132,6 +133,7 @@ struct output_option {
 	{.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
 	{.str = "metric", .field = PERF_OUTPUT_METRIC},
 	{.str = "misc", .field = PERF_OUTPUT_MISC},
+	{.str = "srccode", .field = PERF_OUTPUT_SRCCODE},
 };
 
 enum {
@@ -424,7 +426,7 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		pr_err("Display of DSO requested but no address to convert.\n");
 		return -EINVAL;
 	}
-	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
+	if ((PRINT_FIELD(SRCLINE) || PRINT_FIELD(SRCCODE)) && !PRINT_FIELD(IP)) {
 		pr_err("Display of source line number requested but sample IP is not\n"
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
@@ -907,6 +909,22 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 	return len;
 }
 
+static int print_srccode(struct thread *thread, u8 cpumode, uint64_t addr)
+{
+	struct addr_location al;
+	int ret = 0;
+
+	memset(&al, 0, sizeof(al));
+	thread__find_map(thread, cpumode, addr, &al);
+	if (!al.map)
+		return 0;
+	ret = map__fprintf_srccode(al.map, al.addr, stdout,
+		    &thread->srccode_state);
+	if (ret)
+		ret += printf("\n");
+	return ret;
+}
+
 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)
@@ -998,6 +1016,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
 		printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
 					    &x, buffer, len, 0, fp, &total_cycles);
+		if (PRINT_FIELD(SRCCODE))
+			printed += print_srccode(thread, x.cpumode, br->entries[nr - 1].from);
 	}
 
 	/* Print all blocks */
@@ -1027,12 +1047,16 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			if (ip == end) {
 				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp,
 							    &total_cycles);
+				if (PRINT_FIELD(SRCCODE))
+					printed += print_srccode(thread, x.cpumode, ip);
 				break;
 			} else {
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
 						   dump_insn(&x, ip, buffer + off, len - off, &ilen));
 				if (ilen == 0)
 					break;
+				if (PRINT_FIELD(SRCCODE))
+					print_srccode(thread, x.cpumode, ip);
 				insn++;
 			}
 		}
@@ -1063,13 +1087,17 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip,
 			dump_insn(&x, sample->ip, buffer, len, NULL));
+		if (PRINT_FIELD(SRCCODE))
+			print_srccode(thread, x.cpumode, sample->ip);
 		goto out;
 	}
 	for (off = 0; off <= end - start; off += ilen) {
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off,
 				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
 		if (ilen == 0)
 			break;
+		if (PRINT_FIELD(SRCCODE))
+			print_srccode(thread, x.cpumode, start + off);
 	}
 out:
 	return printed;
@@ -1252,7 +1280,16 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,
 		printed += map__fprintf_srcline(al->map, al->addr, "\n  ", fp);
 
 	printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
-	return printed + fprintf(fp, "\n");
+	printed += fprintf(fp, "\n");
+	if (PRINT_FIELD(SRCCODE)) {
+		int ret = map__fprintf_srccode(al->map, al->addr, stdout,
+					 &thread->srccode_state);
+		if (ret) {
+			printed += ret;
+			printed += printf("\n");
+		}
+	}
+	return printed;
 }
 
 static struct {
@@ -1792,6 +1829,12 @@ static void process_event(struct perf_script *script,
 		fprintf(fp, "%16" PRIx64, sample->phys_addr);
 	fprintf(fp, "\n");
 
+	if (PRINT_FIELD(SRCCODE)) {
+		if (map__fprintf_srccode(al->map, al->addr, stdout,
+					 &thread->srccode_state))
+			printf("\n");
+	}
+
 	if (PRINT_FIELD(METRIC))
 		perf_sample__fprint_metric(script, thread, evsel, sample, fp);
 

tools/perf/util/Build

@@ -77,6 +77,7 @@ libperf-y += stat-shadow.o
 libperf-y += stat-display.o
 libperf-y += record.o
 libperf-y += srcline.o
+libperf-y += srccode.o
 libperf-y += data.o
 libperf-y += tsc.o
 libperf-y += cloexec.o

tools/perf/util/evsel_fprintf.c

@@ -173,6 +173,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 			if (!print_oneline)
 				printed += fprintf(fp, "\n");
 
+			/* Add srccode here too? */
 			if (symbol_conf.bt_stop_list &&
 			    node->sym &&
 			    strlist__has_entry(symbol_conf.bt_stop_list,

tools/perf/util/map.c

@@ -19,6 +19,7 @@
 #include "srcline.h"
 #include "namespaces.h"
 #include "unwind.h"
+#include "srccode.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
 static void __maps__insert_name(struct maps *maps, struct map *map);
@@ -421,6 +422,54 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 	return ret;
 }
 
+int map__fprintf_srccode(struct map *map, u64 addr,
+			 FILE *fp,
+			 struct srccode_state *state)
+{
+	char *srcfile;
+	int ret = 0;
+	unsigned line;
+	int len;
+	char *srccode;
+
+	if (!map || !map->dso)
+		return 0;
+	srcfile = get_srcline_split(map->dso,
+				    map__rip_2objdump(map, addr),
+				    &line);
+	if (!srcfile)
+		return 0;
+
+	/* Avoid redundant printing */
+	if (state &&
+	    state->srcfile &&
+	    !strcmp(state->srcfile, srcfile) &&
+	    state->line == line) {
+		free(srcfile);
+		return 0;
+	}
+
+	srccode = find_sourceline(srcfile, line, &len);
+	if (!srccode)
+		goto out_free_line;
+
+	ret = fprintf(fp, "|%-8d %.*s", line, len, srccode);
+	state->srcfile = srcfile;
+	state->line = line;
+	return ret;
+
+out_free_line:
+	free(srcfile);
+	return ret;
+}
+
+
+void srccode_state_free(struct srccode_state *state)
+{
+	zfree(&state->srcfile);
+	state->line = 0;
+}
+
 /**
  * map__rip_2objdump - convert symbol start address to objdump address.
  * @map: memory map

tools/perf/util/map.h

@@ -174,6 +174,22 @@ char *map__srcline(struct map *map, u64 addr, struct symbol *sym);
 int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 			 FILE *fp);
 
+struct srccode_state {
+	char *srcfile;
+	unsigned line;
+};
+
+static inline void srccode_state_init(struct srccode_state *state)
+{
+	state->srcfile = NULL;
+	state->line = 0;
+}
+
+void srccode_state_free(struct srccode_state *state);
+
+int map__fprintf_srccode(struct map *map, u64 addr,
+			 FILE *fp, struct srccode_state *state);
+
 int map__load(struct map *map);
 struct symbol *map__find_symbol(struct map *map, u64 addr);
 struct symbol *map__find_symbol_by_name(struct map *map, const char *name);