perf script: Support -F brstackoff,dso

The idea here is to make AutoFDO easier in cloud environment with ASLR.
It's easiest to show how this is useful by example. 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 of this program with perf record -b.

Using the existing "brstack,dso", we get absolute addresses that are
affected by ASLR, and could be different on different hosts. The address
does not uniquely identify a branch/target in the binary:

  $ 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

Using the existing "brstacksym,dso" is a little better, because the
symbol plus offset and dso name *does* uniquely identify a branch/target
in the binary.  Ultimately, however, AutoFDO wants a simple offset into
the binary, so we'd have to undo all the work perf did to symbolize in
the first place:

  $ 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

With the new "brstackoff,dso" we get what we need: a simple offset into a
specific dso/binary that uniquely identifies a branch/target:
  $ perf script -F brstackoff,dso | sed 's/\/0 /\/0\n/g' | grep burncpu | grep dso.so | head -n 1
  0x6aa(/tmp/burncpu/dso.so)/0x4006b1(/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/20170619163825.2012979-2-marksan@fb.com
[ Updated documentation about 'brstackoff' using text from above ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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, brstackinsn,
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
         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
@@ -211,6 +211,8 @@ 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.
 
+	The brstackoff field will print an offset into a specific dso/binary.
+
 -k::
 --vmlinux=<file>::
         vmlinux pathname

tools/perf/builtin-script.c

@@ -85,6 +85,7 @@ enum perf_output_field {
 	PERF_OUTPUT_INSN	    = 1U << 21,
 	PERF_OUTPUT_INSNLEN	    = 1U << 22,
 	PERF_OUTPUT_BRSTACKINSN	    = 1U << 23,
+	PERF_OUTPUT_BRSTACKOFF	    = 1U << 24,
 };
 
 struct output_option {
@@ -115,6 +116,7 @@ struct output_option {
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
 	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
+	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
 };
 
 /* default set to maintain compatibility with current format */
@@ -299,10 +301,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		return -EINVAL;
 	}
 	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) &&
-	    !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM)) {
+	    !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) {
-		pr_err("Display of DSO requested but none of sample IP, sample address, "
+		pr_err("Display of DSO requested but no address to convert.  Select\n"
-		       "brstack\nor brstacksym are selected. Hence, no addresses to "
+		       "sample IP, sample address, brstack, brstacksym, or brstackoff.\n");
-		       "convert to DSO.\n");
 		return -EINVAL;
 	}
 	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
@@ -606,6 +607,51 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 	}
 }
 
+static void print_sample_brstackoff(struct perf_sample *sample,
+				    struct thread *thread,
+				    struct perf_event_attr *attr)
+{
+	struct branch_stack *br = sample->branch_stack;
+	struct addr_location alf, alt;
+	u64 i, from, to;
+
+	if (!(br && br->nr))
+		return;
+
+	for (i = 0; i < br->nr; i++) {
+
+		memset(&alf, 0, sizeof(alf));
+		memset(&alt, 0, sizeof(alt));
+		from = br->entries[i].from;
+		to   = br->entries[i].to;
+
+		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
+		if (alf.map && !alf.map->dso->adjust_symbols)
+			from = map__map_ip(alf.map, from);
+
+		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
+		if (alt.map && !alt.map->dso->adjust_symbols)
+			to = map__map_ip(alt.map, to);
+
+		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' : '-',
+			br->entries[i].flags.cycles);
+	}
+}
 #define MAXBB 16384UL
 
 static int grab_bb(u8 *buffer, u64 start, u64 end,
@@ -1227,6 +1273,8 @@ static void process_event(struct perf_script *script,
 		print_sample_brstack(sample, thread, attr);
 	else if (PRINT_FIELD(BRSTACKSYM))
 		print_sample_brstacksym(sample, thread, attr);
+	else if (PRINT_FIELD(BRSTACKOFF))
+		print_sample_brstackoff(sample, thread, attr);
 
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);