Reland "[utils] Implement the llvm-locstats tool"

The tool reports verbose output for the DWARF debug location coverage.
The llvm-locstats for each variable or formal parameter DIE computes what
percentage from the code section bytes, where it is in scope, it has
location description. The line 0 shows the number (and the percentage) of
DIEs with no location information, but the line 100 shows the number (and
the percentage) of DIEs where there is location information in all code
section bytes (where the variable or parameter is in the scope). The line
50..59 shows the number (and the percentage) of DIEs where the location
information is in between 50 and 59 percentage of its scope covered.

Differential Revision: https://reviews.llvm.org/D66526

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@373183 91177308-0d34-0410-b5e6-96231b3b80d8

CMakeLists.txt

@@ -1097,3 +1097,7 @@ if (LLVM_INCLUDE_BENCHMARKS)
   add_subdirectory(utils/benchmark)
   add_subdirectory(benchmarks)
 endif()
+
+if (LLVM_INCLUDE_UTILS AND LLVM_INCLUDE_TOOLS)
+  add_subdirectory(utils/llvm-locstats)
+endif()

docs/CommandGuide/index.rst

@@ -74,3 +74,4 @@ Developer Tools
    llvm-build
    llvm-exegesis
    llvm-pdbutil
+   llvm-locstats

docs/CommandGuide/llvm-locstats.rst

@@ -0,0 +1,79 @@
+llvm-locstats - calculate statistics on DWARF debug location
+============================================================
+
+.. program:: llvm-locstats
+
+SYNOPSIS
+--------
+
+:program:`llvm-locstats` [*options*] [*filename*]
+
+DESCRIPTION
+-----------
+
+:program:`llvm-locstats` works like a wrapper around :program:`llvm-dwarfdump`.
+It parses :program:`llvm-dwarfdump` statistics regarding debug location by
+pretty printing it in a more human readable way.
+
+The line 0% shows the number and the percentage of DIEs with no location
+information, but the line 100% shows the information for DIEs where there is
+location information in all code section bytes (where the variable or parameter
+is in the scope). The line 50-59% shows the number and the percentage of DIEs
+where the location information is between 50 and 59 percentage of its scope
+covered.
+
+OPTIONS
+-------
+
+.. option:: -only-variables
+
+            Calculate the location statistics only for local variables.
+
+.. option:: -only-formal-parameters
+
+            Calculate the location statistics only for formal parameters.
+
+.. option:: -ignore-debug-entry-values
+
+            Ignore the location statistics on locations containing the
+            debug entry values DWARF operation.
+
+EXIT STATUS
+-----------
+
+:program:`llvm-locstats` returns 0 if the input file were parsed
+successfully. Otherwise, it returns 1.
+
+OUTPUT EXAMPLE
+--------------
+
+.. code-block:: none
+
+  =================================================
+            Debug Location Statistics
+  =================================================
+        cov%          samples       percentage(~)
+  -------------------------------------------------
+     0%                    1              16%
+     1-9%                  0               0%
+     10-19%                0               0%
+     20-29%                0               0%
+     30-39%                0               0%
+     40-49%                0               0%
+     50-99%                1              16%
+     60-69%                0               0%
+     70-79%                0               0%
+     80-89%                1              16%
+     90-99%                0               0%
+     100%                  3              50%
+  =================================================
+  -the number of debug variables processed: 6
+  -PC ranges covered: 81%
+  -------------------------------------------------
+  -total availability: 83%
+  =================================================
+
+SEE ALSO
+--------
+
+:manpage:`llvm-dwarfdump(1)`

test/lit.cfg.py

@@ -124,6 +124,11 @@ if config.have_ocamlopt:
 
 opt_viewer_cmd = '%s %s/tools/opt-viewer/opt-viewer.py' % (sys.executable, config.llvm_src_root)
 
