Index: llvm/include/llvm/IR/Intrinsics.td
===================================================================
--- llvm/include/llvm/IR/Intrinsics.td
+++ llvm/include/llvm/IR/Intrinsics.td
@@ -1316,6 +1316,10 @@
                                      ReadOnly<ArgIndex<0>>,
                                      NoCapture<ArgIndex<0>>]>;
 
+// Coroutine Lowering Intrinsics to block optimizations. Used internally by 
+// coroutine passes.
+def int_coro_maychange : Intrinsic<[llvm_ptr_ty], [llvm_ptr_ty]>;
+
 ///===-------------------------- Other Intrinsics --------------------------===//
 //
 def int_trap : Intrinsic<[], [], [IntrNoReturn, IntrCold]>,
Index: llvm/lib/Transforms/Coroutines/CoroCleanup.cpp
===================================================================
--- llvm/lib/Transforms/Coroutines/CoroCleanup.cpp
+++ llvm/lib/Transforms/Coroutines/CoroCleanup.cpp
@@ -93,6 +93,9 @@
         } else
           continue;
         break;
+      case Intrinsic::coro_maychange:
+        II->replaceAllUsesWith(II->getOperand(0));
+        break;
       case Intrinsic::coro_async_size_replace:
         auto *Target = cast<ConstantStruct>(
             cast<GlobalVariable>(II->getArgOperand(0)->stripPointerCasts())
@@ -111,6 +114,7 @@
         Target->replaceAllUsesWith(NewFuncPtrStruct);
         break;
       }
+
       II->eraseFromParent();
       Changed = true;
     }
@@ -129,7 +133,7 @@
       M, {"llvm.coro.alloc", "llvm.coro.begin", "llvm.coro.subfn.addr",
           "llvm.coro.free", "llvm.coro.id", "llvm.coro.id.retcon",
           "llvm.coro.id.retcon.once", "llvm.coro.async.size.replace",
-          "llvm.coro.async.resume"});
+          "llvm.coro.async.resume", "llvm.coro.maychange"});
 }
 
 PreservedAnalyses CoroCleanupPass::run(Function &F,
Index: llvm/lib/Transforms/Coroutines/CoroEarly.cpp
===================================================================
--- llvm/lib/Transforms/Coroutines/CoroEarly.cpp
+++ llvm/lib/Transforms/Coroutines/CoroEarly.cpp
@@ -244,6 +244,27 @@
   for (auto &F : M)
     L.lowerEarlyIntrinsics(F);
 
+  // Add llvm.coro.maychange to TLS variable to avoid misoptimization.
+  //
+  // Previously, the optimizer could assume the address of a TLS variable is
+  // same in the same function. The assumption is broken now after we introduced
+  // coroutines.
+  //
+  // Note that we couldn't mark the use in coroutines only due to potentially
+  // inlining. It is too expensive to do CFG analysis here to mark the use for
+  // reachable function only. And the TLS variable should be able to be optmized
+  // finally after we removed llvm.coro.maychange intrinsic in CoroCleanup.
+  auto *MaychangeFn = Intrinsic::getDeclaration(&M, Intrinsic::coro_maychange);
+  for (auto &GV : M.getGlobalList())
+    if (GV.isThreadLocal())
+      for (auto &Use : llvm::make_early_inc_range(GV.uses())) {
+        auto *UserInst = dyn_cast<Instruction>(Use.getUser());
+        if (!UserInst)
+          continue;
+
+        Use.set(CallInst::Create(MaychangeFn, {&GV}, GV.getName(), UserInst));
+      }
+
   PreservedAnalyses PA;
   PA.preserveSet<CFGAnalyses>();
   return PA;
Index: llvm/lib/Transforms/Coroutines/Coroutines.cpp
===================================================================
--- llvm/lib/Transforms/Coroutines/Coroutines.cpp
+++ llvm/lib/Transforms/Coroutines/Coroutines.cpp
@@ -88,6 +88,7 @@
     "llvm.coro.id.async",
     "llvm.coro.id.retcon",
     "llvm.coro.id.retcon.once",
+    "llvm.coro.maychange",
     "llvm.coro.noop",
     "llvm.coro.prepare.async",
     "llvm.coro.prepare.retcon",
Index: llvm/test/Transforms/Coroutines/coro-TLS-01.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Coroutines/coro-TLS-01.ll
@@ -0,0 +1,66 @@
+; Tests that the TLS variables which cross suspend points wouldn't be misoptimized.
