Index: ELF/OutputSections.h
===================================================================
--- ELF/OutputSections.h
+++ ELF/OutputSections.h
@@ -120,7 +120,7 @@
   void addEntry(SymbolBody *Sym);
   bool addDynTlsEntry(SymbolBody *Sym);
   bool addCurrentModuleTlsIndex();
-  bool empty() const { return Entries.empty(); }
+  bool leaveInOutput() const { return Demanded || !Entries.empty(); }
   uintX_t getEntryAddr(const SymbolBody &B) const;
   uintX_t getGlobalDynAddr(const SymbolBody &B) const;
   uintX_t getNumEntries() const { return Entries.size(); }
@@ -137,6 +137,7 @@
 
   uint32_t getLocalTlsIndexVA() { return Base::getVA() + LocalTlsIndexOff; }
 
+  bool Demanded = false;
 private:
   std::vector<const SymbolBody *> Entries;
   uint32_t LocalTlsIndexOff = -1;
Index: ELF/Target.h
===================================================================
--- ELF/Target.h
+++ ELF/Target.h
@@ -59,6 +59,7 @@
   virtual void relocateOne(uint8_t *Loc, uint8_t *BufEnd, uint32_t Type,
                            uint64_t P, uint64_t SA,
                            uint8_t *PairedLoc = nullptr) const = 0;
+  virtual bool relocUsesGotAddr(uint32_t Type) const;
   virtual bool isTlsOptimized(unsigned Type, const SymbolBody *S) const;
   virtual unsigned relocateTlsOptimize(uint8_t *Loc, uint8_t *BufEnd,
                                        uint32_t Type, uint64_t P, uint64_t SA,
Index: ELF/Target.cpp
===================================================================
--- ELF/Target.cpp
+++ ELF/Target.cpp
@@ -92,6 +92,7 @@
   unsigned relocateTlsOptimize(uint8_t *Loc, uint8_t *BufEnd, uint32_t Type,
                                uint64_t P, uint64_t SA,
                                const SymbolBody &S) const override;
+  bool relocUsesGotAddr(uint32_t Type) const override;
 
 private:
   void relocateTlsLdToLe(uint8_t *Loc, uint8_t *BufEnd, uint64_t P,
@@ -224,6 +225,8 @@
   return false;
 }
 
+bool TargetInfo::relocUsesGotAddr(uint32_t Type) const { return false; }
+
 unsigned TargetInfo::getPltRefReloc(unsigned Type) const { return PCRelReloc; }
 
 bool TargetInfo::isRelRelative(uint32_t Type) const { return true; }
@@ -336,6 +339,13 @@
   return Type == R_386_PLT32 || (Type == R_386_PC32 && S.isShared());
 }
 
+bool X86TargetInfo::relocUsesGotAddr(uint32_t Type) const {
+  // This relocation does not require got entry,
+  // but it is relative to got and needs it to be created.
+  // Here we request for that.
+  return Type == R_386_GOTOFF;
+}
+
 void X86TargetInfo::relocateOne(uint8_t *Loc, uint8_t *BufEnd, uint32_t Type,
                                 uint64_t P, uint64_t SA,
                                 uint8_t *PairedLoc) const {
@@ -344,6 +354,7 @@
     add32le(Loc, SA);
     break;
   case R_386_GOT32:
+  case R_386_GOTOFF:
     add32le(Loc, SA - Out<ELF32LE>::Got->getVA());
     break;
   case R_386_GOTPC:
Index: ELF/Writer.cpp
===================================================================
--- ELF/Writer.cpp
+++ ELF/Writer.cpp
@@ -202,6 +202,9 @@
     SymbolBody *Body = File.getSymbolBody(SymIndex);
     uint32_t Type = RI.getType(Config->Mips64EL);
 
+    if (Target->relocUsesGotAddr(Type))
+      Out<ELF32LE>::Got->Demanded = true;
+
     if (Target->isTlsLocalDynamicReloc(Type)) {
       if (Target->isTlsOptimized(Type, nullptr))
         continue;
@@ -743,8 +746,10 @@
 
   // We add the .got section to the result for dynamic MIPS target because
   // its address and properties are mentioned in the .dynamic section.
-  if (!Out<ELFT>::Got->empty() ||
-      (isOutputDynamic() && Config->EMachine == EM_MIPS))
+  Out<ELFT>::Got->Demanded |=
+      (isOutputDynamic() && Config->EMachine == EM_MIPS);
+
+  if (Out<ELFT>::Got->leaveInOutput())
     OutputSections.push_back(Out<ELFT>::Got);
   if (Out<ELFT>::GotPlt && !Out<ELFT>::GotPlt->empty())
     OutputSections.push_back(Out<ELFT>::GotPlt);
Index: test/ELF/got-i386.s
===================================================================
--- test/ELF/got-i386.s
+++ test/ELF/got-i386.s
@@ -0,0 +1,56 @@
+// RUN: llvm-mc -filetype=obj -triple=i686-unknown-linux %s -o %t.o
+// RUN: ld.lld %t.o -o %t
+// RUN: llvm-readobj -s -r -t %t | FileCheck %s
+// RUN: llvm-objdump -d %t | FileCheck --check-prefix=DISASM %s
+// REQUIRES: x86
+
+// CHECK:      Name: .got
+// CHECK-NEXT: Type: SHT_PROGBITS
+// CHECK-NEXT: Flags [
+// CHECK-NEXT:   SHF_ALLOC
+// CHECK-NEXT:   SHF_WRITE
+// CHECK-NEXT: ]
+// CHECK-NEXT: Address: 0x12000
+// CHECK-NEXT: Offset:
+// CHECK-NEXT: Size: 0
+// CHECK-NEXT: Link:
+// CHECK-NEXT: Info:
+// CHECK-NEXT: AddressAlignment:
+
+// CHECK:      Symbol {
+// CHECK:       Name: bar
+// CHECK-NEXT:  Value: 0x12000
+// CHECK-NEXT:  Size: 10
+// CHECK-NEXT:  Binding: Global
+// CHECK-NEXT:  Type: Object
+// CHECK-NEXT:  Other: 0
+// CHECK-NEXT:  Section: .bss
+// CHECK-NEXT: }
+// CHECK-NEXT: Symbol {
+// CHECK-NEXT:  Name: obj
+// CHECK-NEXT:  Value: 0x1200A
+// CHECK-NEXT:  Size: 10
+// CHECK-NEXT:  Binding: Global
+// CHECK-NEXT:  Type: Object
+// CHECK-NEXT:  Other: 0
+// CHECK-NEXT:  Section: .bss
+// CHECK-NEXT: }
+
+// 0x12000 - 0 = addr(.got) = 0x12000
+// 0x1200A - 10 = addr(.got) = 0x12000
+// 0x1200A + 5 - 15 = addr(.got) = 0x12000
+// DISASM:      Disassembly of section .text:
+// DISASM-NEXT: _start:
+// DISASM-NEXT: 11000: c7 81 00 00 00 00 01 00 00 00 movl $1, (%ecx)
+// DISASM-NEXT: 1100a: c7 81 0a 00 00 00 02 00 00 00 movl $2, 10(%ecx)
+// DISASM-NEXT: 11014: c7 81 0f 00 00 00 03 00 00 00 movl $3, 15(%ecx)
+
+.global _start
+_start:
+  movl $1, bar@GOTOFF(%ecx)
+  movl $2, obj@GOTOFF(%ecx)
+  movl $3, obj+5@GOTOFF(%ecx)
+  .type bar, @object
+  .comm bar, 10
+  .type obj, @object
+  .comm obj, 10