+llvm_locstats_tool = os.path.join(config.llvm_tools_dir, 'llvm-locstats')
+config.substitutions.append(
+    ('%llvm-locstats', "'%s' %s" % (config.python_executable, llvm_locstats_tool)))
+config.llvm_locstats_used = os.path.exists(llvm_locstats_tool)
+
 tools = [
     ToolSubst('%lli', FindTool('lli'), post='.', extra_args=lli_args),
     ToolSubst('%llc_dwarf', FindTool('llc'), extra_args=llc_args),

test/tools/llvm-locstats/lit.local.cfg

@@ -0,0 +1,2 @@
+if not config.llvm_locstats_used:
+    config.unsupported = True

test/tools/llvm-locstats/locstats.ll

@@ -0,0 +1,173 @@
+; RUN: llc %s -o %t0.o -filetype=obj \
+; RUN:   | %llvm-locstats %t0.o | FileCheck %s --check-prefix=LOCSTATS
+;
+; Test the llvm-locstats output.
+; LOCSTATS: 0% 0 0%
+; LOCSTATS: 1-9% 0 0%
+; LOCSTATS: 10-19% 0 0%
+; LOCSTATS: 20-29% 1 11%
+; LOCSTATS: 30-39% 0 0%
+; LOCSTATS: 40-49% 1 11%
+; LOCSTATS: 50-59% 1 11%
+; LOCSTATS: 60-69% 1 11%
+; LOCSTATS: 70-79% 0 0%
+; LOCSTATS: 80-89% 2 22%
+; LOCSTATS: 90-99% 1 11%
+; LOCSTATS: 100% 2 22%
+;
+; The source code of the test case:
+;extern int fn2 (int);
+;
+;__attribute__((noinline))
+;int
+;fn1 (int *x, int *y)
+;{
+;  int a = *x;
+;  int b = *y;
+;  int local = a + b;
+;  if (a > 1) {
+;    local += 2;
+;    ++local;
+;    if (local > 200)
+;      local -= fn2(a);
+;  } else {
+;    local += 3;
+;    ++local;
+;    local += fn2(a);
+; }
+;  if (b > 4)
+;   local += a;
+;  int local2 = 7;
+;  local -= fn2 (local2);
+;  return local;
+;}
+;
+;__attribute__((noinline))
+;int f()
+;{
+;  int l, k;
+;  int res = 0;
+;  res += fn1 (&l, &k);
+;  return res;
+;}
+;
+; ModuleID = 'locstats.c'
+source_filename = "locstats.c"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: noinline nounwind uwtable
+define dso_local i32 @fn1(i32* nocapture readonly %0, i32* nocapture readonly %1) local_unnamed_addr !dbg !7 {
+  call void @llvm.dbg.value(metadata i32* %0, metadata !13, metadata !DIExpression()), !dbg !19
+  call void @llvm.dbg.value(metadata i32* %1, metadata !14, metadata !DIExpression()), !dbg !19
+  %3 = load i32, i32* %0, align 4, !dbg !20
+  call void @llvm.dbg.value(metadata i32 %3, metadata !15, metadata !DIExpression()), !dbg !19
+  %4 = load i32, i32* %1, align 4, !dbg !20
+  call void @llvm.dbg.value(metadata i32 %4, metadata !16, metadata !DIExpression()), !dbg !19
+  %5 = add nsw i32 %4, %3, !dbg !20
+  call void @llvm.dbg.value(metadata i32 %5, metadata !17, metadata !DIExpression()), !dbg !19
+  %6 = icmp sgt i32 %3, 1, !dbg !20
+  br i1 %6, label %7, label %13, !dbg !22
+
+7:                                                ; preds = %2
