Index: lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp
===================================================================
--- lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp
+++ lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp
@@ -706,6 +706,10 @@
   DIE *SPDIE = DU->getAbstractSPDies().lookup(SP);
   if (!SPDIE)
     SPDIE = getDIE(SP);
+  // Don't do this if the function is not referenced by either an
+  // abstract scope or an llvm::Function.
+  if (!SPDIE)
+    return;
   assert(SPDIE);
   for (const DILocalVariable *DV : Variables) {
     DbgVariable NewVar(DV, /* IA */ nullptr, DD);
Index: lib/CodeGen/AsmPrinter/DwarfDebug.cpp
===================================================================
--- lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ lib/CodeGen/AsmPrinter/DwarfDebug.cpp
@@ -527,29 +527,10 @@
 
 void DwarfDebug::finishSubprogramDefinitions() {
   for (const auto &P : SPMap)
-    forBothCUs(*P.second, [&](DwarfCompileUnit &CU) {
-      CU.finishSubprogramDefinition(cast<DISubprogram>(P.first));
-    });
-}
-
-// Collect info for variables that were optimized out.
-void DwarfDebug::collectDeadVariables() {
-  const Module *M = MMI->getModule();
-
-  if (NamedMDNode *CU_Nodes = M->getNamedMetadata("llvm.dbg.cu")) {
-    for (MDNode *N : CU_Nodes->operands()) {
-      auto *TheCU = cast<DICompileUnit>(N);
-      // Construct subprogram DIE and add variables DIEs.
-      DwarfCompileUnit *SPCU =
-          static_cast<DwarfCompileUnit *>(CUMap.lookup(TheCU));
-      assert(SPCU && "Unable to find Compile Unit!");
-      for (auto *SP : TheCU->getSubprograms()) {
-        if (ProcessedSPNodes.count(SP) != 0)
-          continue;
-        SPCU->collectDeadVariables(SP);
-      }
-    }
-  }
+    if (ProcessedSPNodes.count(P.first))
+      forBothCUs(*P.second, [&](DwarfCompileUnit &CU) {
+          CU.finishSubprogramDefinition(cast<DISubprogram>(P.first));
+        });
 }
 
 void DwarfDebug::finalizeModuleInfo() {
@@ -559,9 +540,6 @@
 
   finishVariableDefinitions();
 
-  // Collect info for variables that were optimized out.
-  collectDeadVariables();
-
   // Handle anything that needs to be done on a per-unit basis after
   // all other generation.
   for (const auto &P : CUMap) {
@@ -1121,6 +1099,10 @@
     PrevCU = nullptr;
     CurFn = nullptr;
     DebugHandlerBase::endFunction(MF);
+    // Mark functions with no debug info on any instructions, but a
+    // valid DISubprogram as processed.
+    if (auto *SP = MF->getFunction()->getSubprogram())
+      ProcessedSPNodes.insert(SP);
     return;
   }
 
Index: test/DebugInfo/Generic/cross-cu-linkonce-distinct.ll
===================================================================
--- test/DebugInfo/Generic/cross-cu-linkonce-distinct.ll
+++ test/DebugInfo/Generic/cross-cu-linkonce-distinct.ll
@@ -26,24 +26,16 @@
 ; }
 ; int (*y)(int) = &func;
 
+; The DISubprogram should show up in compile unit a.
 ; CHECK: DW_TAG_compile_unit
-; CHECK:   DW_TAG_subprogram
 ; CHECK-NOT: DW_TAG
-; CHECK:     DW_AT_name {{.*}} "func"
-; CHECK: DW_TAG_compile_unit
-
-; FIXME: Maybe we should drop the subprogram here - since the function was
-; emitted in one CU, due to linkonce_odr uniquing. We certainly don't emit the
-; subprogram here if the source location for this definition is the same (see
-; test/DebugInfo/cross-cu-linkonce.ll), though it's very easy to tickle that
-; into failing even without duplicating the source as has been done in this
-; case (two cpp files in different directories, including the same header that
-; contains an inline function - clang will produce distinct subprogram metadata
-; that won't deduplicate owing to the file location information containing the
-; directory of the source file even though the file name is absolute, not
-; relative)
+; CHECK:    DW_AT_name {{.*}}"b.cpp"
+; CHECK-NOT: DW_TAG_subprogram
 
-; CHECK: DW_TAG_subprogram
+; CHECK: DW_TAG_compile_unit
+; CHECK-NOT: DW_TAG
+; CHECK:     DW_AT_name {{.*}}"a.cpp"
+; CHECK:     DW_AT_name {{.*}} "func"
 
 @x = global i32 (i32)* @_Z4funci, align 8
 @y = global i32 (i32)* @_Z4funci, align 8
Index: test/DebugInfo/Generic/nodebug.ll
===================================================================
--- test/DebugInfo/Generic/nodebug.ll
+++ test/DebugInfo/Generic/nodebug.ll
@@ -16,10 +16,8 @@
 ;   f1();
 ; }
 
-; Check that there's only one DW_TAG_subprogram, nothing for the 'f2' function.
-; CHECK: DW_TAG_subprogram
-; CHECK-NOT: DW_TAG
-; CHECK:   DW_AT_name {{.*}} "f1"
+; Check that there's no DW_TAG_subprogram, not even for the 'f2' function.
+; CHECK: DW_TAG_compile_unit
 ; CHECK-NOT: DW_TAG_subprogram
 
 @i = external global i32
Index: test/DebugInfo/X86/debug-dead-local-var.ll
===================================================================
--- test/DebugInfo/X86/debug-dead-local-var.ll
+++ test/DebugInfo/X86/debug-dead-local-var.ll
@@ -11,9 +11,12 @@
 ;   return 1;
 ; }
 
-; Check that we still have the structure type for X even though we're not
-; going to emit a low/high_pc for foo.
-; CHECK: DW_TAG_structure_type
+; Check that don't have the structure type for X since its scope has
+; been optimized away.
+; CHECK-NOT: DW_TAG_structure_type
+; CHECK: DW_TAG_subprogram
+; CHECK: DW_AT_name {{.*}}"bar"
+; CHECK-NOT: DW_TAG_structure_type
 
 ; Function Attrs: nounwind readnone uwtable
 define i32 @bar() #0 !dbg !4 {