TargetLowering: fix an infinite DAG combine in SimplifySETCC

TargetLowering::SimplifySetCC wants to swap the operands of a SETCC to
canonicalize the constant to the RHS. The bug here was that it did so whether
or not the RHS was already a constant, leading to an infinite loop.

rdar://111847838

Differential revision: https://reviews.llvm.org/D155095

Author: jroelofs

llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp

@@ -4227,12 +4227,12 @@ SDValue TargetLowering::SimplifySetCC(EVT VT, SDValue N0, SDValue N1,
   bool N1ConstOrSplat =
       isConstOrConstSplat(N1, /*AllowUndefs*/ false, /*AllowTruncate*/ true);
 
-  // Ensure that the constant occurs on the RHS and fold constant comparisons.
+  // Canonicalize toward having the constant on the RHS.
   // TODO: Handle non-splat vector constants. All undef causes trouble.
   // FIXME: We can't yet fold constant scalable vector splats, so avoid an
   // infinite loop here when we encounter one.
   ISD::CondCode SwappedCC = ISD::getSetCCSwappedOperands(Cond);
-  if (N0ConstOrSplat && (!OpVT.isScalableVector() || !N1ConstOrSplat) &&
+  if (N0ConstOrSplat && !N1ConstOrSplat && !OpVT.isScalableVector() &&
       (DCI.isBeforeLegalizeOps() ||
        isCondCodeLegal(SwappedCC, N0.getSimpleValueType())))
     return DAG.getSetCC(dl, VT, N1, N0, SwappedCC);

llvm/test/CodeGen/AArch64/arm64-setcc-swap-infloop.ll

@@ -0,0 +1,33 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=arm64-apple-ios --global-isel=0 | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
+target triple = "arm64-apple-ios"
+
+declare void @llvm.memset.p0.i64(ptr nocapture writeonly, i8, i64, i1 immarg)
+
+; TargetLowering::SimplifySetCC wants to swap the operands of a SETCC to
+; canonicalize the constant to the RHS. The bug here was that it did so whether
+; or not the RHS was already a constant, leading to an infinite loop.
+define <16 x i1> @setcc_swap_infloop(ptr %arg) {
+; CHECK-LABEL: setcc_swap_infloop:
+; CHECK:       ; %bb.0:
+; CHECK-NEXT:    mov x8, xzr
+; CHECK-NEXT:    mov w9, #16 ; =0x10
+; CHECK-NEXT:    movi.16b v1, #1
+; CHECK-NEXT:    ldr q0, [x8]
+; CHECK-NEXT:    cmeq.16b v2, v1, #0
+; CHECK-NEXT:    str q1, [x8]
+; CHECK-NEXT:    cmeq.16b v0, v0, #0
+; CHECK-NEXT:    str q1, [x9]
+; CHECK-NEXT:    orr.16b v0, v0, v2
+; CHECK-NEXT:    ret
+  call void @llvm.memset.p0.i64(ptr nonnull null, i8 1, i64 32, i1 false)
+  %v = getelementptr inbounds i8, ptr null, i64 16
+  %v14 = load <16 x i8>, ptr undef, align 32
+  %v15 = icmp eq <16 x i8> %v14, zeroinitializer
+  %v16 = load <16 x i8>, ptr %v, align 16
+  %v17 = icmp eq <16 x i8> %v16, zeroinitializer
+  %v20 = or <16 x i1> %v15, %v17
+  ret <16 x i1> %v20
+}