diff --git a/llvm/lib/MC/MCAsmStreamer.cpp b/llvm/lib/MC/MCAsmStreamer.cpp
--- a/llvm/lib/MC/MCAsmStreamer.cpp
+++ b/llvm/lib/MC/MCAsmStreamer.cpp
@@ -27,6 +27,7 @@
 #include "llvm/MC/MCRegister.h"
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCSectionMachO.h"
+#include "llvm/MC/MCSectionXCOFF.h"
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/MC/MCSymbolXCOFF.h"
 #include "llvm/MC/TargetRegistry.h"
@@ -937,6 +938,17 @@
 }
 
 void MCAsmStreamer::emitXCOFFRefDirective(StringRef Name) {
+  assert([&]() -> bool {
+    MCSectionXCOFF *CS = cast<MCSectionXCOFF>(getCurrentSectionOnly());
+    return CS && CS->getCSectType() == XCOFF::XTY_SD &&
+           CS->getMappingClass() != XCOFF::XMC_BS &&
+           CS->getMappingClass() != XCOFF::XMC_UC;
+  }() && "The .ref pseudo-op cannot be included in a csect with a storage "
+         "mapping class of BS or UC");
+  assert(
+      !(Name.endswith_insensitive("[bs]") ||
+        Name.endswith_insensitive("[uc]")) &&
+      ".ref operand cannot be a name with storage mapping class of BS or UC");
   OS << "\t.ref " << Name;
   EmitEOL();
 }
diff --git a/llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp b/llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp
--- a/llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp
+++ b/llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp
@@ -142,6 +142,8 @@
   const PPCSubtarget *Subtarget = nullptr;
   StackMaps SM;
 
+  virtual void trackTOCRef(const MCSymbol *Sym) {}
+
 public:
   explicit PPCAsmPrinter(TargetMachine &TM,
                          std::unique_ptr<MCStreamer> Streamer)
@@ -223,6 +225,20 @@
   DenseMap<const GlobalObject *, SmallVector<const GlobalAlias *, 1>>
       GOAliasMap;
 
+  // To support `-bcdtors:csect` on AIX, clang handles .ref regarding variable
+  // and corresponding init/term functions. In addition, we need to generate
+  // .ref from program code to internal global variables for safety reason
+  // consider following case: one internal global variable with init function
+  // which produces side effect, but that variable is not referenced by any
+  // function; without .ref from program code to the variable, the side effect
+  // could be missed after link. We put all target internal GV in
+  // InternalGlobalRW, keep track of function touched GV in FuncBodyTouchedTOC,
+  // and finally generate .ref for those not touched.
+  SmallVector<const MCSymbolXCOFF *, 8> InternalGlobalRW;
+  SmallSet<const MCSymbolXCOFF *, 8> FuncBodyTouchedTOC;
+  bool IsTextEmpty = true;
+  bool IsFuncBodyTOC = false;
+
   uint16_t getNumberOfVRSaved();
   void emitTracebackTable();
 
@@ -233,6 +249,14 @@
   // Get the offset of an alias based on its AliaseeObject.
   uint64_t getAliasOffset(const Constant *C);
 
+  void emitAssociatedRefs(const GlobalObject &);
+
+  void trackTOCRef(const MCSymbol *Sym) override {
+    if (IsFuncBodyTOC)
+      if (const auto *S = dyn_cast<const MCSymbolXCOFF>(Sym))
+        FuncBodyTouchedTOC.insert(S);
+  }
+
 public:
   PPCAIXAsmPrinter(TargetMachine &TM, std::unique_ptr<MCStreamer> Streamer)
       : PPCAsmPrinter(TM, std::move(Streamer)) {
@@ -256,6 +280,8 @@
 
   void emitFunctionEntryLabel() override;
 
+  void emitFunctionBodyStart() override { IsFuncBodyTOC = true; }
+
   void emitFunctionBodyEnd() override;
 
   void emitPGORefs();
@@ -421,6 +447,7 @@
 MCSymbol *
 PPCAsmPrinter::lookUpOrCreateTOCEntry(const MCSymbol *Sym,
                                       MCSymbolRefExpr::VariantKind Kind) {
+  trackTOCRef(Sym);
   MCSymbol *&TOCEntry = TOC[{Sym, Kind}];
   if (!TOCEntry)
     TOCEntry = createTempSymbol("C");
@@ -1953,6 +1980,15 @@
 }
 
 void PPCAIXAsmPrinter::emitFunctionBodyEnd() {
+  IsTextEmpty = false;
+  if (TM.getFunctionSections()) {
+    for (auto I = InternalGlobalRW.begin(), E = InternalGlobalRW.end(); I != E;
+         ++I)
+      if (!FuncBodyTouchedTOC.contains(*I))
+        OutStreamer->emitXCOFFRefDirective((*I)->getName());
+    FuncBodyTouchedTOC.clear();
+  }
+  IsFuncBodyTOC = false;
 
   if (!TM.getXCOFFTracebackTable())
     return;
@@ -2444,6 +2480,8 @@
 
   MCSymbol *EmittedInitSym = GVSym;
 
