Deep-Memory-Profiler (DMP) implementation

third_party/tcmalloc/chromium/src/pprof

Index: third_party/tcmalloc/chromium/src/pprof
diff --git a/third_party/tcmalloc/chromium/src/pprof b/third_party/tcmalloc/chromium/src/pprof
index 03bafa4446a1e520542cb953b04b314a4c1b1fe4..2d889d0e08efcc5e944624157c5e3812ff14b441 100755
--- a/third_party/tcmalloc/chromium/src/pprof
+++ b/third_party/tcmalloc/chromium/src/pprof
@@ -72,7 +72,7 @@ use strict;
 use warnings;
 use Getopt::Long;
 
-my $PPROF_VERSION = "1.7";
+my $PPROF_VERSION = "1.8.2";
 
 # These are the object tools we use which can come from a
 # user-specified location using --tools, from the PPROF_TOOLS
@@ -156,7 +156,8 @@ pprof [options] <profile>
    The /<service> can be $HEAP_PAGE, $PROFILE_PAGE, /pprof/pmuprofile,
                          $GROWTH_PAGE, $CONTENTION_PAGE, /pprof/wall,
                          $CENSUSPROFILE_PAGE, or /pprof/filteredprofile.
-   For instance: "pprof http://myserver.com:80$HEAP_PAGE".
+   For instance:
+     pprof http://myserver.com:80$HEAP_PAGE
    If /<service> is omitted, the service defaults to $PROFILE_PAGE (cpu profiling).
 pprof --symbols <program>
    Maps addresses to symbol names.  In this mode, stdin should be a
@@ -545,7 +546,7 @@ sub Init() {
     ConfigureObjTools($main::prog)
   }
 
-  # Break the opt_list_prefix into the prefix_list array
+  # Break the opt_lib_prefix into the prefix_list array
   @prefix_list = split (',', $main::opt_lib_prefix);
 
   # Remove trailing / from the prefixes, in the list to prevent
@@ -643,7 +644,7 @@ sub Main() {
     if ($main::opt_disasm) {
       PrintDisassembly($libs, $flat, $cumulative, $main::opt_disasm);
     } elsif ($main::opt_list) {
-      PrintListing($libs, $flat, $cumulative, $main::opt_list);
+      PrintListing($total, $libs, $flat, $cumulative, $main::opt_list, 0);
     } elsif ($main::opt_text) {
       # Make sure the output is empty when have nothing to report
       # (only matters when --heapcheck is given but we must be
@@ -839,7 +840,7 @@ sub InteractiveCommand {
     my $ignore;
     ($routine, $ignore) = ParseInteractiveArgs($3);
 
-    my $profile = ProcessProfile($orig_profile, $symbols, "", $ignore);
+    my $profile = ProcessProfile($total, $orig_profile, $symbols, "", $ignore);
     my $reduced = ReduceProfile($symbols, $profile);
 
     # Get derived profiles
@@ -866,21 +867,22 @@ sub InteractiveCommand {
 
     return 1;
   }
-  if (m/^\s*list\s*(.+)/) {
+  if (m/^\s*(web)?list\s*(.+)/) {
+    my $html = (defined($1) && ($1 eq "web"));
     $main::opt_list = 1;
 
     my $routine;
     my $ignore;
-    ($routine, $ignore) = ParseInteractiveArgs($1);
+    ($routine, $ignore) = ParseInteractiveArgs($2);
 
-    my $profile = ProcessProfile($orig_profile, $symbols, "", $ignore);
+    my $profile = ProcessProfile($total, $orig_profile, $symbols, "", $ignore);
     my $reduced = ReduceProfile($symbols, $profile);
 
     # Get derived profiles
     my $flat = FlatProfile($reduced);
     my $cumulative = CumulativeProfile($reduced);
 
-    PrintListing($libs, $flat, $cumulative, $routine);
+    PrintListing($total, $libs, $flat, $cumulative, $routine, $html);
     return 1;
   }
   if (m/^\s*disasm\s*(.+)/) {
@@ -891,7 +893,7 @@ sub InteractiveCommand {
     ($routine, $ignore) = ParseInteractiveArgs($1);
 