+  call void @llvm.dbg.value(metadata i32 %5, metadata !17, metadata !DIExpression(DW_OP_plus_uconst, 2, DW_OP_stack_value)), !dbg !19
+  %8 = add nsw i32 %5, 3, !dbg !23
+  call void @llvm.dbg.value(metadata i32 %8, metadata !17, metadata !DIExpression()), !dbg !19
+  %9 = icmp sgt i32 %8, 200, !dbg !25
+  br i1 %9, label %10, label %17, !dbg !27
+
+10:                                               ; preds = %7
+  %11 = tail call i32 @fn2(i32 %3), !dbg !27
+  %12 = sub nsw i32 %8, %11, !dbg !27
+  call void @llvm.dbg.value(metadata i32 %12, metadata !17, metadata !DIExpression()), !dbg !19
+  br label %17, !dbg !27
+
+13:                                               ; preds = %2
+  call void @llvm.dbg.value(metadata i32 %5, metadata !17, metadata !DIExpression(DW_OP_plus_uconst, 3, DW_OP_stack_value)), !dbg !19
+  %14 = add nsw i32 %5, 4, !dbg !28
+  call void @llvm.dbg.value(metadata i32 %14, metadata !17, metadata !DIExpression()), !dbg !19
+  %15 = tail call i32 @fn2(i32 %3), !dbg !30
+  %16 = add nsw i32 %14, %15, !dbg !30
+  call void @llvm.dbg.value(metadata i32 %16, metadata !17, metadata !DIExpression()), !dbg !19
+  br label %17
+
+17:                                               ; preds = %7, %10, %13
+  %18 = phi i32 [ %12, %10 ], [ %8, %7 ], [ %16, %13 ], !dbg !31
+  call void @llvm.dbg.value(metadata i32 %18, metadata !17, metadata !DIExpression()), !dbg !19
+  %19 = icmp sgt i32 %4, 4, !dbg !32
+  %20 = select i1 %19, i32 %3, i32 0, !dbg !34
+  %21 = add nsw i32 %18, %20, !dbg !34
+  call void @llvm.dbg.value(metadata i32 %21, metadata !17, metadata !DIExpression()), !dbg !19
+  call void @llvm.dbg.value(metadata i32 7, metadata !18, metadata !DIExpression()), !dbg !19
+  %22 = tail call i32 @fn2(i32 7), !dbg !34
+  %23 = sub i32 %21, %22, !dbg !34
+  call void @llvm.dbg.value(metadata i32 %23, metadata !17, metadata !DIExpression()), !dbg !19
+  ret i32 %23, !dbg !34
+}
+
+declare dso_local i32 @fn2(i32) local_unnamed_addr
+
+; Function Attrs: noinline nounwind uwtable
+define dso_local i32 @f() local_unnamed_addr !dbg !35 {
+  %1 = alloca i32, align 4
+  %2 = alloca i32, align 4
+  %3 = bitcast i32* %1 to i8*, !dbg !42
+  %4 = bitcast i32* %2 to i8*, !dbg !42
+  call void @llvm.dbg.value(metadata i32 0, metadata !41, metadata !DIExpression()), !dbg !42
+  call void @llvm.dbg.value(metadata i32* %1, metadata !39, metadata !DIExpression(DW_OP_deref)), !dbg !42
+  call void @llvm.dbg.value(metadata i32* %2, metadata !40, metadata !DIExpression(DW_OP_deref)), !dbg !42
+  %5 = call i32 @fn1(i32* nonnull %1, i32* nonnull %2), !dbg !42
+  call void @llvm.dbg.value(metadata i32 %5, metadata !41, metadata !DIExpression()), !dbg !42
+  ret i32 %5, !dbg !42
+}
+
+; Function Attrs: nounwind readnone speculatable willreturn
