Entry.Alignment = Align;
CLI.getArgs().insert(CLI.getArgs().begin(), Entry);
CLI.RetTy = Type::getVoidTy(CLI.RetTy->getContext());
+
+ // sret demotion isn't compatible with tail-calls, since the sret argument
+ // points into the callers stack frame.
+ CLI.IsTailCall = false;
} else {
for (unsigned I = 0, E = RetTys.size(); I != E; ++I) {
EVT VT = RetTys[I];
--- /dev/null
+; RUN: llc < %s -mtriple arm64-apple-darwin -aarch64-load-store-opt=false -asm-verbose=false | FileCheck %s
+; Disable the load/store optimizer to avoid having LDP/STPs and simplify checks.
+
+target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
+
+; Check that we don't try to tail-call with an sret-demoted return.
+
+declare i1024 @test_sret() #0
+
+; CHECK-LABEL: _test_call_sret:
+; CHECK: mov x[[CALLERX8NUM:[0-9]+]], x8
+; CHECK: mov x8, sp
+; CHECK-NEXT: bl _test_sret
+; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
+; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
+; CHECK: ret
+define i1024 @test_call_sret() #0 {
+ %a = call i1024 @test_sret()
+ ret i1024 %a
+}
+
+; CHECK-LABEL: _test_tailcall_sret:
+; CHECK: mov x[[CALLERX8NUM:[0-9]+]], x8
+; CHECK: mov x8, sp
+; CHECK-NEXT: bl _test_sret
+; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
+; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
+; CHECK: ret
+define i1024 @test_tailcall_sret() #0 {
+ %a = tail call i1024 @test_sret()
+ ret i1024 %a
+}
+
+; CHECK-LABEL: _test_indirect_tailcall_sret:
+; CHECK: mov x[[CALLERX8NUM:[0-9]+]], x8
+; CHECK: mov x8, sp
+; CHECK-NEXT: blr x0
+; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
+; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
+; CHECK: ret
+define i1024 @test_indirect_tailcall_sret(i1024 ()* %f) #0 {
+ %a = tail call i1024 %f()
+ ret i1024 %a
+}
+
+attributes #0 = { nounwind }