     # Process current profile to account for various settings
-    my $profile = ProcessProfile($orig_profile, $symbols, "", $ignore);
+    my $profile = ProcessProfile($total, $orig_profile, $symbols, "", $ignore);
     my $reduced = ReduceProfile($symbols, $profile);
 
     # Get derived profiles
@@ -918,7 +920,8 @@ sub InteractiveCommand {
     ($focus, $ignore) = ParseInteractiveArgs($2);
 
     # Process current profile to account for various settings
-    my $profile = ProcessProfile($orig_profile, $symbols, $focus, $ignore);
+    my $profile = ProcessProfile($total, $orig_profile, $symbols,
+                                 $focus, $ignore);
     my $reduced = ReduceProfile($symbols, $profile);
 
     # Get derived profiles
@@ -946,6 +949,7 @@ sub InteractiveCommand {
 
 
 sub ProcessProfile {
+  my $total_count = shift;
   my $orig_profile = shift;
   my $symbols = shift;
   my $focus = shift;
@@ -953,7 +957,6 @@ sub ProcessProfile {
 
   # Process current profile to account for various settings
   my $profile = $orig_profile;
-  my $total_count = TotalProfile($profile);
   printf("Total: %s %s\n", Unparse($total_count), Units());
   if ($focus ne '') {
     $profile = FocusProfile($symbols, $profile, $focus);
@@ -1000,6 +1003,11 @@ Commands:
   list [routine_regexp] [-ignore1] [-ignore2]
       Show source listing of routines whose names match "routine_regexp"
 
+  weblist [routine_regexp] [-ignore1] [-ignore2]
+     Displays a source listing of routines whose names match "routine_regexp"
+     in a web browser.  You can click on source lines to view the
+     corresponding disassembly.
+
   top [--cum] [-ignore1] [-ignore2]
   top20 [--cum] [-ignore1] [-ignore2]
   top37 [--cum] [-ignore1] [-ignore2]
@@ -1175,7 +1183,7 @@ sub PrintText {
              $sym);
     }
     $lines++;
-    last if ($line_limit >= 0 && $lines > $line_limit);
+    last if ($line_limit >= 0 && $lines >= $line_limit);
   }
 }
 
@@ -1322,13 +1330,33 @@ sub ByName {
   return ShortFunctionName($a) cmp ShortFunctionName($b);
 }
 
-# Print source-listing for all all routines that match $main::opt_list
+# Print source-listing for all all routines that match $list_opts
 sub PrintListing {
+  my $total = shift;
   my $libs = shift;
   my $flat = shift;
   my $cumulative = shift;
   my $list_opts = shift;
+  my $html = shift;
 