+; RUN: opt < %s -S -passes=coro-early,sroa,early-cse,coro-split,coro-cleanup,simplifycfg -opaque-pointers | FileCheck %s
+
+@tls_variable = thread_local global i32 0
+
+define ptr @f() "coroutine.presplit"="0" {
+entry:
+  %id = call token @llvm.coro.id(i32 0, i8* null, i8* null, i8* null)
+  %size = call i32 @llvm.coro.size.i32()
+  %alloc = call i8* @malloc(i32 %size)
+  %i = alloca ptr
+  %j = alloca ptr
+  %hdl = call i8* @llvm.coro.begin(token %id, i8* %alloc)
+  store ptr @tls_variable, ptr %i
+  %sus_result = call i8 @llvm.coro.suspend(token none, i1 false)
+  switch i8 %sus_result, label %suspend [i8 0, label %resume
+                                         i8 1, label %cleanup]
+resume:
+  store ptr @tls_variable, ptr %j
+  %i_value = load ptr, ptr %i
+  %j_value = load ptr, ptr %j
+  %cmp = icmp eq ptr %i_value, %j_value
+  br i1 %cmp, label %same, label %diff
+
+same:
+  call void @print_same()
+  br label %cleanup
+
+diff:
+  call void @print_diff()
+  br label %cleanup
+
+cleanup:
+  %mem = call i8* @llvm.coro.free(token %id, i8* %hdl)
+  call void @free(i8* %mem)
+  br label %suspend
+
+suspend:
+  call i1 @llvm.coro.end(i8* %hdl, i1 0)
+  ret i8* %hdl
+}
+
+; CHECK-LABEL: f.resume(
+; CHECK: br i1 %cmp, label %same, label %diff
+; CHECK-EMPTY:
+; CHECK-NEXT: same:
+; CHECK-NEXT:   call void @print_same()
+; CHECK-NEXT:   br label %cleanup
+; CHECK-EMPTY:
+; CHECK-NEXT: diff:
+; CHECK-NEXT:   call void @print_diff()
+; CHECK-NEXT:   br label %cleanup
+
+declare void @print_same()
+declare void @print_diff()
+declare i8* @llvm.coro.free(token, i8*)
+declare i32 @llvm.coro.size.i32()
+declare i8  @llvm.coro.suspend(token, i1)
+
+declare token @llvm.coro.id(i32, i8*, i8*, i8*)
+declare i1 @llvm.coro.alloc(token)
+declare i8* @llvm.coro.begin(token, i8*)
+declare i1 @llvm.coro.end(i8*, i1)
+
+declare noalias i8* @malloc(i32)
+declare void @free(i8*)
Index: llvm/test/Transforms/Coroutines/coro-TLS-02.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Coroutines/coro-TLS-02.ll
@@ -0,0 +1,61 @@
+; Tests that the TLS variables which don't cross suspend points would be optimized correctly.
