diff --git a/clang/test/CodeGenCoroutines/coro-attributes.cpp b/clang/test/CodeGenCoroutines/coro-attributes.cpp
index ecd298e6b4b5..8f171771a8cb 100644
--- a/clang/test/CodeGenCoroutines/coro-attributes.cpp
+++ b/clang/test/CodeGenCoroutines/coro-attributes.cpp
@@ -14,7 +14,9 @@ struct coro {
 };
 
 // CHECK: void @_Z3foov() #[[FOO_ATTR_NUM:[0-9]+]]
+// CHECK: declare token @llvm.coro.save(ptr) #[[SAVE_ATTR_NUM:[0-9]+]]
 // CHECK: attributes #[[FOO_ATTR_NUM]] = { {{.*}} presplitcoroutine
+// CHECK: attributes #[[SAVE_ATTR_NUM]] = { {{.*}}nomerge
 coro foo() {
   co_await suspend_always{};
 }
diff --git a/llvm/docs/Coroutines.rst b/llvm/docs/Coroutines.rst
index f20284a74d5a..df05d0264967 100644
--- a/llvm/docs/Coroutines.rst
+++ b/llvm/docs/Coroutines.rst
@@ -1555,7 +1555,9 @@ Overview:
 
 The '``llvm.coro.save``' marks the point where a coroutine need to update its
 state to prepare for resumption to be considered suspended (and thus eligible
-for resumption).
+for resumption). It is illegal to merge two '``llvm.coro.save``' calls unless their
+'``llvm.coro.suspend``' users are also merged. So '``llvm.coro.save``' is currently
+tagged with the `no_merge` function attribute.
 
 Arguments:
 """"""""""
diff --git a/llvm/include/llvm/IR/Intrinsics.td b/llvm/include/llvm/IR/Intrinsics.td
index 0dceea13ea36..8bf8e9ca76ad 100644
--- a/llvm/include/llvm/IR/Intrinsics.td
+++ b/llvm/include/llvm/IR/Intrinsics.td
@@ -1308,7 +1308,7 @@ def int_coro_noop : Intrinsic<[llvm_ptr_ty], [], [IntrNoMem]>;
 def int_coro_size : Intrinsic<[llvm_anyint_ty], [], [IntrNoMem]>;
 def int_coro_align : Intrinsic<[llvm_anyint_ty], [], [IntrNoMem]>;
 
-def int_coro_save : Intrinsic<[llvm_token_ty], [llvm_ptr_ty], []>;
+def int_coro_save : Intrinsic<[llvm_token_ty], [llvm_ptr_ty], [IntrNoMerge]>;
 def int_coro_suspend : Intrinsic<[llvm_i8_ty], [llvm_token_ty, llvm_i1_ty], []>;
 def int_coro_suspend_retcon : Intrinsic<[llvm_any_ty], [llvm_vararg_ty], []>;
 def int_coro_prepare_retcon : Intrinsic<[llvm_ptr_ty], [llvm_ptr_ty],
diff --git a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
index 86b2128a1937..c1d9de197a6b 100644
--- a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -1499,10 +1499,6 @@ bool SimplifyCFGOpt::HoistThenElseCodeToIf(BranchInst *BI,
     if (I1->isTerminator())
       goto HoistTerminator;
 