+  my $output = \*STDOUT;
+  my $fname = "";
+
+  if ($html) {
+    # Arrange to write the output to a temporary file
+    $fname = TempName($main::next_tmpfile, "html");
+    $main::next_tmpfile++;
+    if (!open(TEMP, ">$fname")) {
+      print STDERR "$fname: $!\n";
+      return;
+    }
+    $output = \*TEMP;
+    print $output HtmlListingHeader();
+    printf $output ("<div class=\"legend\">%s<br>Total: %s %s</div>\n",
+                    $main::prog, Unparse($total), Units());
+  }
+
+  my $listed = 0;
   foreach my $lib (@{$libs}) {
     my $symbol_table = GetProcedureBoundaries($lib->[0], $list_opts);
     my $offset = AddressSub($lib->[1], $lib->[3]);
@@ -1340,15 +1368,113 @@ sub PrintListing {
       my $addr = AddressAdd($start_addr, $offset);
       for (my $i = 0; $i < $length; $i++) {
         if (defined($cumulative->{$addr})) {
-          PrintSource($lib->[0], $offset,
-                      $routine, $flat, $cumulative,
-                      $start_addr, $end_addr);
+          $listed += PrintSource(
+            $lib->[0], $offset,
+            $routine, $flat, $cumulative,
+            $start_addr, $end_addr,
+            $html,
+            $output);
           last;
         }
         $addr = AddressInc($addr);
       }
     }
   }
+
+  if ($html) {
+    if ($listed > 0) {
+      print $output HtmlListingFooter();
+      close($output);
+      RunWeb($fname);
+    } else {
+      close($output);
+      unlink($fname);
+    }
+  }
+}
+
+sub HtmlListingHeader {
+  return <<'EOF';
+<DOCTYPE html>
+<html>
+<head>
+<title>Pprof listing</title>
+<style type="text/css">
+body {
+  font-family: sans-serif;
+}
+h1 {
+  font-size: 1.5em;
+  margin-bottom: 4px;
+}
+.legend {
+  font-size: 1.25em;
+}
+.line {
+  color: #aaaaaa;
+}
+.nop {
+  color: #aaaaaa;
+}
+.unimportant {
+  color: #cccccc;
+}
+.disasmloc {
+  color: #000000;
+}
+.deadsrc {
+  cursor: pointer;
+}
+.deadsrc:hover {
+  background-color: #eeeeee;
+}
+.livesrc {
+  color: #0000ff;
+  cursor: pointer;
+}
+.livesrc:hover {
+  background-color: #eeeeee;
+}
+.asm {
+  color: #008800;
+  display: none;
+}
+</style>
+<script type="text/javascript">
+function pprof_toggle_asm(e) {
+  var target;
+  if (!e) e = window.event;
+  if (e.target) target = e.target;
+  else if (e.srcElement) target = e.srcElement;
+
+  if (target) {
+    var asm = target.nextSibling;
+    if (asm && asm.className == "asm") {
+      asm.style.display = (asm.style.display == "block" ? "" : "block");
+      e.preventDefault();
+      return false;
+    }
+  }
+}
+</script>
+</head>
+<body>
+EOF
+}
+
+sub HtmlListingFooter {
+  return <<'EOF';
+</body>
+</html>
+EOF
+}
+
+sub HtmlEscape {
+  my $text = shift;
+  $text =~ s/&/&amp;/g;
+  $text =~ s/</&lt;/g;
+  $text =~ s/>/&gt;/g;
+  return $text;
 }
 
 # Returns the indentation of the line, if it has any non-whitespace
@@ -1362,6 +1488,45 @@ sub Indentation {
   }
 }
 
+# If the symbol table contains inlining info, Disassemble() may tag an
+# instruction with a location inside an inlined function.  But for
+# source listings, we prefer to use the location in the function we
+# are listing.  So use MapToSymbols() to fetch full location
+# information for each instruction and then pick out the first
+# location from a location list (location list contains callers before
+# callees in case of inlining).
+#
+# After this routine has run, each entry in $instructions contains:
+#   [0] start address
+#   [1] filename for function we are listing
+#   [2] line number for function we are listing
+#   [3] disassembly
+#   [4] limit address
+#   [5] most specific filename (may be different from [1] due to inlining)
+#   [6] most specific line number (may be different from [2] due to inlining)
+sub GetTopLevelLineNumbers {
+  my ($lib, $offset, $instructions) = @_;
+  my $pcs = [];
+  for (my $i = 0; $i <= $#{$instructions}; $i++) {
+    push(@{$pcs}, $instructions->[$i]->[0]);
+  }
+  my $symbols = {};
+  MapToSymbols($lib, $offset, $pcs, $symbols);
+  for (my $i = 0; $i <= $#{$instructions}; $i++) {
+    my $e = $instructions->[$i];
+    push(@{$e}, $e->[1]);
+    push(@{$e}, $e->[2]);
+    my $addr = $e->[0];
+    my $sym = $symbols->{$addr};
+    if (defined($sym)) {
+      if ($#{$sym} >= 2 && $sym->[1] =~ m/^(.*):(\d+)$/) {
+        $e->[1] = $1;  # File name
+        $e->[2] = $2;  # Line number
+      }
+    }
+  }
+}
+
 # Print source-listing for one routine
 sub PrintSource {
   my $prog = shift;
@@ -1371,9 +1536,12 @@ sub PrintSource {
   my $cumulative = shift;
   my $start_addr = shift;
   my $end_addr = shift;
+  my $html = shift;
+  my $output = shift;
 