+declare void @llvm.dbg.value(metadata, metadata, metadata)
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 10.0.0", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, nameTableKind: None)
+!1 = !DIFile(filename: "locstats.c", directory: "/dir")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"wchar_size", i32 4}
+!6 = !{!"clang version 10.0.0"}
+!7 = distinct !DISubprogram(name: "fn1", scope: !1, file: !1, line: 5, type: !8, scopeLine: 6, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !12)
+!8 = !DISubroutineType(types: !9)
+!9 = !{!10, !11, !11}
+!10 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!11 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !10, size: 64)
+!12 = !{!13, !14, !15, !16, !17, !18}
+!13 = !DILocalVariable(name: "x", arg: 1, scope: !7, file: !1, line: 5, type: !11)
+!14 = !DILocalVariable(name: "y", arg: 2, scope: !7, file: !1, line: 5, type: !11)
+!15 = !DILocalVariable(name: "a", scope: !7, file: !1, line: 7, type: !10)
+!16 = !DILocalVariable(name: "b", scope: !7, file: !1, line: 8, type: !10)
+!17 = !DILocalVariable(name: "local", scope: !7, file: !1, line: 9, type: !10)
+!18 = !DILocalVariable(name: "local2", scope: !7, file: !1, line: 22, type: !10)
+!19 = !DILocation(line: 0, scope: !7)
+!20 = !DILocation(line: 7, column: 11, scope: !7)
+!21 = distinct !DILexicalBlock(scope: !7, file: !1, line: 10, column: 7)
+!22 = !DILocation(line: 10, column: 7, scope: !7)
+!23 = !DILocation(line: 12, column: 5, scope: !24)
+!24 = distinct !DILexicalBlock(scope: !21, file: !1, line: 10, column: 14)
+!25 = !DILocation(line: 13, column: 15, scope: !26)
+!26 = distinct !DILexicalBlock(scope: !24, file: !1, line: 13, column: 9)
+!27 = !DILocation(line: 13, column: 9, scope: !24)
+!28 = !DILocation(line: 17, column: 5, scope: !26)
+!29 = distinct !DILexicalBlock(scope: !21, file: !1, line: 15, column: 10)
+!30 = !DILocation(line: 18, column: 14, scope: !29)
+!31 = !DILocation(line: 0, scope: !21)
+!32 = !DILocation(line: 20, column: 9, scope: !33)
+!33 = distinct !DILexicalBlock(scope: !7, file: !1, line: 20, column: 7)
+!34 = !DILocation(line: 20, column: 7, scope: !7)
+!35 = distinct !DISubprogram(name: "f", scope: !1, file: !1, line: 28, type: !36, scopeLine: 29, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !38)
+!36 = !DISubroutineType(types: !37)
+!37 = !{!10}
+!38 = !{!39, !40, !41}
+!39 = !DILocalVariable(name: "l", scope: !35, file: !1, line: 30, type: !10)
+!40 = !DILocalVariable(name: "k", scope: !35, file: !1, line: 30, type: !10)
+!41 = !DILocalVariable(name: "res", scope: !35, file: !1, line: 31, type: !10)
+!42 = !DILocation(line: 30, column: 3, scope: !35)