+; RUN: opt < %s -S -passes=coro-early,coro-split,coro-cleanup,sroa,early-cse,simplifycfg -opaque-pointers | FileCheck %s
+
+@tls_variable = thread_local global i32 0
+
+define ptr @f() "coroutine.presplit"="0" {
+entry:
+  %id = call token @llvm.coro.id(i32 0, i8* null, i8* null, i8* null)
+  %size = call i32 @llvm.coro.size.i32()
+  %alloc = call i8* @malloc(i32 %size)
+  %i = alloca ptr
+  %j = alloca ptr
+  %hdl = call i8* @llvm.coro.begin(token %id, i8* %alloc)
+  %sus_result = call i8 @llvm.coro.suspend(token none, i1 false)
+  switch i8 %sus_result, label %suspend [i8 0, label %resume
+                                         i8 1, label %cleanup]
+resume:
+  store ptr @tls_variable, ptr %i
+  store ptr @tls_variable, ptr %j
+  %i_value = load ptr, ptr %i
+  %j_value = load ptr, ptr %j
+  %cmp = icmp eq ptr %i_value, %j_value
+  br i1 %cmp, label %same, label %diff
+
+same:
+  call void @print_same()
+  br label %cleanup
+
+diff:
+  call void @print_diff()
+  br label %cleanup
+
+cleanup:
+  %mem = call i8* @llvm.coro.free(token %id, i8* %hdl)
+  call void @free(i8* %mem)
+  br label %suspend
+
+suspend:
+  call i1 @llvm.coro.end(i8* %hdl, i1 0)
+  ret i8* %hdl
+}
+
+; CHECK: void @f.resume
+; CHECK-NEXT: entry.resume:
+; CHECK-NEXT: call void @print_same()
+; CHECK-NEXT: call void @free(ptr %hdl)
+; CHECK-NEXT: ret void 
+
+declare void @print_same()
+declare void @print_diff()
+declare i8* @llvm.coro.free(token, i8*)
+declare i32 @llvm.coro.size.i32()
+declare i8  @llvm.coro.suspend(token, i1)
+
+declare token @llvm.coro.id(i32, i8*, i8*, i8*)
+declare i1 @llvm.coro.alloc(token)
+declare i8* @llvm.coro.begin(token, i8*)
+declare i1 @llvm.coro.end(i8*, i1)
+
+declare noalias i8* @malloc(i32)
+declare void @free(i8*)
Index: llvm/test/Transforms/Coroutines/coro-TLS-03.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Coroutines/coro-TLS-03.ll
@@ -0,0 +1,66 @@
+; Tests that the TLS variables which cross suspend points wouldn't be misoptimized during O2 pipeline.
+; RUN: opt < %s -S -passes='default<O2>' -opaque-pointers | FileCheck %s
+
+@tls_variable = thread_local global i32 0
+
+define ptr @f() "coroutine.presplit"="0" {
+entry:
+  %id = call token @llvm.coro.id(i32 0, i8* null, i8* null, i8* null)
+  %size = call i32 @llvm.coro.size.i32()
+  %alloc = call i8* @malloc(i32 %size)
+  %i = alloca ptr
+  %j = alloca ptr
+  %hdl = call i8* @llvm.coro.begin(token %id, i8* %alloc)
+  store ptr @tls_variable, ptr %i
+  %sus_result = call i8 @llvm.coro.suspend(token none, i1 false)
+  switch i8 %sus_result, label %suspend [i8 0, label %resume
+                                         i8 1, label %cleanup]
+resume:
+  store ptr @tls_variable, ptr %j
+  %i_value = load ptr, ptr %i
+  %j_value = load ptr, ptr %j
+  %cmp = icmp eq ptr %i_value, %j_value
+  br i1 %cmp, label %same, label %diff
+
+same:
+  call void @print_same()
+  br label %cleanup
+
+diff:
+  call void @print_diff()
+  br label %cleanup
+
+cleanup:
+  %mem = call i8* @llvm.coro.free(token %id, i8* %hdl)
+  call void @free(i8* %mem)
+  br label %suspend
+
+suspend:
+  call i1 @llvm.coro.end(i8* %hdl, i1 0)
+  ret i8* %hdl
+}
+
+; CHECK-LABEL: f.resume(
+; CHECK: br i1 %cmp, label %same, label %diff
+; CHECK-EMPTY:
+; CHECK-NEXT: same:
+; CHECK-NEXT:   call void @print_same()
+; CHECK-NEXT:   br label
+; CHECK-EMPTY:
+; CHECK-NEXT: diff:
+; CHECK-NEXT:   call void @print_diff()
+; CHECK-NEXT:   br label
+
+declare void @print_same()
+declare void @print_diff()
+declare i8* @llvm.coro.free(token, i8*)
+declare i32 @llvm.coro.size.i32()
+declare i8  @llvm.coro.suspend(token, i1)
+
+declare token @llvm.coro.id(i32, i8*, i8*, i8*)
+declare i1 @llvm.coro.alloc(token)
+declare i8* @llvm.coro.begin(token, i8*)
+declare i1 @llvm.coro.end(i8*, i1)
+
+declare noalias i8* @malloc(i32)
+declare void @free(i8*)
Index: llvm/test/Transforms/Coroutines/coro-TLS-04.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Coroutines/coro-TLS-04.ll
@@ -0,0 +1,61 @@
+; Tests that the TLS variables which don't cross suspend points would be optimized correctly during O2 pipelines.