-    // Hoisting token-returning instructions would obscure the origin.
-    if (I1->getType()->isTokenTy())
-      return Changed;
-
     // If we're going to hoist a call, make sure that the two instructions we're
     // commoning/hoisting are both marked with musttail, or neither of them is
     // marked as such. Otherwise, we might end up in a situation where we hoist
diff --git a/llvm/test/Transforms/Coroutines/coro-save-nomerge.ll b/llvm/test/Transforms/Coroutines/coro-save-nomerge.ll
new file mode 100644
index 000000000000..17dfe2c26920
--- /dev/null
+++ b/llvm/test/Transforms/Coroutines/coro-save-nomerge.ll
@@ -0,0 +1,75 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -passes='simplifycfg<hoist-common-insts>' -S | FileCheck %s
+
+declare token @llvm.coro.save(ptr) #0
+declare i8 @llvm.coro.suspend(token, i1)
+
+define void @final_nonfinal_suspend(i32 %x) {
+; CHECK-LABEL: @final_nonfinal_suspend(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[X:%.*]], 0
+; CHECK-NEXT:    br i1 [[CMP]], label [[AWAIT_SUSPEND:%.*]], label [[FINAL_SUSPEND:%.*]]
+; CHECK:       await.suspend:
+; CHECK-NEXT:    [[TMP0:%.*]] = call token @llvm.coro.save(ptr null)
+; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.coro.suspend(token [[TMP0]], i1 false)
+; CHECK-NEXT:    br label [[CORO_RET:%.*]]
+; CHECK:       final.suspend:
+; CHECK-NEXT:    [[TMP2:%.*]] = call token @llvm.coro.save(ptr null)
+; CHECK-NEXT:    [[TMP3:%.*]] = call i8 @llvm.coro.suspend(token [[TMP2]], i1 true)
+; CHECK-NEXT:    br label [[CORO_RET]]
+; CHECK:       coro.ret:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %cmp = icmp slt i32 %x, 0
+  br i1 %cmp, label %await.suspend, label %final.suspend
+
+await.suspend:
+  %0 = call token @llvm.coro.save(ptr null)
+  %1 = call i8 @llvm.coro.suspend(token %0, i1 false)
+  br label %coro.ret
+
+final.suspend:
+  %2 = call token @llvm.coro.save(ptr null)
+  %3 = call i8 @llvm.coro.suspend(token %2, i1 true)
+  br label %coro.ret
+
+coro.ret:
+  ret void
+}
+
+define void @both_nonfinal_suspend(i32 %x) {
+; CHECK-LABEL: @both_nonfinal_suspend(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[X:%.*]], 0
+; CHECK-NEXT:    br i1 [[CMP]], label [[AWAIT_SUSPEND:%.*]], label [[FINAL_SUSPEND:%.*]]
+; CHECK:       await.suspend:
+; CHECK-NEXT:    [[TMP0:%.*]] = call token @llvm.coro.save(ptr null)
+; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.coro.suspend(token [[TMP0]], i1 false)
+; CHECK-NEXT:    br label [[CORO_RET:%.*]]
+; CHECK:       final.suspend:
+; CHECK-NEXT:    [[TMP2:%.*]] = call token @llvm.coro.save(ptr null)
+; CHECK-NEXT:    [[TMP3:%.*]] = call i8 @llvm.coro.suspend(token [[TMP2]], i1 false)
+; CHECK-NEXT:    br label [[CORO_RET]]
+; CHECK:       coro.ret:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %cmp = icmp slt i32 %x, 0
+  br i1 %cmp, label %await.suspend, label %final.suspend
+
+await.suspend:
+  %0 = call token @llvm.coro.save(ptr null)
+  %1 = call i8 @llvm.coro.suspend(token %0, i1 false)
+  br label %coro.ret
+
+final.suspend:
+  %2 = call token @llvm.coro.save(ptr null)
+  %3 = call i8 @llvm.coro.suspend(token %2, i1 false)
+  br label %coro.ret
+
+coro.ret:
+  ret void
+}
+
+attributes #0 = { nomerge }
diff --git a/llvm/test/Transforms/SimplifyCFG/hoist-skip-token.ll b/llvm/test/Transforms/SimplifyCFG/hoist-skip-token.ll
deleted file mode 100644
index 1e9dc253f198..000000000000
--- a/llvm/test/Transforms/SimplifyCFG/hoist-skip-token.ll
+++ /dev/null
@@ -1,39 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -passes='simplifycfg<hoist-common-insts>' -S | FileCheck %s
-
-declare token @llvm.coro.save(ptr)
-declare i8 @llvm.coro.suspend(token, i1)
-
-define void @f(i32 %x) {
-; CHECK-LABEL: @f(
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[X:%.*]], 0
-; CHECK-NEXT:    br i1 [[CMP]], label [[AWAIT_SUSPEND:%.*]], label [[FINAL_SUSPEND:%.*]]
-; CHECK:       await.suspend:
-; CHECK-NEXT:    [[TMP0:%.*]] = call token @llvm.coro.save(ptr null)
-; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.coro.suspend(token [[TMP0]], i1 false)
-; CHECK-NEXT:    br label [[CORO_RET:%.*]]
-; CHECK:       final.suspend:
-; CHECK-NEXT:    [[TMP2:%.*]] = call token @llvm.coro.save(ptr null)
-; CHECK-NEXT:    [[TMP3:%.*]] = call i8 @llvm.coro.suspend(token [[TMP2]], i1 true)
-; CHECK-NEXT:    br label [[CORO_RET]]
-; CHECK:       coro.ret:
-; CHECK-NEXT:    ret void
-;
-entry:
-  %cmp = icmp slt i32 %x, 0
-  br i1 %cmp, label %await.suspend, label %final.suspend
-
-await.suspend:
-  %0 = call token @llvm.coro.save(ptr null)
-  %1 = call i8 @llvm.coro.suspend(token %0, i1 false)
-  br label %coro.ret
-
-final.suspend:
-  %2 = call token @llvm.coro.save(ptr null)
-  %3 = call i8 @llvm.coro.suspend(token %2, i1 true)
-  br label %coro.ret
-
-coro.ret:
-  ret void
-}