utils/llvm-locstats/CMakeLists.txt

@@ -0,0 +1,7 @@
+if (LLVM_BUILD_UTILS AND LLVM_BUILD_TOOLS)
+  add_custom_target(llvm-locstats ALL
+    COMMAND  ${CMAKE_COMMAND} -E copy ${LLVM_MAIN_SRC_DIR}/utils/llvm-locstats/llvm-locstats.py ${LLVM_TOOLS_BINARY_DIR}/llvm-locstats
+    COMMENT "Copying llvm-locstats into ${LLVM_TOOLS_BINARY_DIR}"
+    )
+  set_target_properties(llvm-locstats PROPERTIES FOLDER "Tools")
+endif()

utils/llvm-locstats/llvm-locstats.py

@@ -0,0 +1,208 @@
+#!/usr/bin/env python
+#
+# This is a tool that works like debug location coverage calculator.
+# It parses the llvm-dwarfdump --statistics output by reporting it
+# in a more human readable way.
+#
+
+from __future__ import print_function
+import argparse
+import os
+import sys
+from json import loads
+from math import ceil
+from subprocess import Popen, PIPE
+
+def coverage_buckets():
+  yield '0%'
+  yield '1-9%'
+  for start in range(10, 91, 10):
+    yield '{0}-{1}%'.format(start, start + 9)
+  yield '100%'
+
+def locstats_output(
+  variables_total,
+  variables_total_locstats,
+  variables_with_loc,
+  scope_bytes_covered,
+  scope_bytes_from_first_def,
+  variables_coverage_map
+  ):
+
+  pc_ranges_covered = int(ceil(scope_bytes_covered * 100.0)
+              / scope_bytes_from_first_def)
+  variables_coverage_per_map = {}
+  for cov_bucket in coverage_buckets():
+    variables_coverage_per_map[cov_bucket] = \
+      int(ceil(variables_coverage_map[cov_bucket] * 100.0) \
+               / variables_total_locstats)
+
+  print (' =================================================')
+  print ('            Debug Location Statistics       ')
+  print (' =================================================')
+  print ('     cov%          samples          percentage(~)  ')
+  print (' -------------------------------------------------')
+  for cov_bucket in coverage_buckets():
+    print ('   {0:6}        {1:8d}             {2:3d}%'. \
+      format(cov_bucket, variables_coverage_map[cov_bucket], \
+             variables_coverage_per_map[cov_bucket]))
+  print (' =================================================')
+  print (' -the number of debug variables processed: ' \
+    + str(variables_total_locstats))
+  print (' -PC ranges covered: ' + str(pc_ranges_covered) + '%')
+
+  # Only if we are processing all the variables output the total
+  # availability.
+  if variables_total and variables_with_loc:
+    total_availability = int(ceil(variables_with_loc * 100.0) \
+                                  / variables_total)
+    print (' -------------------------------------------------')
+    print (' -total availability: ' + str(total_availability) + '%')
+  print (' =================================================')
+
+def parse_program_args(parser):
+  parser.add_argument('-only-variables', action='store_true',
+            default=False,
+            help='calculate the location statistics only for '
+               'local variables'
+            )
+  parser.add_argument('-only-formal-parameters', action='store_true',
+            default=False,
+            help='calculate the location statistics only for '
+               'formal parameters'
+            )
+  parser.add_argument('-ignore-debug-entry-values', action='store_true',
+            default=False,
+            help='ignore the location statistics on locations with '
+               'entry values'
+            )
+  parser.add_argument('file_name', type=str, help='file to process')
+  return parser.parse_args()
+
+
+def Main():
+  parser = argparse.ArgumentParser()
+  results = parse_program_args(parser)
+
+  if len(sys.argv) < 2:
+    print ('error: Too few arguments.')
+    parser.print_help()
+    sys.exit(1)
+
+  if results.only_variables and results.only_formal_parameters:
+    print ('error: Please use just one only* option.')
+    parser.print_help()
+    sys.exit(1)
+
+  # These will be different due to different options enabled.
+  variables_total = None
+  variables_total_locstats = None
+  variables_with_loc = None
+  variables_scope_bytes_covered = None
+  variables_scope_bytes_from_first_def = None
+  variables_scope_bytes_entry_values = None
+  variables_coverage_map = {}
+  binary = results.file_name
+
+  # Get the directory of the LLVM tools.
+  llvm_dwarfdump_cmd = os.path.join(os.path.dirname(__file__), \