+; RUN: opt < %s -S -passes='default<O2>' -opaque-pointers | FileCheck %s
+
+@tls_variable = thread_local global i32 0
+
+define ptr @f() "coroutine.presplit"="0" {
+entry:
+  %id = call token @llvm.coro.id(i32 0, i8* null, i8* null, i8* null)
+  %size = call i32 @llvm.coro.size.i32()
+  %alloc = call i8* @malloc(i32 %size)
+  %i = alloca ptr
+  %j = alloca ptr
+  %hdl = call i8* @llvm.coro.begin(token %id, i8* %alloc)
+  %sus_result = call i8 @llvm.coro.suspend(token none, i1 false)
+  switch i8 %sus_result, label %suspend [i8 0, label %resume
+                                         i8 1, label %cleanup]
+resume:
+  store ptr @tls_variable, ptr %i
+  store ptr @tls_variable, ptr %j
+  %i_value = load ptr, ptr %i
+  %j_value = load ptr, ptr %j
+  %cmp = icmp eq ptr %i_value, %j_value
+  br i1 %cmp, label %same, label %diff
+
+same:
+  call void @print_same()
+  br label %cleanup
+
+diff:
+  call void @print_diff()
+  br label %cleanup
+
+cleanup:
+  %mem = call i8* @llvm.coro.free(token %id, i8* %hdl)
+  call void @free(i8* %mem)
+  br label %suspend
+
+suspend:
+  call i1 @llvm.coro.end(i8* %hdl, i1 0)
+  ret i8* %hdl
+}
+
+; CHECK: void @f.resume
+; CHECK-NEXT: resume:
+; CHECK-NEXT: call void @print_same(
+; CHECK-NEXT: call void @free(
+; CHECK-NEXT: ret void 
+
+declare void @print_same()
+declare void @print_diff()
+declare i8* @llvm.coro.free(token, i8*)
+declare i32 @llvm.coro.size.i32()
+declare i8  @llvm.coro.suspend(token, i1)
+
+declare token @llvm.coro.id(i32, i8*, i8*, i8*)
+declare i1 @llvm.coro.alloc(token)
+declare i8* @llvm.coro.begin(token, i8*)
+declare i1 @llvm.coro.end(i8*, i1)
+
+declare noalias i8* @malloc(i32)
+declare void @free(i8*)
Index: llvm/test/Transforms/Coroutines/coro-cleanup-maychange.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Coroutines/coro-cleanup-maychange.ll
@@ -0,0 +1,73 @@
+; Test that coro-cleanup would convert llvm.coro.maychange intrinsics
+; correctly.
+; RUN: opt < %s -S -passes=coro-cleanup -opaque-pointers | FileCheck %s
+
+%f.Frame = type { ptr, ptr, ptr, ptr, i1 }
+
+@tls_variable = thread_local global i32 0
+@f.resumers = private constant [3 x ptr] [ptr @f.resume, ptr @f.destroy, ptr @f.cleanup]
+
+define ptr @f() {
+entry:
+  %id = call token @llvm.coro.id(i32 0, ptr null, ptr @f, ptr @f.resumers)
+  %alloc = call ptr @malloc(i32 40)
+  %i = alloca ptr, align 8
+  %j = alloca ptr, align 8
+  %hdl = call noalias nonnull ptr @llvm.coro.begin(token %id, ptr %alloc)
+  %resume.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 0
+  store ptr @f.resume, ptr %resume.addr, align 8
+  %destroy.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 1
+  store ptr @f.destroy, ptr %destroy.addr, align 8
+  %i.reload.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 2
+  %j.reload.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 3
+  ; CHECK: store ptr @tls_variable, ptr %i.reload.addr, align 8
+  %tls_variable1 = call ptr @llvm.coro.maychange(ptr @tls_variable)
+  store ptr %tls_variable1, ptr %i.reload.addr, align 8
+  %index.addr2 = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 4
+  store i1 false, ptr %index.addr2, align 1
+  ret ptr %hdl
+}
+
+define internal fastcc void @f.resume(ptr noalias nonnull align 8 dereferenceable(40) %hdl) {
+entry.resume:
