[InstCombine] Fix infinite loop in min/max load/store bitcast combine (PR44835)

Fixes https://bugs.llvm.org/show_bug.cgi?id=44835. Skip the transform
if it wouldn't actually do anything (apart from removing and reinserting
the same instructions).

Note that the test case doesn't loop on current master anymore, only
on the LLVM 10 release branch. The issue is already mitigated on master
due to worklist order fixes, but we should fix the root cause there as well.

As a side note, we should probably assert in combineLoadToNewType()
that it does not combine to the same type. Not doing this here, because
this assertion would also be triggered in another place right now.

Differential Revision: https://reviews.llvm.org/D74278

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
index a2be015..4db4826 100644 (file)
--- a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
@@ -1320,6 +1320,11 @@ static bool removeBitcastsFromLoadStoreOnMinMax(InstCombiner &IC,
   if (!isMinMaxWithLoads(LoadAddr, CmpLoadTy))
     return false;
 
+  // Make sure the type would actually change.
+  // This condition can be hit with chains of bitcasts.
+  if (LI->getType() == CmpLoadTy)
+    return false;
+
   // Make sure we're not changing the size of the load/store.
   const auto &DL = IC.getDataLayout();
   if (DL.getTypeStoreSizeInBits(LI->getType()) !=

diff --git a/llvm/test/Transforms/InstCombine/pr44835.ll b/llvm/test/Transforms/InstCombine/pr44835.ll
new file mode 100644 (file)
index 0000000..46c9fca
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/pr44835.ll
@@ -0,0 +1,29 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -instcombine < %s | FileCheck %s
+
+; This test used to cause an infinite loop in the load/store min/max bitcast
+; transform.
+
+define void @test(i32* %p, i32* %p2) {
+; CHECK-LABEL: @test(
+; CHECK-NEXT:    [[V:%.*]] = load i32, i32* [[P:%.*]], align 4
+; CHECK-NEXT:    [[V2:%.*]] = load i32, i32* [[P2:%.*]], align 4
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i32 [[V2]], [[V]]
+; CHECK-NEXT:    [[TMP1:%.*]] = select i1 [[CMP]], i32 [[V2]], i32 [[V]]
+; CHECK-NEXT:    store i32 [[TMP1]], i32* [[P]], align 4
+; CHECK-NEXT:    ret void
+;
+  %v = load i32, i32* %p, align 4
+  %v2 = load i32, i32* %p2, align 4
+  %cmp = icmp ult i32 %v2, %v
+  %sel = select i1 %cmp, i32* %p2, i32* %p
+  %p8 = bitcast i32* %p to i8*
+  %sel8 = bitcast i32* %sel to i8*
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %p8, i8* align 4 %sel8, i64 4, i1 false)
+  ret void
+}
+
+; Function Attrs: argmemonly nounwind willreturn
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i64, i1 immarg) #0
+
+attributes #0 = { argmemonly nounwind willreturn }