diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
--- a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
@@ -3455,45 +3455,67 @@
   if (!ignoreCallingConv(Func) && !IsCallingConvC)
     return nullptr;
 
+  Value *New;
   switch (Func) {
   case LibFunc_memcpy_chk:
-    return optimizeMemCpyChk(CI, Builder);
+    New = optimizeMemCpyChk(CI, Builder);
+    break;
   case LibFunc_mempcpy_chk:
-    return optimizeMemPCpyChk(CI, Builder);
+    New = optimizeMemPCpyChk(CI, Builder);
+    break;
   case LibFunc_memmove_chk:
-    return optimizeMemMoveChk(CI, Builder);
+    New = optimizeMemMoveChk(CI, Builder);
+    break;
   case LibFunc_memset_chk:
-    return optimizeMemSetChk(CI, Builder);
+    New = optimizeMemSetChk(CI, Builder);
+    break;
   case LibFunc_stpcpy_chk:
   case LibFunc_strcpy_chk:
-    return optimizeStrpCpyChk(CI, Builder, Func);
+    New = optimizeStrpCpyChk(CI, Builder, Func);
+    break;
   case LibFunc_strlen_chk:
-    return optimizeStrLenChk(CI, Builder);
+    New = optimizeStrLenChk(CI, Builder);
+    break;
   case LibFunc_stpncpy_chk:
   case LibFunc_strncpy_chk:
-    return optimizeStrpNCpyChk(CI, Builder, Func);
+    New = optimizeStrpNCpyChk(CI, Builder, Func);
+    break;
   case LibFunc_memccpy_chk:
-    return optimizeMemCCpyChk(CI, Builder);
+    New = optimizeMemCCpyChk(CI, Builder);
+    break;
   case LibFunc_snprintf_chk:
-    return optimizeSNPrintfChk(CI, Builder);
+    New = optimizeSNPrintfChk(CI, Builder);
+    break;
   case LibFunc_sprintf_chk:
-    return optimizeSPrintfChk(CI, Builder);
+    New = optimizeSPrintfChk(CI, Builder);
+    break;
   case LibFunc_strcat_chk:
-    return optimizeStrCatChk(CI, Builder);
+    New = optimizeStrCatChk(CI, Builder);
+    break;
   case LibFunc_strlcat_chk:
-    return optimizeStrLCat(CI, Builder);
+    New = optimizeStrLCat(CI, Builder);
+    break;
   case LibFunc_strncat_chk:
-    return optimizeStrNCatChk(CI, Builder);
+    New = optimizeStrNCatChk(CI, Builder);
+    break;
   case LibFunc_strlcpy_chk:
-    return optimizeStrLCpyChk(CI, Builder);
+    New = optimizeStrLCpyChk(CI, Builder);
+    break;
   case LibFunc_vsnprintf_chk:
-    return optimizeVSNPrintfChk(CI, Builder);
+    New = optimizeVSNPrintfChk(CI, Builder);
+    break;
   case LibFunc_vsprintf_chk:
-    return optimizeVSPrintfChk(CI, Builder);
-  default:
+    New = optimizeVSPrintfChk(CI, Builder);
     break;
+  default:
+    return nullptr;
   }
-  return nullptr;
+
+  if (auto *SimplifiedCI = dyn_cast_or_null<CallInst>(New))
+    if (CI->isTailCall() && !SimplifiedCI->isTailCall())
+      SimplifiedCI->setTailCall();
+
+  return New;
 }
 
 FortifiedLibCallSimplifier::FortifiedLibCallSimplifier(
diff --git a/llvm/test/Transforms/InstCombine/fortify-folding.ll b/llvm/test/Transforms/InstCombine/fortify-folding.ll
--- a/llvm/test/Transforms/InstCombine/fortify-folding.ll
+++ b/llvm/test/Transforms/InstCombine/fortify-folding.ll
@@ -11,12 +11,12 @@
 
 define i8* @test_memccpy() {
 ; CHECK-LABEL: @test_memccpy(
-; CHECK-NEXT:    [[MEMCCPY:%.*]] = call i8* @memccpy(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i64 0, i64 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i64 0, i64 0), i32 0, i64 60)
+; CHECK-NEXT:    [[MEMCCPY:%.*]] = tail call i8* @memccpy(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i64 0, i64 0), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @b, i64 0, i64 0), i32 0, i64 60)
 ; CHECK-NEXT:    ret i8* [[MEMCCPY]]
 ;
   %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0
   %src = getelementptr inbounds [60 x i8], [60 x i8]* @b, i32 0, i32 0
-  %ret = call i8* @__memccpy_chk(i8* %dst, i8* %src, i32 0, i64 60, i64 -1)
+  %ret = tail call i8* @__memccpy_chk(i8* %dst, i8* %src, i32 0, i64 60, i64 -1)
   ret i8* %ret
 }