[profiler] Fix attribution for the top-most interpreted frame.

[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter frame to the second-topmost frame if we were in a bytecode handler with elided frame. With this change we try to detect that we are in a handler without a frame. If we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17

Review-Url: https://codereview.chromium.org/2667253004
Cr-Original-Commit-Position: refs/heads/master@{#42894}
Committed: https://chromium.googlesource.com/v8/v8/+/d07f6540c1f9628ed2ba1fa6507c90db07ccc5f5
Review-Url: https://codereview.chromium.org/2667253004
Cr-Commit-Position: refs/heads/master@{#42924}
Committed: https://chromium.googlesource.com/v8/v8/+/e82880b65d6cf73892523f0d0a054838540e75c5

[Jarin, 2017-02-02 12:14:18]

Description was changed from

==========
[profiler] Fix attribution for the top-most interpreted frame.
==========

to

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter from to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, --prof and linux-tick-processor would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17
==========

[Jarin, 2017-02-02 12:14:45]

The CQ bit was checked by jarin@chromium.org to run a CQ dry run

[commit-bot: I haz the power, 2017-02-02 12:14:52]

Dry run: CQ is trying da patch. Follow status at
 
https://chromium-cq-status.appspot.com/v2/patch-status/codereview.chromium.or...

[Jarin, 2017-02-02 12:22:48]

jarin@chromium.org changed reviewers:
+ bmeurer@chromium.org

[Jarin, 2017-02-02 12:22:49]

Could you take a look, please?

[Benedikt Meurer, 2017-02-02 12:24:39]

lgtm

[Jarin, 2017-02-02 12:24:50]

The CQ bit was checked by jarin@chromium.org

[commit-bot: I haz the power, 2017-02-02 12:25:03]

CQ is trying da patch. Follow status at
 
https://chromium-cq-status.appspot.com/v2/patch-status/codereview.chromium.or...

[Jarin, 2017-02-02 12:29:37]

Description was changed from

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter from to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, --prof and linux-tick-processor would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17
==========

to

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter from to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor
would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17
==========

[Jarin, 2017-02-02 12:30:22]

Description was changed from

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter from to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor
would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17
==========

to

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter frame to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor
would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17
==========

[commit-bot: I haz the power, 2017-02-02 13:11:20]

The CQ bit was unchecked by commit-bot@chromium.org

[commit-bot: I haz the power, 2017-02-02 13:11:21]

Try jobs failed on following builders:
  v8_linux_arm_rel_ng on master.tryserver.v8 (JOB_FAILED,
http://build.chromium.org/p/tryserver.v8/builders/v8_linux_arm_rel_ng/builds/...)
  v8_linux_arm_rel_ng_triggered on master.tryserver.v8 (JOB_FAILED,
http://build.chromium.org/p/tryserver.v8/builders/v8_linux_arm_rel_ng_trigger...)

[Jarin, 2017-02-02 13:47:40]

The CQ bit was checked by jarin@chromium.org to run a CQ dry run

[commit-bot: I haz the power, 2017-02-02 13:47:48]

Dry run: CQ is trying da patch. Follow status at
 
https://chromium-cq-status.appspot.com/v2/patch-status/codereview.chromium.or...

[Jarin, 2017-02-02 14:13:43]

The CQ bit was unchecked by jarin@chromium.org

[Jarin, 2017-02-02 14:13:44]

The CQ bit was checked by jarin@chromium.org

[Jarin, 2017-02-02 14:13:44]

The patchset sent to the CQ was uploaded after l-g-t-m from bmeurer@chromium.org
Link to the patchset: https://codereview.chromium.org/2667253004/#ps40001
(title: "Added conservative check for interpreted frame.")

[commit-bot: I haz the power, 2017-02-02 14:13:57]

CQ is trying da patch. Follow status at
 
https://chromium-cq-status.appspot.com/v2/patch-status/codereview.chromium.or...

[commit-bot: I haz the power, 2017-02-02 14:23:25]

CQ is committing da patch.

Bot data: {"patchset_id": 40001, "attempt_start_ts": 1486044824278760,
"parent_rev": "8ae463d736c1a85d66babf2593fd4397162a80f0", "commit_rev":
"d07f6540c1f9628ed2ba1fa6507c90db07ccc5f5"}

[commit-bot: I haz the power, 2017-02-02 14:23:29]

Description was changed from

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter frame to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor
would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17
==========

to

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter frame to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor
would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17

Review-Url: https://codereview.chromium.org/2667253004
Cr-Commit-Position: refs/heads/master@{#42894}
Committed:
https://chromium.googlesource.com/v8/v8/+/d07f6540c1f9628ed2ba1fa6507c90db07c...
==========

[commit-bot: I haz the power, 2017-02-02 14:23:30]

Committed patchset #3 (id:40001) as
https://chromium.googlesource.com/v8/v8/+/d07f6540c1f9628ed2ba1fa6507c90db07c...