+                                    "llvm-dwarfdump")
+  # The statistics llvm-dwarfdump option.
+  llvm_dwarfdump_stats_opt = "--statistics"
+
+  subproc = Popen([llvm_dwarfdump_cmd, llvm_dwarfdump_stats_opt, binary], \
+                  stdin=PIPE, stdout=PIPE, stderr=PIPE, \
+                  universal_newlines = True)
+  cmd_stdout, cmd_stderr = subproc.communicate()
+
+  # Get the JSON and parse it.
+  json_parsed = None
+
+  try:
+    json_parsed = loads(cmd_stdout)
+  except:
+    print ('error: No valid llvm-dwarfdump statistics found.')
+    sys.exit(1)
+
+  if results.only_variables:
+    # Read the JSON only for local variables.
+    variables_total_locstats = \
+      json_parsed['total vars procesed by location statistics']
+    variables_scope_bytes_covered = \
+      json_parsed['vars scope bytes covered']
+    variables_scope_bytes_from_first_def = \
+      json_parsed['vars scope bytes total']
+    if not results.ignore_debug_entry_values:
+      for cov_bucket in coverage_buckets():
+        cov_category = "vars with {} of its scope covered".format(cov_bucket)
+        variables_coverage_map[cov_bucket] = json_parsed[cov_category]
+    else:
+      variables_scope_bytes_entry_values = \
+        json_parsed['vars entry value scope bytes covered']
+      variables_scope_bytes_covered = variables_scope_bytes_covered \
+         - variables_scope_bytes_entry_values
+      for cov_bucket in coverage_buckets():
+        cov_category = \
+          "vars (excluding the debug entry values) " \
+          "with {} of its scope covered".format(cov_bucket)
+        variables_coverage_map[cov_bucket] = json_parsed[cov_category]
+  elif results.only_formal_parameters:
+    # Read the JSON only for formal parameters.
+    variables_total_locstats = \
+      json_parsed['total params procesed by location statistics']
+    variables_scope_bytes_covered = \
+      json_parsed['formal params scope bytes covered']
+    variables_scope_bytes_from_first_def = \
+      json_parsed['formal params scope bytes total']
+    if not results.ignore_debug_entry_values:
+      for cov_bucket in coverage_buckets():
+        cov_category = "params with {} of its scope covered".format(cov_bucket)
+        variables_coverage_map[cov_bucket] = json_parsed[cov_category]
+    else:
+      variables_scope_bytes_entry_values = \
+        json_parsed['formal params entry value scope bytes covered']
+      variables_scope_bytes_covered = variables_scope_bytes_covered \
+        - variables_scope_bytes_entry_values
+      for cov_bucket in coverage_buckets():
+        cov_category = \
+          "params (excluding the debug entry values) " \
+          "with {} of its scope covered".format(cov_bucket)
+  else:
+    # Read the JSON for both local variables and formal parameters.
+    variables_total = \
+      json_parsed['source variables']
+    variables_with_loc = json_parsed['variables with location']
+    variables_total_locstats = \
+      json_parsed['total variables procesed by location statistics']
+    variables_scope_bytes_covered = \
+      json_parsed['scope bytes covered']
+    variables_scope_bytes_from_first_def = \
+      json_parsed['scope bytes total']
+    if not results.ignore_debug_entry_values:
+      for cov_bucket in coverage_buckets():
+        cov_category = "variables with {} of its scope covered". \
+                       format(cov_bucket)
+        variables_coverage_map[cov_bucket] = json_parsed[cov_category]
+    else:
+      variables_scope_bytes_entry_values = \
+        json_parsed['entry value scope bytes covered']
+      variables_scope_bytes_covered = variables_scope_bytes_covered \
+        - variables_scope_bytes_entry_values
+      for cov_bucket in coverage_buckets():
+        cov_category = "variables (excluding the debug entry values) " \
+                       "with {} of its scope covered". format(cov_bucket)
+        variables_coverage_map[cov_bucket] = json_parsed[cov_category]
+
+  # Pretty print collected info.
+  locstats_output(
+    variables_total,
+    variables_total_locstats,
+    variables_with_loc,
+    variables_scope_bytes_covered,
+    variables_scope_bytes_from_first_def,
+    variables_coverage_map
+    )
+
+if __name__ == '__main__':
+  Main()
+  sys.exit(0)