[AArch64][Stackmaps] Optimize stackmap shadows on AArch64.

Reduce the number of nops emitted for stackmap shadows on AArch64 by counting
non-stackmap instructions up to the next branch target towards the requested
shadow.

<rdar://problem/14959522>

llvm-svn: 223156

2 files changed, 31 insertions, 1 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp b/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp
index 8bee4f51351..08ee687d84a 100644
--- a/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp
+++ b/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp
@@ -381,8 +381,23 @@ void AArch64AsmPrinter::LowerSTACKMAP(MCStreamer &OutStreamer, StackMaps &SM,
   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));
 }
diff --git a/llvm/test/CodeGen/AArch64/arm64-stackmap-nops.ll b/llvm/test/CodeGen/AArch64/arm64-stackmap-nops.ll
new file mode 100644
index 00000000000..5915b64edf0
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/arm64-stackmap-nops.ll
@@ -0,0 +1,15 @@
+; 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, ...)