perf script: Support -F brstack,dso and brstacksym,dso

Perf script can report the dso for "addr" and "ip" fields.

This adds the same support for the "brstack" and "brstacksym" fields.
This can be helpful for AutoFDO: we can ignore LBR entries unless the
source and target address are both in the target module we are about to
build.

I built a small test akin to "while(1) { do_nothing(); }" where the
do_nothing function is loaded from a dso:

  $ cat burncpu.cpp
  #include <dlfcn.h>

  int main() {
    void* handle = dlopen("./dso.so", RTLD_LAZY);
    if (!handle) return -1;

    typedef void (*fp)();
    fp do_nothing = (fp) dlsym(handle, "do_nothing");

    while(1) {
      do_nothing();
    }
  }

  $ cat dso.cpp
  extern "C" void do_nothing() {}

  $ cat build.sh
  #!/bin/bash
  g++ -shared dso.cpp -o dso.so
  g++ burncpu.cpp -o burncpu -ldl

I sampled the execution with perf record -b.  Using the new perf script
functionality I can easily find cases where there was a transition from one
dso to another:

  $ perf record -a -b -- sleep 5
  [ perf record: Woken up 55 times to write data ]
  [ perf record: Captured and wrote 18.815 MB perf.data (43593 samples) ]

  $ perf script -F brstack,dso | sed 's/\/0 /\/0\n/g' | grep burncpu | grep dso.so | head -n 1
  0x7f967139b6aa(/tmp/burncpu/dso.so)/0x4006b1(/tmp/burncpu/exe)/P/-/-/0

  $ perf script -F brstacksym,dso | sed 's/\/0 /\/0\n/g' | grep burncpu | grep dso.so | head -n 1
  do_nothing+0x5(/tmp/burncpu/dso.so)/main+0x44(/tmp/burncpu/exe)/P/-/-/0

Signed-off-by: Mark Santaniello <marksan@fb.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170619163825.2012979-1-marksan@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-script.c

@@ -298,10 +298,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected.\n");
 		return -EINVAL;
 	}
-	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
+	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) &&
-		pr_err("Display of DSO requested but neither sample IP nor "
+	    !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM)) {
-			   "sample address\nis selected. Hence, no addresses to convert "
+		pr_err("Display of DSO requested but none of sample IP, sample address, "
-		       "to DSO.\n");
+		       "brstack\nor brstacksym are selected. Hence, no addresses to "
+		       "convert to DSO.\n");
 		return -EINVAL;
 	}
 	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
@@ -514,18 +515,43 @@ mispred_str(struct branch_entry *br)
 	return br->flags.predicted ? 'P' : 'M';
 }
 
-static void print_sample_brstack(struct perf_sample *sample)
+static void print_sample_brstack(struct perf_sample *sample,
+				 struct thread *thread,
+				 struct perf_event_attr *attr)
 {
 	struct branch_stack *br = sample->branch_stack;
-	u64 i;
+	struct addr_location alf, alt;
+	u64 i, from, to;
 
 	if (!(br && br->nr))
 		return;
 
 	for (i = 0; i < br->nr; i++) {
-		printf(" 0x%"PRIx64"/0x%"PRIx64"/%c/%c/%c/%d ",
+		from = br->entries[i].from;
-			br->entries[i].from,
+		to   = br->entries[i].to;
-			br->entries[i].to,
+
+		if (PRINT_FIELD(DSO)) {
+			memset(&alf, 0, sizeof(alf));
+			memset(&alt, 0, sizeof(alt));
+			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
+			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
+		}
+
+		printf("0x%"PRIx64, from);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alf.map, stdout);
+			printf(")");
+		}
+
+		printf("/0x%"PRIx64, to);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alt.map, stdout);
+			printf(")");
+		}
+
+		printf("/%c/%c/%c/%d ",
 			mispred_str( br->entries + i),
 			br->entries[i].flags.in_tx? 'X' : '-',
 			br->entries[i].flags.abort? 'A' : '-',
@@ -534,7 +560,8 @@ static void print_sample_brstack(struct perf_sample *sample)
 }
 
 static void print_sample_brstacksym(struct perf_sample *sample,
-				    struct thread *thread)
+				    struct thread *thread,
+				    struct perf_event_attr *attr)
 {
 	struct branch_stack *br = sample->branch_stack;
 	struct addr_location alf, alt;
@@ -559,8 +586,18 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 			alt.sym = map__find_symbol(alt.map, alt.addr);
 
 		symbol__fprintf_symname_offs(alf.sym, &alf, stdout);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alf.map, stdout);
+			printf(")");
+		}
 		putchar('/');
 		symbol__fprintf_symname_offs(alt.sym, &alt, stdout);
+		if (PRINT_FIELD(DSO)) {
+			printf("(");
+			map__fprintf_dsoname(alt.map, stdout);
+			printf(")");
+		}
 		printf("/%c/%c/%c/%d ",
 			mispred_str( br->entries + i),
 			br->entries[i].flags.in_tx? 'X' : '-',
@@ -1187,9 +1224,9 @@ static void process_event(struct perf_script *script,
 		print_sample_iregs(sample, attr);
 
 	if (PRINT_FIELD(BRSTACK))
-		print_sample_brstack(sample);
+		print_sample_brstack(sample, thread, attr);
 	else if (PRINT_FIELD(BRSTACKSYM))
-		print_sample_brstacksym(sample, thread);
+		print_sample_brstacksym(sample, thread, attr);
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);