[misexpect] Re-implement MisExpect Diagnostics

Reimplements MisExpect diagnostics from D66324 to reconstruct its
original checking methodology only using MD_prof branch_weights
metadata.

New checks rely on 2 invariants:

1) For frontend instrumentation, MD_prof branch_weights will always be
   populated before llvm.expect intrinsics are lowered.

2) for IR and sample profiling, llvm.expect intrinsics will always be
   lowered before branch_weights are populated from the IR profiles.

These invariants allow the checking to assume how the existing branch
weights are populated depending on the profiling method used, and emit
the correct diagnostics. If these invariants are ever invalidated, the
MisExpect related checks would need to be updated, potentially by
re-introducing MD_misexpect metadata, and ensuring it always will be
transformed the same way as branch_weights in other optimization passes.

Frontend based profiling is now enabled without using LLVM Args, by
introducing a new CodeGen option, and checking if the -Wmisexpect flag
has been passed on the command line.

Reviewed By: tejohnson

Differential Revision: https://reviews.llvm.org/D115907

1 files changed, 41 insertions, 0 deletions

diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index f8fd3a29..714660f 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -107,6 +107,20 @@ using namespace options;
 using namespace llvm::opt;
 
 //===----------------------------------------------------------------------===//
+// Helpers.
+//===----------------------------------------------------------------------===//
+
+// Parse misexpect tolerance argument value.
+// Valid option values are integers in the range [0, 100)
+inline Expected<Optional<uint64_t>> parseToleranceOption(StringRef Arg) {
+  int64_t Val;
+  if (Arg.getAsInteger(10, Val))
+    return llvm::createStringError(llvm::inconvertibleErrorCode(),
+                                   "Not an integer: %s", Arg.data());
+  return Val;
+}
+
+//===----------------------------------------------------------------------===//
 // Initialization.
 //===----------------------------------------------------------------------===//
 
@@ -1535,6 +1549,9 @@ void CompilerInvocation::GenerateCodeGenArgs(
                   : "auto",
               SA);
 
+  GenerateArg(Args, OPT_fdiagnostics_misexpect_tolerance_EQ,
+              Twine(*Opts.DiagnosticsMisExpectTolerance), SA);
+
   for (StringRef Sanitizer : serializeSanitizerKinds(Opts.SanitizeRecover))
     GenerateArg(Args, OPT_fsanitize_recover_EQ, Sanitizer, SA);
 
@@ -1952,6 +1969,23 @@ bool CompilerInvocation::ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args,
     }
   }
 
+  if (auto *arg =
+          Args.getLastArg(options::OPT_fdiagnostics_misexpect_tolerance_EQ)) {
+    auto ResultOrErr = parseToleranceOption(arg->getValue());
+
+    if (!ResultOrErr) {
+      Diags.Report(diag::err_drv_invalid_diagnotics_misexpect_tolerance)
+          << "-fdiagnostics-misexpect-tolerance=";
+    } else {
+      Opts.DiagnosticsMisExpectTolerance = *ResultOrErr;
+      if ((!Opts.DiagnosticsMisExpectTolerance.hasValue() ||
+           Opts.DiagnosticsMisExpectTolerance.getValue() > 0) &&
+          !UsingProfile)
+        Diags.Report(diag::warn_drv_diagnostics_misexpect_requires_pgo)
+            << "-fdiagnostics-misexpect-tolerance=";
+    }
+  }
+
   // If the user requested to use a sample profile for PGO, then the
   // backend will need to track source location information so the profile
   // can be incorporated into the IR.
@@ -4577,6 +4611,13 @@ bool CompilerInvocation::CreateFromArgsImpl(
   if (Res.getFrontendOpts().ProgramAction == frontend::RewriteObjC)
     LangOpts.ObjCExceptions = 1;
 
+  for (auto Warning : Res.getDiagnosticOpts().Warnings) {
+    if (Warning == "misexpect" &&
+        !Diags.isIgnored(diag::warn_profile_data_misexpect, SourceLocation())) {
+      Res.getCodeGenOpts().MisExpect = true;
+    }
+  }
+
   if (LangOpts.CUDA) {
     // During CUDA device-side compilation, the aux triple is the
     // triple used for host compilation.