   # Disassemble all instructions (just to get line numbers)
   my @instructions = Disassemble($prog, $offset, $start_addr, $end_addr);
+  GetTopLevelLineNumbers($prog, $offset, \@instructions);
 
   # Hack 1: assume that the first source file encountered in the
   # disassembly contains the routine
@@ -1386,7 +1554,7 @@ sub PrintSource {
   }
   if (!defined($filename)) {
     print STDERR "no filename found in $routine\n";
-    return;
+    return 0;
   }
 
   # Hack 2: assume that the largest line number from $filename is the
@@ -1419,7 +1587,7 @@ sub PrintSource {
   {
     if (!open(FILE, "<$filename")) {
       print STDERR "$filename: $!\n";
-      return;
+      return 0;
     }
     my $l = 0;
     my $first_indentation = -1;
@@ -1447,12 +1615,24 @@ sub PrintSource {
   # Assign all samples to the range $firstline,$lastline,
   # Hack 4: If an instruction does not occur in the range, its samples
   # are moved to the next instruction that occurs in the range.
-  my $samples1 = {};
-  my $samples2 = {};
-  my $running1 = 0;     # Unassigned flat counts
-  my $running2 = 0;     # Unassigned cumulative counts
-  my $total1 = 0;       # Total flat counts
-  my $total2 = 0;       # Total cumulative counts
+  my $samples1 = {};        # Map from line number to flat count
+  my $samples2 = {};        # Map from line number to cumulative count
+  my $running1 = 0;         # Unassigned flat counts
+  my $running2 = 0;         # Unassigned cumulative counts
+  my $total1 = 0;           # Total flat counts
+  my $total2 = 0;           # Total cumulative counts
+  my %disasm = ();          # Map from line number to disassembly
+  my $running_disasm = "";  # Unassigned disassembly
+  my $skip_marker = "---\n";
+  if ($html) {
+    $skip_marker = "";
+    for (my $l = $firstline; $l <= $lastline; $l++) {
+      $disasm{$l} = "";
+    }
+  }
+  my $last_dis_filename = '';
+  my $last_dis_linenum = -1;
+  my $last_touched_line = -1;  # To detect gaps in disassembly for a line
   foreach my $e (@instructions) {
     # Add up counts for all address that fall inside this instruction
     my $c1 = 0;
@@ -1461,6 +1641,38 @@ sub PrintSource {
       $c1 += GetEntry($flat, $a);
       $c2 += GetEntry($cumulative, $a);
     }
+
+    if ($html) {
+      my $dis = sprintf("      %6s %6s \t\t%8s: %s ",
+                        HtmlPrintNumber($c1),
+                        HtmlPrintNumber($c2),
+                        UnparseAddress($offset, $e->[0]),
+                        CleanDisassembly($e->[3]));
+      
+      # Append the most specific source line associated with this instruction
+      if (length($dis) < 80) { $dis .= (' ' x (80 - length($dis))) };
+      $dis = HtmlEscape($dis);
+      my $f = $e->[5];
+      my $l = $e->[6];
+      if ($f ne $last_dis_filename) {
+        $dis .= sprintf("<span class=disasmloc>%s:%d</span>", 
+                        HtmlEscape(CleanFileName($f)), $l);
+      } elsif ($l ne $last_dis_linenum) {
+        # De-emphasize the unchanged file name portion
+        $dis .= sprintf("<span class=unimportant>%s</span>" .
+                        "<span class=disasmloc>:%d</span>", 
+                        HtmlEscape(CleanFileName($f)), $l);
+      } else {
+        # De-emphasize the entire location
+        $dis .= sprintf("<span class=unimportant>%s:%d</span>", 
+                        HtmlEscape(CleanFileName($f)), $l);
+      }
+      $last_dis_filename = $f;
+      $last_dis_linenum = $l;
+      $running_disasm .= $dis;
+      $running_disasm .= "\n";
+    }
+
     $running1 += $c1;
     $running2 += $c2;
     $total1 += $c1;
@@ -1475,23 +1687,49 @@ sub PrintSource {
       AddEntry($samples2, $line, $running2);
       $running1 = 0;
       $running2 = 0;
+      if ($html) {
+        if ($line != $last_touched_line && $disasm{$line} ne '') {
+          $disasm{$line} .= "\n";
+        }
+        $disasm{$line} .= $running_disasm;
+        $running_disasm = '';
+        $last_touched_line = $line;
+      }
     }
   }
 
