unsigned NumNOPBytes = MI.getOperand(1).getImm();
SM.recordStackMap(MI);
- // Emit padding.
assert(NumNOPBytes % 4 == 0 && "Invalid number of NOP bytes requested!");
+
+ // Scan ahead to trim the shadow.
+ const MachineBasicBlock &MBB = *MI.getParent();
+ MachineBasicBlock::const_iterator MII(MI);
+ ++MII;
+ while (NumNOPBytes > 0) {
+ if (MII == MBB.end() || MII->isCall() ||
+ MII->getOpcode() == AArch64::DBG_VALUE ||
+ MII->getOpcode() == TargetOpcode::PATCHPOINT ||
+ MII->getOpcode() == TargetOpcode::STACKMAP)
+ break;
+ ++MII;
+ NumNOPBytes -= 4;
+ }
+
+ // Emit nops.
for (unsigned i = 0; i < NumNOPBytes; i += 4)
EmitToStreamer(OutStreamer, MCInstBuilder(AArch64::HINT).addImm(0));
}
--- /dev/null
+; RUN: llc < %s -mtriple=arm64-apple-darwin | FileCheck %s
+
+define void @test_shadow_optimization() {
+entry:
+; Expect 8 bytes worth of nops here rather than 16: With the shadow optimization
+; in place, 8 bytes will be consumed by the frame teardown and return instr.
+; CHECK-LABEL: test_shadow_optimization:
+; CHECK: nop
+; CHECK-NEXT: nop
+; CHECK-NOT: nop
+ tail call void (i64, i32, ...)* @llvm.experimental.stackmap(i64 0, i32 16)
+ ret void
+}
+
+declare void @llvm.experimental.stackmap(i64, i32, ...)