+  %i.reload.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 2
+  %j.reload.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 3
+  %tls_variable = call ptr @llvm.coro.maychange(ptr @tls_variable)
+  ; CHECK: store ptr @tls_variable, ptr %j.reload.addr, align 8
+  store ptr %tls_variable, ptr %j.reload.addr, align 8
+  call void @consume(ptr %i.reload.addr)
+  call void @consume(ptr %j.reload.addr)
+  call void @free(ptr %hdl)
+  ret void
+}
+
+define internal fastcc void @f.destroy(ptr noalias nonnull align 8 dereferenceable(40) %hdl) {
+entry.destroy:
+  %i.reload.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 2
+  %j.reload.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 3
+  call void @free(ptr %hdl)
+  ret void
+}
+
+define internal fastcc void @f.cleanup(ptr noalias nonnull align 8 dereferenceable(40) %hdl) {
+entry.cleanup:
+  %i.reload.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 2
+  %j.reload.addr = getelementptr inbounds %f.Frame, ptr %hdl, i32 0, i32 3
+  call void @free(ptr null)
+  ret void
+}
+
+declare void @consume(ptr)
+declare i8* @llvm.coro.free(token, i8*)
+declare i32 @llvm.coro.size.i32()
+declare i8  @llvm.coro.suspend(token, i1)
+
+declare token @llvm.coro.id(i32, i8*, i8*, i8*)
+declare i1 @llvm.coro.alloc(token)
+declare i8* @llvm.coro.begin(token, i8*)
+declare i1 @llvm.coro.end(i8*, i1)
+
+declare noalias i8* @malloc(i32)
+declare void @free(i8*)
+
+declare ptr @llvm.coro.maychange(ptr)
Index: llvm/test/Transforms/Coroutines/coro-early-maychange.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Coroutines/coro-early-maychange.ll
@@ -0,0 +1,50 @@
+; Tests that coro-early would generate llvm.coro.maychange intrinsics for TLS
+; variable correctly.
+; RUN: opt < %s -S -passes=coro-early -opaque-pointers | FileCheck %s
+
+@tls_variable = thread_local global i32 0
+
+define i8* @f() "coroutine.presplit"="0" {
+entry:
+  %id = call token @llvm.coro.id(i32 0, i8* null, i8* null, i8* null)
+  %size = call i32 @llvm.coro.size.i32()
+  %alloc = call i8* @malloc(i32 %size)
+  %i = alloca ptr
+  %j = alloca ptr
+  %hdl = call i8* @llvm.coro.begin(token %id, i8* %alloc)
+  ; CHECK: %[[TLS_VARIABLE:.*]] = call ptr @llvm.coro.maychange(ptr @tls_variable)
+  ; CHECK-NEXT: store ptr %[[TLS_VARIABLE]], ptr %i
+  store ptr @tls_variable, ptr %i
+  %sus_result = call i8 @llvm.coro.suspend(token none, i1 false)
+  switch i8 %sus_result, label %suspend [i8 0, label %resume
+                                         i8 1, label %cleanup]
+resume:
+  ; CHECK: %[[TLS_VARIABLE2:.*]] = call ptr @llvm.coro.maychange(ptr @tls_variable)
+  ; CHECK-NEXT: store ptr %[[TLS_VARIABLE2]], ptr %j
+  store ptr @tls_variable, ptr %j
+  call void @consume(ptr %i)
+  call void @consume(ptr %j)
+  br label %cleanup
+
+cleanup:
+  %mem = call i8* @llvm.coro.free(token %id, i8* %hdl)
+  call void @free(i8* %mem)
+  br label %suspend
+
+suspend:
+  call i1 @llvm.coro.end(i8* %hdl, i1 0)
+  ret i8* %hdl
+}
+
+declare void @consume(ptr)
+declare i8* @llvm.coro.free(token, i8*)
+declare i32 @llvm.coro.size.i32()
+declare i8  @llvm.coro.suspend(token, i1)
+
+declare token @llvm.coro.id(i32, i8*, i8*, i8*)
+declare i1 @llvm.coro.alloc(token)
+declare i8* @llvm.coro.begin(token, i8*)
+declare i1 @llvm.coro.end(i8*, i1)
+
+declare noalias i8* @malloc(i32)
+declare void @free(i8*)