   # Assign any leftover samples to $lastline
   AddEntry($samples1, $lastline, $running1);
   AddEntry($samples2, $lastline, $running2);
-
-  printf("ROUTINE ====================== %s in %s\n" .
-         "%6s %6s Total %s (flat / cumulative)\n",
-         ShortFunctionName($routine),
-         $filename,
-         Units(),
-         Unparse($total1),
-         Unparse($total2));
+  if ($html) {
+    if ($lastline != $last_touched_line && $disasm{$lastline} ne '') {
+      $disasm{$lastline} .= "\n";
+    }
+    $disasm{$lastline} .= $running_disasm;
+  }
+
+  if ($html) {
+    printf $output (
+      "<h1>%s</h1>%s\n<pre onClick=\"pprof_toggle_asm()\">\n" .
+      "Total:%6s %6s (flat / cumulative %s)\n",
+      HtmlEscape(ShortFunctionName($routine)),
+      HtmlEscape(CleanFileName($filename)),
+      Unparse($total1),
+      Unparse($total2),
+      Units());
+  } else {
+    printf $output (
+      "ROUTINE ====================== %s in %s\n" .
+      "%6s %6s Total %s (flat / cumulative)\n",
+      ShortFunctionName($routine),
+      CleanFileName($filename),
+      Unparse($total1),
+      Unparse($total2),
+      Units());
+  }
   if (!open(FILE, "<$filename")) {
     print STDERR "$filename: $!\n";
-    return;
+    return 0;
   }
   my $l = 0;
   while (<FILE>) {
@@ -1501,16 +1739,47 @@ sub PrintSource {
         (($l <= $oldlastline + 5) || ($l <= $lastline))) {
       chop;
       my $text = $_;
-      if ($l == $firstline) { printf("---\n"); }
-      printf("%6s %6s %4d: %s\n",
-             UnparseAlt(GetEntry($samples1, $l)),
-             UnparseAlt(GetEntry($samples2, $l)),
-             $l,
-             $text);
-      if ($l == $lastline)  { printf("---\n"); }
+      if ($l == $firstline) { print $output $skip_marker; }
+      my $n1 = GetEntry($samples1, $l);
+      my $n2 = GetEntry($samples2, $l);
+      if ($html) {
+        # Emit a span that has one of the following classes:
+        #    livesrc -- has samples
+        #    deadsrc -- has disassembly, but with no samples
+        #    nop     -- has no matching disasembly
+        # Also emit an optional span containing disassembly.
+        my $dis = $disasm{$l};
+        my $asm = "";
+        if (defined($dis) && $dis ne '') {
+          $asm = "<span class=\"asm\">" . $dis . "</span>";
+        }
+        my $source_class = (($n1 + $n2 > 0) 
+                            ? "livesrc" 
+                            : (($asm ne "") ? "deadsrc" : "nop"));
+        printf $output (
+          "<span class=\"line\">%5d</span> " .
+          "<span class=\"%s\">%6s %6s %s</span>%s\n",
+          $l, $source_class,
+          HtmlPrintNumber($n1),
+          HtmlPrintNumber($n2),
+          HtmlEscape($text),
+          $asm);
+      } else {
+        printf $output(
+          "%6s %6s %4d: %s\n",
+          UnparseAlt($n1),
+          UnparseAlt($n2),
+          $l,
+          $text);
+      }
+      if ($l == $lastline)  { print $output $skip_marker; }
     };
   }
   close(FILE);
+  if ($html) {
+    print $output "</pre>\n";
+  }
+  return 1;
 }
 
