3 files changed, 48 insertions, 2 deletions

diff --git a/clang/lib/CodeGen/CGRecordLayoutBuilder.cpp b/clang/lib/CodeGen/CGRecordLayoutBuilder.cpp
index 7d530a278fb..1644ab4c072 100644
--- a/clang/lib/CodeGen/CGRecordLayoutBuilder.cpp
+++ b/clang/lib/CodeGen/CGRecordLayoutBuilder.cpp
@@ -403,6 +403,27 @@ CGRecordLowering::accumulateBitFields(RecordDecl::field_iterator Field,
     }
     return;
   }
+
+  // Check if current Field is better as a single field run. When current field
+  // has legal integer width, and its bitfield offset is naturally aligned, it
+  // is better to make the bitfield a separate storage component so as it can be
+  // accessed directly with lower cost.
+  auto IsBetterAsSingleFieldRun = [&](RecordDecl::field_iterator Field) {
+    if (!Types.getCodeGenOpts().FineGrainedBitfieldAccesses)
+      return false;
+    unsigned Width = Field->getBitWidthValue(Context);
+    if (!DataLayout.isLegalInteger(Width))
+      return false;
+    // Make sure Field is natually aligned if it is treated as an IType integer.
+    if (getFieldBitOffset(*Field) %
+            Context.toBits(getAlignment(getIntNType(Width))) !=
+        0)
+      return false;
+    return true;
+  };
+
+  // The start field is better as a single field run.
+  bool StartFieldAsSingleRun = false;
   for (;;) {
     // Check to see if we need to start a new run.
     if (Run == FieldEnd) {
@@ -414,17 +435,28 @@ CGRecordLowering::accumulateBitFields(RecordDecl::field_iterator Field,
         Run = Field;
         StartBitOffset = getFieldBitOffset(*Field);
         Tail = StartBitOffset + Field->getBitWidthValue(Context);
+        StartFieldAsSingleRun = IsBetterAsSingleFieldRun(Run);
       }
       ++Field;
       continue;
     }
-    // Add bitfields to the run as long as they qualify.
-    if (Field != FieldEnd && Field->getBitWidthValue(Context) != 0 &&
+
+    // If the start field of a new run is better as a single run, or
+    // if current field is better as a single run, or
+    // if current field has zero width bitfield, or
+    // if the offset of current field is inconsistent with the offset of
+    // previous field plus its offset,
+    // skip the block below and go ahead to emit the storage.
+    // Otherwise, try to add bitfields to the run.
+    if (!StartFieldAsSingleRun && Field != FieldEnd &&
+        !IsBetterAsSingleFieldRun(Field) &&
+        Field->getBitWidthValue(Context) != 0 &&
         Tail == getFieldBitOffset(*Field)) {
       Tail += Field->getBitWidthValue(Context);
       ++Field;
       continue;
     }
+
     // We've hit a break-point in the run and need to emit a storage field.
     llvm::Type *Type = getIntNType(Tail - StartBitOffset);
     // Add the storage member to the record and set the bitfield info for all of
@@ -435,6 +467,7 @@ CGRecordLowering::accumulateBitFields(RecordDecl::field_iterator Field,
       Members.push_back(MemberInfo(bitsToCharUnits(StartBitOffset),
                                    MemberInfo::Field, nullptr, *Run));
     Run = FieldEnd;
+    StartFieldAsSingleRun = false;
   }
 }
 
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index f0f2bc21986..aeec477b88d 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -3365,6 +3365,9 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
                     options::OPT_fno_optimize_sibling_calls))
     CmdArgs.push_back("-mdisable-tail-calls");
 
+  Args.AddLastArg(CmdArgs, options::OPT_ffine_grained_bitfield_accesses,
+                  options::OPT_fno_fine_grained_bitfield_accesses);
+
   // Handle segmented stacks.
   if (Args.hasArg(options::OPT_fsplit_stack))
     CmdArgs.push_back("-split-stacks");
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index 9a4fc774f47..19e26c18bfd 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -546,6 +546,9 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
     OPT_fuse_register_sized_bitfield_access);
   Opts.RelaxedAliasing = Args.hasArg(OPT_relaxed_aliasing);
   Opts.StructPathTBAA = !Args.hasArg(OPT_no_struct_path_tbaa);
+  Opts.FineGrainedBitfieldAccesses =
+      Args.hasFlag(OPT_ffine_grained_bitfield_accesses,
+                   OPT_fno_fine_grained_bitfield_accesses, false);
   Opts.DwarfDebugFlags = Args.getLastArgValue(OPT_dwarf_debug_flags);
   Opts.MergeAllConstants = !Args.hasArg(OPT_fno_merge_all_constants);
   Opts.NoCommon = Args.hasArg(OPT_fno_common);
@@ -2763,6 +2766,13 @@ bool CompilerInvocation::CreateFromArgs(CompilerInvocation &Res,
   if (Arch == llvm::Triple::spir || Arch == llvm::Triple::spir64) {
     Res.getDiagnosticOpts().Warnings.push_back("spir-compat");
   }
+
+  // If sanitizer is enabled, disable OPT_ffine_grained_bitfield_accesses.
+  if (Res.getCodeGenOpts().FineGrainedBitfieldAccesses &&
+      !Res.getLangOpts()->Sanitize.empty()) {
+    Res.getCodeGenOpts().FineGrainedBitfieldAccesses = false;
+    Diags.Report(diag::warn_drv_fine_grained_bitfield_accesses_ignored);
+  }
   return Success;
 }