Index: lib/CodeGen/CGCall.cpp
===================================================================
--- lib/CodeGen/CGCall.cpp
+++ lib/CodeGen/CGCall.cpp
@@ -1877,46 +1877,7 @@
                         TargetDecl->hasAttr<AnyX86InterruptAttr>()));
     FuncAttrs.addAttribute("disable-tail-calls",
                            llvm::toStringRef(DisableTailCalls));
-
-    // Add target-cpu and target-features attributes to functions. If
-    // we have a decl for the function and it has a target attribute then
-    // parse that and add it to the feature set.
-    StringRef TargetCPU = getTarget().getTargetOpts().CPU;
-    std::vector<std::string> Features;
-    const FunctionDecl *FD = dyn_cast_or_null<FunctionDecl>(TargetDecl);
-    if (FD && FD->hasAttr<TargetAttr>()) {
-      llvm::StringMap<bool> FeatureMap;
-      getFunctionFeatureMap(FeatureMap, FD);
-
-      // Produce the canonical string for this set of features.
-      for (llvm::StringMap<bool>::const_iterator it = FeatureMap.begin(),
-                                                 ie = FeatureMap.end();
-           it != ie; ++it)
-        Features.push_back((it->second ? "+" : "-") + it->first().str());
-
-      // Now add the target-cpu and target-features to the function.
-      // While we populated the feature map above, we still need to
-      // get and parse the target attribute so we can get the cpu for
-      // the function.
-      const auto *TD = FD->getAttr<TargetAttr>();
-      TargetAttr::ParsedTargetAttr ParsedAttr = TD->parse();
-      if (ParsedAttr.Architecture != "" &&
-          getTarget().isValidCPUName(ParsedAttr.Architecture))
-        TargetCPU = ParsedAttr.Architecture;
-    } else {
-      // Otherwise just add the existing target cpu and target features to the
-      // function.
-      Features = getTarget().getTargetOpts().Features;
-    }
-
-    if (TargetCPU != "")
-      FuncAttrs.addAttribute("target-cpu", TargetCPU);
-    if (!Features.empty()) {
-      std::sort(Features.begin(), Features.end());
-      FuncAttrs.addAttribute(
-          "target-features",
-          llvm::join(Features, ","));
-    }
+    GetCPUAndFeaturesAttributes(TargetDecl, FuncAttrs);
   }
 
   ClangToLLVMArgMapping IRFunctionArgs(getContext(), FI);
Index: lib/CodeGen/CodeGenModule.h
===================================================================
--- lib/CodeGen/CodeGenModule.h
+++ lib/CodeGen/CodeGenModule.h
@@ -1273,6 +1273,8 @@
                                         ForDefinition_t IsForDefinition
                                           = NotForDefinition);
 
+  bool GetCPUAndFeaturesAttributes(const Decl *D,
+                                   llvm::AttrBuilder &AttrBuilder);
   void setNonAliasAttributes(const Decl *D, llvm::GlobalObject *GO);
 
   /// Set function attributes for a function declaration.
Index: lib/CodeGen/CodeGenModule.cpp
===================================================================
--- lib/CodeGen/CodeGenModule.cpp
+++ lib/CodeGen/CodeGenModule.cpp
@@ -1248,6 +1248,52 @@
     GV->setDLLStorageClass(llvm::GlobalValue::DLLExportStorageClass);
 }
 
