Stackmap shadows should consider call returns a branch target.

To avoid emitting too many nops, a stackmap shadow can include emitted instructions in the shadow, but these must not include branch targets.

A return from a call should count as a branch target as patching over the instructions after the call would lead to incorrect behaviour for threads currently making that call, when they return.

llvm-svn: 220710

2 files changed, 12 insertions, 4 deletions

diff --git a/llvm/lib/Target/X86/X86MCInstLower.cpp b/llvm/lib/Target/X86/X86MCInstLower.cpp
index fc3662e6bec..85cf5144f0c 100644
--- a/llvm/lib/Target/X86/X86MCInstLower.cpp
+++ b/llvm/lib/Target/X86/X86MCInstLower.cpp
@@ -1210,4 +1210,10 @@ void X86AsmPrinter::EmitInstruction(const MachineInstr *MI) {
   MCInst TmpInst;
   MCInstLowering.Lower(MI, TmpInst);
   EmitAndCountInstruction(TmpInst);
+
+  // Stackmap shadows cannot include branch targets, so we can count the bytes
+  // in a call towards the shadow, but must flush the shadow immediately after
+  // to account for the return from the call.
+  if (MI->isCall())
+    SMShadowTracker.emitShadowPadding(OutStreamer, getSubtargetInfo());
 }
diff --git a/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll b/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll
index 6f7c5935b8f..f640b9e6f6c 100644
--- a/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll
+++ b/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll
@@ -1,16 +1,18 @@
 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 | FileCheck %s
 
-; Check that the X86 stackmap shadow optimization is only outputting a 1-byte
-; nop here. 8-bytes are requested, but 7 are covered by the code for the call to
-; bar, the frame teardown and the return.
+; Check that the X86 stackmap shadow optimization is only outputting a 3-byte
+; nop here. 8-bytes are requested, but 5 are covered by the code for the call to
+; bar.  However, the frame teardown and the return do not count towards the
+; stackmap shadow as the call return counts as a branch target so must flush
+; the shadow.
 define void @shadow_optimization_test() {
 entry:
 ; CHECK-LABEL:  shadow_optimization_test:
 ; CHECK:        callq   _bar
 ; CHECK-NOT:    nop
 ; CHECK:        callq   _bar
-; CHECK:        retq
 ; CHECK:        nop
+; CHECK:        retq
   call void @bar()
   tail call void (i64, i32, ...)* @llvm.experimental.stackmap(i64 0, i32 8)
   call void @bar()