 # Return the source line for the specified file/linenumber.
@@ -1653,21 +1922,11 @@ sub PrintDisassembledFunction {
     # Print disassembly
     for (my $x = $first_inst; $x <= $last_inst; $x++) {
       my $e = $instructions[$x];
-      my $address = $e->[0];
-      $address = AddressSub($address, $offset);  # Make relative to section
-      $address =~ s/^0x//;
-      $address =~ s/^0*//;
-
-      # Trim symbols
-      my $d = $e->[3];
-      while ($d =~ s/\([^()%]*\)(\s*const)?//g) { } # Argument types, not (%rax)
-      while ($d =~ s/(\w+)<[^<>]*>/$1/g)  { }       # Remove template arguments
-
       printf("%6s %6s    %8s: %6s\n",
              UnparseAlt($flat_count[$x]),
              UnparseAlt($cum_count[$x]),
-             $address,
-             $d);
+             UnparseAddress($offset, $e->[0]),
+             CleanDisassembly($e->[3]));
     }
   }
 }
@@ -2326,6 +2585,16 @@ sub UnparseAlt {
   }
 }
 
+# Alternate pretty-printed form: 0 maps to ""
+sub HtmlPrintNumber {
+  my $num = shift;
+  if ($num == 0) {
+    return "";
+  } else {
+    return Unparse($num);
+  }
+}
+
 # Return output units
 sub Units {
   if ($main::profile_type eq 'heap' || $main::profile_type eq 'growth') {
@@ -2482,6 +2751,13 @@ sub RemoveUninterestingFrames {
                       '__builtin_vec_new',
                       'operator new',
                       'operator new[]',
+		      # The entry to our memory-allocation routines on OS X
+		      'malloc_zone_malloc',
+		      'malloc_zone_calloc',
+		      'malloc_zone_valloc',
+		      'malloc_zone_realloc',
+		      'malloc_zone_memalign',
+		      'malloc_zone_free',
                       # These mark the beginning/end of our custom sections
                       '__start_google_malloc',
                       '__stop_google_malloc',
@@ -3976,7 +4252,7 @@ sub ParseLibraries {
     my $finish;
     my $offset;
     my $lib;
-    if ($l =~ /^($h)-($h)\s+..x.\s+($h)\s+\S+:\S+\s+\d+\s+(\S+\.(so|dll|dylib|bundle)((\.\d+)+\w*(\.\d+){0,3})?)$/i) {
+    if ($l =~ /^($h)-($h)\s+..x.\s+($h)\s+\S+:\S+\s+\d+\s+(\S+(\.(so|dll|dylib|bundle)|chrome)((\.\d+)+\w*(\.\d+){0,3})?)$/i) {
       # Full line from /proc/self/maps.  Example:
       #   40000000-40015000 r-xp 00000000 03:01 12845071   /lib/ld-2.3.2.so
       $start = HexExtend($1);
@@ -3997,7 +4273,6 @@ sub ParseLibraries {
 
     # Expand "$build" variable if available
     $lib =~ s/\$build\b/$buildvar/g;
-
     $lib = FindLibrary($lib);
 
     # Check for pre-relocated libraries, which use pre-relocated symbol tables
@@ -4414,6 +4689,31 @@ sub ShortFunctionName {
   return $function;
 }
 
+# Trim overly long symbols found in disassembler output
+sub CleanDisassembly {
+  my $d = shift;
+  while ($d =~ s/\([^()%]*\)(\s*const)?//g) { } # Argument types, not (%rax)
+  while ($d =~ s/(\w+)<[^<>]*>/$1/g)  { }       # Remove template arguments
+  return $d;
+}
+
+# Clean file name for display
+sub CleanFileName {
+  my ($f) = @_;
+  $f =~ s|^/proc/self/cwd/||;
+  $f =~ s|^\./||;
+  return $f;
+}
+
+# Make address relative to section and clean up for display
+sub UnparseAddress {
+  my ($offset, $address) = @_;
+  $address = AddressSub($address, $offset);
+  $address =~ s/^0x//;
+  $address =~ s/^0*//;
+  return $address;
+}
+
 ##### Miscellaneous #####
 
 # Find the right versions of the above object tools to use.  The