diff --git a/llvm/lib/Transforms/Utils/EscapeEnumerator.cpp b/llvm/lib/Transforms/Utils/EscapeEnumerator.cpp
--- a/llvm/lib/Transforms/Utils/EscapeEnumerator.cpp
+++ b/llvm/lib/Transforms/Utils/EscapeEnumerator.cpp
@@ -41,7 +41,27 @@
     if (!isa<ReturnInst>(TI) && !isa<ResumeInst>(TI))
       continue;
 
-    Builder.SetInsertPoint(TI);
+    // If the ret instruction is followed by a musttaill call,
+    // or a bitcast instruction and then a musttail call, we should return
+    // the musttail call as the insertion point to not break the musttail
+    // contract.
+    auto AdjustMustTailCall = [&](Instruction *I) -> Instruction * {
+      auto *RI = dyn_cast<ReturnInst>(I);
+      if (!RI || !RI->getPrevNode())
+        return I;
+      auto *CI = dyn_cast<CallInst>(RI->getPrevNode());
+      if (CI && CI->isMustTailCall())
+        return CI;
+      auto *BI = dyn_cast<BitCastInst>(RI->getPrevNode());
+      if (!BI || !BI->getPrevNode())
+        return I;
+      CI = dyn_cast<CallInst>(BI->getPrevNode());
+      if (CI && CI->isMustTailCall())
+        return CI;
+      return I;
+    };
+
+    Builder.SetInsertPoint(AdjustMustTailCall(TI));
     return &Builder;
   }
 
@@ -54,11 +74,12 @@
     return nullptr;
 
   // Find all 'call' instructions that may throw.
+  // We cannot tranform calls with musttail tag.
   SmallVector<Instruction *, 16> Calls;
   for (BasicBlock &BB : F)
     for (Instruction &II : BB)
       if (CallInst *CI = dyn_cast<CallInst>(&II))
-        if (!CI->doesNotThrow())
+        if (!CI->doesNotThrow() && !CI->isMustTailCall())
           Calls.push_back(CI);
 
   if (Calls.empty())
diff --git a/llvm/test/Instrumentation/ThreadSanitizer/tsan_musttail.ll b/llvm/test/Instrumentation/ThreadSanitizer/tsan_musttail.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Instrumentation/ThreadSanitizer/tsan_musttail.ll
@@ -0,0 +1,28 @@
+; To test that __tsan_func_exit always happen before musttaill call and no exception handling code.
+; RUN: opt < %s -tsan -S | FileCheck %s
+
+define internal i32 @preallocated_musttail(i32* preallocated(i32) %p) sanitize_thread {
+  %rv = load i32, i32* %p
+  ret i32 %rv
+}
+
+define i32 @call_preallocated_musttail(i32* preallocated(i32) %a) sanitize_thread {
+  %r = musttail call i32 @preallocated_musttail(i32* preallocated(i32) %a)
+  ret i32 %r
+}
+
+; CHECK:        call void @__tsan_func_exit()
+; CHECK-NEXT:   %r = musttail call i32 @preallocated_musttail(i32* preallocated(i32) %a)
+; CHECK-NEXT:   ret i32 %r
+
+
+define i32 @call_preallocated_musttail_cast(i32* preallocated(i32) %a) sanitize_thread {
+  %r = musttail call i32 @preallocated_musttail(i32* preallocated(i32) %a)
+  %t = bitcast i32 %r to i32
+  ret i32 %t
+}
+
+; CHECK:        call void @__tsan_func_exit()
+; CHECK-NEXT:   %r = musttail call i32 @preallocated_musttail(i32* preallocated(i32) %a)
+; CHECK-NEXT:   %t = bitcast i32 %r to i32
+; CHECK-NEXT:   ret i32 %t