+  emitAssociatedRefs(*GV);
+
   // Emit linkage for the global variable and its aliases.
   emitLinkage(GV, EmittedInitSym);
   for (const GlobalAlias *GA : GOAliasMap[GV])
@@ -2473,6 +2511,26 @@
                      &AliasList);
 }
 
+void PPCAIXAsmPrinter::emitAssociatedRefs(const GlobalObject &GO) {
+  MDNode *MD = GO.getMetadata(LLVMContext::MD_associated);
+  if (!MD)
+    return;
+
+  for (unsigned i = 0, e = MD->getNumOperands(); i != e; ++i) {
+    const MDOperand &Op = MD->getOperand(i);
+    if (!Op.get())
+      continue;
+
+    const auto *VM = dyn_cast<ValueAsMetadata>(Op);
+    if (!VM)
+      report_fatal_error("MD_associated operand is not ValueAsMetadata");
+
+    if (const auto *OtherGV = dyn_cast<GlobalValue>(VM->getValue()))
+      if (OtherGV != &GO)
+        OutStreamer->emitXCOFFRefDirective(getSymbol(OtherGV)->getName());
+  }
+}
+
 void PPCAIXAsmPrinter::emitFunctionDescriptor() {
   const DataLayout &DL = getDataLayout();
   const unsigned PointerSize = DL.getPointerSizeInBits() == 64 ? 8 : 4;
@@ -2486,6 +2544,9 @@
   for (const GlobalAlias *Alias : GOAliasMap[&MF->getFunction()])
     OutStreamer->emitLabel(getSymbol(Alias));
 
+  // Emit .ref from dtor to term function
+  emitAssociatedRefs(MF->getFunction());
+
   // Emit function entry point address.
   OutStreamer->emitValue(MCSymbolRefExpr::create(CurrentFnSym, OutContext),
                          PointerSize);
@@ -2643,6 +2704,15 @@
     GOAliasMap[Base].push_back(&Alias);
   }
 
+  // Collect all LGLOBAL located inside {RW} mapping class for .ref
+  for (const auto &G : M.globals())
+    if (G.getLinkage() == GlobalValue::InternalLinkage ||
+        G.getLinkage() == GlobalValue::PrivateLinkage) {
+      SectionKind GVKind = getObjFileLowering().getKindForGlobal(&G, TM);
+      if (GVKind.isData() || GVKind.isReadOnlyWithRel())
+        InternalGlobalRW.push_back(cast<const MCSymbolXCOFF>(getSymbol(&G)));
+    }
+
   return Result;
 }
 
@@ -2707,6 +2777,17 @@
 
   for (MCSymbol *Sym : ExtSymSDNodeSymbols)
     OutStreamer->emitSymbolAttribute(Sym, MCSA_Extern);
+
+  // Do not generate .ref for empty .text{PR}
+  if (!TM.getFunctionSections() && !IsTextEmpty) {
+    for (auto I = InternalGlobalRW.begin(), E = InternalGlobalRW.end(); I != E;
+         ++I)
+      if (!FuncBodyTouchedTOC.contains(*I))
+        OutStreamer->emitXCOFFRefDirective((*I)->getName());
+  }
+  InternalGlobalRW.clear();
+  FuncBodyTouchedTOC.clear();
+
   return PPCAsmPrinter::doFinalization(M);
 }
 