[Jakob Kummerow, 2017-02-03 06:09:58]

ASan is complaining about SafeStackFrameIterator, see e.g.
https://build.chromium.org/p/client.v8/builders/V8%20Mac64%20ASAN/builds/1073...

[Michael Achenbach, 2017-02-03 07:37:24]

A revert of this CL (patchset #3 id:40001) has been created in
https://codereview.chromium.org/2670843005/ by machenbach@chromium.org.

The reason for reverting is: Flaky crashes on mac asan:
https://build.chromium.org/p/client.v8/builders/V8%20Mac64%20ASAN/builds/10739.

[Jarin, 2017-02-03 12:22:58]

Description was changed from

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter frame to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor
would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17

Review-Url: https://codereview.chromium.org/2667253004
Cr-Commit-Position: refs/heads/master@{#42894}
Committed:
https://chromium.googlesource.com/v8/v8/+/d07f6540c1f9628ed2ba1fa6507c90db07c...
==========

to

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter frame to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor
would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17

Review-Url: https://codereview.chromium.org/2667253004
Cr-Commit-Position: refs/heads/master@{#42894}
Committed:
https://chromium.googlesource.com/v8/v8/+/d07f6540c1f9628ed2ba1fa6507c90db07c...
==========

[Jarin, 2017-02-03 12:23:08]

The CQ bit was checked by jarin@chromium.org

[Jarin, 2017-02-03 12:23:08]

The patchset sent to the CQ was uploaded after l-g-t-m from bmeurer@chromium.org
Link to the patchset: https://codereview.chromium.org/2667253004/#ps60001
(title: "ASAN workaround")

[commit-bot: I haz the power, 2017-02-03 12:23:13]

CQ is trying da patch. Follow status at
 
https://chromium-cq-status.appspot.com/v2/patch-status/codereview.chromium.or...

[commit-bot: I haz the power, 2017-02-03 12:47:36]

CQ is committing da patch.

Bot data: {"patchset_id": 60001, "attempt_start_ts": 1486124588145240,
"parent_rev": "bff24112faa64c43f00cb68c0fbd5f6987f248ab", "commit_rev":
"e82880b65d6cf73892523f0d0a054838540e75c5"}

[commit-bot: I haz the power, 2017-02-03 12:47:43]

Description was changed from

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter frame to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor
would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17

Review-Url: https://codereview.chromium.org/2667253004
Cr-Commit-Position: refs/heads/master@{#42894}
Committed:
https://chromium.googlesource.com/v8/v8/+/d07f6540c1f9628ed2ba1fa6507c90db07c...
==========

to

==========
[profiler] Fix attribution for the top-most interpreted frame.

Before this change, we attributed samples for the top-most interpreter frame to
the second-topmost frame if we were in a bytecode handler with elided frame.
With this change we try to detect that we are in a handler without a frame. If
we are, we do not drop the topmost frame.

For example, consider the program

function inner() {
  var s = 0;
  for (var i = 0; i < 100000; i++) {
    s += i * i;
  }
  return s;
}

function trivial() {
  return inner();
}

for (var i = 0; i < 2000; i++) {
  trivial();
}


Before this change, d8 --prof --ignition --nocrankshaft and linux-tick-processor
would produce:

  [JavaScript]:
   ticks  total  nonlib   name
   4885   83.4%   83.5%  Function: ~trivial a.js:15:17
    759   13.0%   13.0%  Function: ~inner a.js:7:15

After this change, we get 

 [JavaScript]:
   ticks  total  nonlib   name
   5486   95.9%   96.2%  Function: ~inner a.js:7:15
      4    0.1%    0.1%  Function: ~trivial a.js:15:17

Review-Url: https://codereview.chromium.org/2667253004
Cr-Original-Commit-Position: refs/heads/master@{#42894}
Committed:
https://chromium.googlesource.com/v8/v8/+/d07f6540c1f9628ed2ba1fa6507c90db07c...
Review-Url: https://codereview.chromium.org/2667253004
Cr-Commit-Position: refs/heads/master@{#42924}
Committed:
https://chromium.googlesource.com/v8/v8/+/e82880b65d6cf73892523f0d0a054838540...
==========

[commit-bot: I haz the power, 2017-02-03 12:47:44]

Committed patchset #4 (id:60001) as
https://chromium.googlesource.com/v8/v8/+/e82880b65d6cf73892523f0d0a054838540...