+bool CodeGenModule::GetCPUAndFeaturesAttributes(const Decl *D,
+                                                llvm::AttrBuilder &Attrs) {
+  // Add target-cpu and target-features attributes to functions. If
+  // we have a decl for the function and it has a target attribute then
+  // parse that and add it to the feature set.
+  StringRef TargetCPU = getTarget().getTargetOpts().CPU;
+  std::vector<std::string> Features;
+  const auto *FD = dyn_cast_or_null<FunctionDecl>(D);
+  FD = FD ? FD->getMostRecentDecl() : FD;
+  const auto *TD = FD ? FD->getAttr<TargetAttr>() : nullptr;
+  bool AddedAttr = false;
+  if (TD) {
+    llvm::StringMap<bool> FeatureMap;
+    getFunctionFeatureMap(FeatureMap, FD);
+
+    // Produce the canonical string for this set of features.
+    for (const llvm::StringMap<bool>::value_type &Entry : FeatureMap)
+      Features.push_back((Entry.getValue() ? "+" : "-") + Entry.getKey().str());
+
+    // Now add the target-cpu and target-features to the function.
+    // While we populated the feature map above, we still need to
+    // get and parse the target attribute so we can get the cpu for
+    // the function.
+    TargetAttr::ParsedTargetAttr ParsedAttr = TD->parse();
+    if (ParsedAttr.Architecture != "" &&
+        getTarget().isValidCPUName(ParsedAttr.Architecture))
+      TargetCPU = ParsedAttr.Architecture;
+  } else {
+    // Otherwise just add the existing target cpu and target features to the
+    // function.
+    Features = getTarget().getTargetOpts().Features;
+  }
+
+  if (TargetCPU != "") {
+    Attrs.addAttribute("target-cpu", TargetCPU);
+    AddedAttr = true;
+  }
+  if (!Features.empty()) {
+    std::sort(Features.begin(), Features.end());
+    Attrs.addAttribute("target-features", llvm::join(Features, ","));
+    AddedAttr = true;
+  }
+
+  return AddedAttr;
+}
+
 void CodeGenModule::setNonAliasAttributes(const Decl *D,
                                           llvm::GlobalObject *GO) {
   SetCommonAttributes(D, GO);
@@ -1266,6 +1312,16 @@
       if (auto *SA = D->getAttr<PragmaClangTextSectionAttr>())
         if (!D->getAttr<SectionAttr>())
           F->addFnAttr("implicit-section-name", SA->getName());
+
+      llvm::AttrBuilder Attrs;
+      if (GetCPUAndFeaturesAttributes(D, Attrs)) {
+        // We know that GetCPUAndFeaturesAttributes will always have the
+        // newest set, since it has the newest possible FunctionDecl, so the
+        // new ones should replace the old.
+        F->removeFnAttr("target-cpu");
+        F->removeFnAttr("target-features");
+        F->addAttributes(llvm::AttributeList::FunctionIndex, Attrs);
+      }
     }
 
     if (const SectionAttr *SA = D->getAttr<SectionAttr>())
Index: test/CodeGen/attr-target-x86.c
===================================================================
--- test/CodeGen/attr-target-x86.c
+++ test/CodeGen/attr-target-x86.c
@@ -21,6 +21,17 @@
 
 int __attribute__((target("arch=lakemont,mmx"))) lake(int a) { return 4; }
 
+int use_before_def(void);
+int useage(void){
+  return use_before_def();
+}
+
+// Adding the attribute to a definition does update it in IR.
+int __attribute__((target("arch=lakemont,mmx"))) use_before_def(void) {
+  return 5;
+}
+
+
 // Check that we emit the additional subtarget and cpu features for foo and not for baz or bar.
 // CHECK: baz{{.*}} #0
 // CHECK: foo{{.*}} #1
@@ -36,6 +47,7 @@
 // CHECK: qax{{.*}} #5
 // CHECK: qq{{.*}} #6
 // CHECK: lake{{.*}} #7
+// CHECK: use_before_def{{.*}} #7
 // CHECK: #0 = {{.*}}"target-cpu"="i686" "target-features"="+x87"
 // CHECK: #1 = {{.*}}"target-cpu"="ivybridge" "target-features"="+aes,+avx,+cx16,+f16c,+fsgsbase,+fxsr,+mmx,+pclmul,+popcnt,+rdrnd,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt"
 // CHECK: #2 = {{.*}}"target-cpu"="i686" "target-features"="+x87,-aes,-avx,-avx2,-avx512bitalg,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vbmi2,-avx512vl,-avx512vnni,-avx512vpopcntdq,-f16c,-fma,-fma4,-gfni,-pclmul,-sha,-sse2,-sse3,-sse4.1,-sse4.2,-sse4a,-ssse3,-vaes,-vpclmulqdq,-xop,-xsave,-xsaveopt"