diff --git a/llvm/lib/Target/TargetLoweringObjectFile.cpp b/llvm/lib/Target/TargetLoweringObjectFile.cpp
--- a/llvm/lib/Target/TargetLoweringObjectFile.cpp
+++ b/llvm/lib/Target/TargetLoweringObjectFile.cpp
@@ -233,9 +233,14 @@
   // Most non-mergeable zero data can be put in the BSS section unless otherwise
   // specified.
   if (isSuitableForBSS(GVar) && !TM.Options.NoZerosInBSS) {
-    if (GVar->hasLocalLinkage())
+    if (GVar->hasLocalLinkage()) {
+      // AIX XCOFF with associated metadata is part of .ref pseudo-op, should be
+      // classified as Data.
+      if (TM.getTargetTriple().isOSAIX() &&
+          GVar->getMetadata(LLVMContext::MD_associated))
+        return SectionKind::getData();
       return SectionKind::getBSSLocal();
-    else if (GVar->hasExternalLinkage())
+    } else if (GVar->hasExternalLinkage())
       return SectionKind::getBSSExtern();
     return SectionKind::getBSS();
   }
diff --git a/llvm/test/CodeGen/PowerPC/aix-xcoff-ref-empty-text.ll b/llvm/test/CodeGen/PowerPC/aix-xcoff-ref-empty-text.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/aix-xcoff-ref-empty-text.ll
@@ -0,0 +1,8 @@
+; RUN: llc -mtriple powerpc-ibm-aix-xcoff -mcpu=pwr9 --filetype=asm < %s | FileCheck %s --check-prefix=CHECK
+
+@a = internal global i32 3, align 4
+@b = internal global i32 6, align 4
+@c = internal global i32 9, align 4
+
+; CHECK:      .csect .text[PR],5
+; CHECK-NOT:  .ref
diff --git a/llvm/test/CodeGen/PowerPC/aix-xcoff-ref.ll b/llvm/test/CodeGen/PowerPC/aix-xcoff-ref.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/aix-xcoff-ref.ll
@@ -0,0 +1,71 @@
+; RUN: llc -mtriple powerpc-ibm-aix-xcoff -mcpu=pwr9 --function-sections --filetype=asm < %s | FileCheck %s --check-prefixes=CHECK-FS,CHECK
+; RUN: llc -mtriple powerpc-ibm-aix-xcoff -mcpu=pwr9 --filetype=asm < %s | FileCheck %s --check-prefixes=CHECK-NFS,CHECK
+
+@a = internal global i32 0, align 4, !associated !0
+@b = internal global i32 3, align 4
+@c = internal global i32 0, align 4
+@d = internal global i32 3, align 4, !associated !2
+
+define i32 @foo() {
+entry:
+  %0 = load i32, ptr @a, align 4
+  ret i32 %0
+}
+
+define void @bar() {
+entry:
+  ret void
+}
+
+define void @baz() !associated !1 {
+entry:
+  ret void
+}
+
+!0 = !{i32 ()* @foo, void ()* @bar}
+!1 = !{void ()* @bar}
+!2 = distinct !{null}
+
+; CHECK-FS:         .csect .foo[PR],5
+; CHECK-FS:         .csect .foo[PR],5
+; CHECK-FS-NEXT:    # %bb.0:                                # %entry
+; CHECK-FS-NEXT:    lwz 3, L..C0(2)                         # @a
+; CHECK-FS-NEXT:    lwz 3, 0(3)
+; CHECK-FS-NEXT:    blr
+; CHECK-FS-NEXT:    .ref b[RW]
+; CHECK-FS-NEXT:    .ref d[RW]
+
+; CHECK-FS:         .csect .bar[PR],5
+; CHECK-FS:         .csect .bar[PR],5
+; CHECK-FS-NEXT:    # %bb.0:                                # %entry
+; CHECK-FS-NEXT:    blr
+; CHECK-FS-NEXT:    .ref a[RW]
+; CHECK-FS-NEXT:    .ref b[RW]
+; CHECK-FS-NEXT:    .ref d[RW]
+
+; CHECK-FS:         .csect baz[DS],2
+; CHECK-FS-NEXT:    .ref bar[DS]                            # @baz
+; CHECK-FS:         .csect .baz[PR],5
+; CHECK-FS-NEXT:    # %bb.0:                                # %entry
+; CHECK-FS-NEXT:    blr
+; CHECK-FS-NEXT:    .ref a[RW]
+; CHECK-FS-NEXT:    .ref b[RW]
+; CHECK-FS-NEXT:    .ref d[RW]
+
+; CHECK-NFS:        .csect baz[DS],2
+; CHECK-NFS-NEXT:   .ref bar[DS]                            # @baz
+
+; The whole .text{PR} has one .ref points to b[RW] and d[RW]
+; CHECK-NFS:        .byte   "baz"                           # Function Name
+; CHECK-NFS-NEXT:                                           # -- End function
+; CHECK-NFS-NEXT:   .ref b[RW]
+; CHECK-NFS-NEXT:   .ref d[RW]
+
+; CHECK:            .csect a[RW],2
+; CHECK-NEXT:       .ref foo[DS]                            # @a
+; CHECK-NEXT:       .ref bar[DS]
+
+; CHECK:            .lcomm  c,4,c[BS],2                     # @c
+
+; CHECK:           .csect d[RW],2
+; CHECK:           .lglobl d[RW]                           # @d