Index: include/llvm/Target/TargetOptions.h
===================================================================
--- include/llvm/Target/TargetOptions.h
+++ include/llvm/Target/TargetOptions.h
@@ -108,7 +108,7 @@
           DisableIntegratedAS(false), CompressDebugSections(false),
           RelaxELFRelocations(false), FunctionSections(false),
           DataSections(false), UniqueSectionNames(true), TrapUnreachable(false),
-          EmulatedTLS(false), EnableIPRA(false),
+          EmulatedTLS(false), EnableIPRA(false), DebugInfoForProfiling(false),
           FloatABIType(FloatABI::Default),
           AllowFPOpFusion(FPOpFusion::Standard),
           ThreadModel(ThreadModel::POSIX),
@@ -225,6 +225,9 @@
     /// This flag enables InterProcedural Register Allocation (IPRA).
     unsigned EnableIPRA : 1;
 
+    /// This flag enables emitting extra debug info for sample profiling.
+    unsigned DebugInfoForProfiling : 1;
+
     /// FloatABIType - This setting is set by -float-abi=xxx option is specfied
     /// on the command line. This setting may either be Default, Soft, or Hard.
     /// Default selects the target's default behavior. Soft selects the ABI for
@@ -299,7 +302,8 @@
     ARE_EQUAL(FPDenormalMode) &&
     ARE_EQUAL(ExceptionModel) &&
     ARE_EQUAL(MCOptions) &&
-    ARE_EQUAL(EnableIPRA);
+    ARE_EQUAL(EnableIPRA) &&
+    ARE_EQUAL(DebugInfoForProfiling);
 #undef ARE_EQUAL
 }
 
Index: lib/CodeGen/AsmPrinter/DwarfDebug.cpp
===================================================================
--- lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ lib/CodeGen/AsmPrinter/DwarfDebug.cpp
@@ -1184,8 +1184,10 @@
   TheCU.addRange(RangeSpan(Asm->getFunctionBegin(), Asm->getFunctionEnd()));
 
   // Under -gmlt, skip building the subprogram if there are no inlined
-  // subroutines inside it.
-  if (TheCU.getCUNode()->getEmissionKind() == DICompileUnit::LineTablesOnly &&
+  // subroutines inside it. But with -fdebug-info-for-profiling, the subprogram
+  // is still needed as we need its source location.
+  if (!Asm->TM.Options.DebugInfoForProfiling &&
+      TheCU.getCUNode()->getEmissionKind() == DICompileUnit::LineTablesOnly &&
       LScopes.getAbstractScopesList().empty() && !IsDarwin) {
     assert(InfoHolder.getScopeVariables().empty());
     assert(DbgValues.empty());
Index: lib/CodeGen/AsmPrinter/DwarfUnit.h
===================================================================
--- lib/CodeGen/AsmPrinter/DwarfUnit.h
+++ lib/CodeGen/AsmPrinter/DwarfUnit.h
@@ -256,7 +256,7 @@
   DIE *getOrCreateSubprogramDIE(const DISubprogram *SP, bool Minimal = false);
 
   void applySubprogramAttributes(const DISubprogram *SP, DIE &SPDie,
-                                 bool Minimal = false);
+                                 bool SkipSPAttributes = false);
 
   /// Find existing DIE or create new DIE for the given type.
   DIE *getOrCreateTypeDIE(const MDNode *N);
Index: lib/CodeGen/AsmPrinter/DwarfUnit.cpp
===================================================================
--- lib/CodeGen/AsmPrinter/DwarfUnit.cpp
+++ lib/CodeGen/AsmPrinter/DwarfUnit.cpp
@@ -1178,8 +1178,12 @@
 }
 
 void DwarfUnit::applySubprogramAttributes(const DISubprogram *SP, DIE &SPDie,
-                                          bool Minimal) {
-  if (!Minimal)
+                                          bool SkipSPAttributes) {
+  // If -fdebug-info-for-profiling is enabled, need to emit the subprogram
+  // and its source location.
+  bool SkipSPSourceLocation = SkipSPAttributes &&
+                              !Asm->TM.Options.DebugInfoForProfiling;
+  if (!SkipSPSourceLocation)
     if (applySubprogramDefinitionAttributes(SP, SPDie))
       return;
 
@@ -1187,12 +1191,13 @@
   if (!SP->getName().empty())
     addString(SPDie, dwarf::DW_AT_name, SP->getName());
 
+  if (!SkipSPSourceLocation)
+    addSourceLine(SPDie, SP);
+
   // Skip the rest of the attributes under -gmlt to save space.
-  if (Minimal)
+  if (SkipSPAttributes)
     return;
 
-  addSourceLine(SPDie, SP);
-
   // Add the prototype if we have a prototype and we have a C like
   // language.
   uint16_t Language = getLanguage();
Index: lib/Target/TargetMachine.cpp
===================================================================
--- lib/Target/TargetMachine.cpp
+++ lib/Target/TargetMachine.cpp
@@ -35,6 +35,10 @@
                          cl::desc("Enable interprocedural register allocation "
                                   "to reduce load/store at procedure calls."));
 
+cl::opt<bool> DebugInfoForProfiling(
+    "debug-info-for-profiling", cl::init(false), cl::Hidden,
+    cl::desc("Emit extra debug info to make sample profile more accurate."));
+
 //---------------------------------------------------------------------------
 // TargetMachine Class
 //
@@ -47,6 +51,8 @@
       RequireStructuredCFG(false), Options(Options) {
   if (EnableIPRA.getNumOccurrences())
     this->Options.EnableIPRA = EnableIPRA;
+  if (DebugInfoForProfiling.getNumOccurrences())
+    this->Options.DebugInfoForProfiling = DebugInfoForProfiling;
 }
 
 TargetMachine::~TargetMachine() {
Index: test/DebugInfo/Generic/gmlt.test
===================================================================
--- test/DebugInfo/Generic/gmlt.test
+++ test/DebugInfo/Generic/gmlt.test
@@ -1,5 +1,6 @@
 ; REQUIRES: object-emission
 ; RUN: %llc_dwarf -O0 -filetype=obj < %S/../Inputs/gmlt.ll | llvm-dwarfdump - | FileCheck %S/../Inputs/gmlt.ll
+; RUN: %llc_dwarf -O0 -filetype=obj -debug-info-for-profiling < %S/../Inputs/gmlt.ll | llvm-dwarfdump - | FileCheck %S/../Inputs/gmlt.ll --check-prefixes=PROFILING
 
 ; There's a darwin specific test in X86/gmlt, so it's okay to XFAIL this here.
 ; XFAIL: darwin
Index: test/DebugInfo/Inputs/gmlt.ll
===================================================================
--- test/DebugInfo/Inputs/gmlt.ll
+++ test/DebugInfo/Inputs/gmlt.ll
@@ -76,6 +76,12 @@
 ; CHECK-NOT: {{DW_TAG|DW_AT}}
 ; CHECK: NULL
 
+; PROFILING: DW_TAG_subprogram
+; PROFILING: DW_AT_name {{.*}} "f1"
+; With -debug-info-for-profiling, we need to emit decl_file a-nd decl_line
+; of the subprogram.
+; PROFILING: DW_AT_decl_file
+; PROFILING: DW_AT_decl_line
 
 ; CHECK: .debug_ranges contents: