Fix a stackmap bug introduced in r220710.

For a call to not return in to the stackmap shadow, the shadow must end with the call.

To do this, we must insert any required nops *before* the call, and not after it.

llvm-svn: 220728

2 files changed, 21 insertions, 6 deletions

diff --git a/llvm/lib/Target/X86/X86MCInstLower.cpp b/llvm/lib/Target/X86/X86MCInstLower.cpp
index 85cf5144f0c..4e0d594238c 100644
--- a/llvm/lib/Target/X86/X86MCInstLower.cpp
+++ b/llvm/lib/Target/X86/X86MCInstLower.cpp
@@ -1209,11 +1209,21 @@ 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())
+  // in a call towards the shadow, but must ensure that the no thread returns
+  // in to the stackmap shadow.  The only way to achieve this is if the call
+  // is at the end of the shadow.
+  if (MI->isCall()) {
+    // Count then size of the call towards the shadow
+    SMShadowTracker.count(TmpInst, getSubtargetInfo());
+    // Then flush the shadow so that we fill with nops before the call, not
+    // after it.
     SMShadowTracker.emitShadowPadding(OutStreamer, getSubtargetInfo());
+    // Then emit the call
+    OutStreamer.EmitInstruction(TmpInst, getSubtargetInfo());
+    return;
+  }
+
+  EmitAndCountInstruction(TmpInst);
 }
diff --git a/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll b/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll
index f640b9e6f6c..a3725f2c5b7 100644
--- a/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll
+++ b/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll
@@ -5,17 +5,22 @@
 ; 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.
+; Note that in order for a thread to not return in to the patched space
+; the call must be at the end of the shadow, so the required nop must be
+; before the call, not after.
 define void @shadow_optimization_test() {
 entry:
 ; CHECK-LABEL:  shadow_optimization_test:
 ; CHECK:        callq   _bar
+; CHECK:        nop
+; CHECK:        callq   _bar
 ; CHECK-NOT:    nop
 ; CHECK:        callq   _bar
-; CHECK:        nop
-; CHECK:        retq
+; CHECK-NOT:    nop
   call void @bar()
   tail call void (i64, i32, ...)* @llvm.experimental.stackmap(i64 0, i32 8)
   call void @bar()
+  call void @bar()
   ret void
 }