[flang] Do not leave length parameters uninitialized in descriptor addendums (#81858)

Descriptor addendum have a field to hold length parameters (currently
only one). This field is currently never used because flang does not
lowered derived types with length parameters.

However, leaving it uninitialized is causing bugs in code like gFTL
where the code is trying to sort POINTERs (see [1]). More precisely, it
is an issue when two pointers should compare equal (same base address),
because the uninitialized values in the addendum may differ depending on
the "stack history" and optimization level.

Always initialized the length parameters field in the addendum to zero.

[1]:
https://github.com/Goddard-Fortran-Ecosystem/gFTL/blob/dc93a5fc2fe2b487590580d9f0a17d77ca3fe5c1/include/v1/templates/set_impl.inc#L312

The type being transferred to an integer array may look like:

```
   TYPE :: localwrapper
    TYPE(T), POINTER :: item
   END TYPE localwrapper
```

Which in flang case ends-up transferring a descriptor to an integer
array, the code in gFTL later compare the integer arrays. This logic is
used when building set data structures in gFTL.

7 files changed, 31 insertions, 14 deletions

diff --git a/flang/include/flang/Runtime/descriptor.h b/flang/include/flang/Runtime/descriptor.h
index 38ab415..7ad548d 100644
--- a/flang/include/flang/Runtime/descriptor.h
+++ b/flang/include/flang/Runtime/descriptor.h
@@ -99,7 +99,7 @@ class DescriptorAddendum {
 public:
   explicit RT_API_ATTRS DescriptorAddendum(
       const typeInfo::DerivedType *dt = nullptr)
-      : derivedType_{dt} {}
+      : derivedType_{dt}, len_{0} {}
   RT_API_ATTRS DescriptorAddendum &operator=(const DescriptorAddendum &);
 
   const RT_API_ATTRS typeInfo::DerivedType *derivedType() const {
diff --git a/flang/lib/Optimizer/CodeGen/CodeGen.cpp b/flang/lib/Optimizer/CodeGen/CodeGen.cpp
index f89f28c..7fdf39a 100644
--- a/flang/lib/Optimizer/CodeGen/CodeGen.cpp
+++ b/flang/lib/Optimizer/CodeGen/CodeGen.cpp
@@ -147,6 +147,9 @@ static unsigned getTypeDescFieldId(mlir::Type ty) {
   auto isArray = fir::dyn_cast_ptrOrBoxEleTy(ty).isa<fir::SequenceType>();
   return isArray ? kOptTypePtrPosInBox : kDimsPosInBox;
 }
+static unsigned getLenParamFieldId(mlir::Type ty) {
+  return getTypeDescFieldId(ty) + 1;
+}
 
 namespace {
 /// FIR conversion pattern template
@@ -1583,6 +1586,14 @@ struct EmboxCommonConversion : public FIROpConversion<OP> {
         descriptor =
             insertField(rewriter, loc, descriptor, {typeDescFieldId}, typeDesc,
                         /*bitCast=*/true);
+      // Always initialize the length parameter field to zero to avoid issues
+      // with uninitialized values in Fortran code trying to compare physical
+      // representation of derived types with pointer/allocatable components.
+      // This has been seen in hashing algorithms using TRANSFER.
+      mlir::Value zero =
+          genConstantIndex(loc, rewriter.getI64Type(), rewriter, 0);
+      descriptor = insertField(rewriter, loc, descriptor,
+                               {getLenParamFieldId(boxTy), 0}, zero);
     }
     return descriptor;
   }
diff --git a/flang/test/Fir/ignore-missing-type-descriptor.fir b/flang/test/Fir/ignore-missing-type-descriptor.fir
index f55ea12..e83c8d6 100644
--- a/flang/test/Fir/ignore-missing-type-descriptor.fir
+++ b/flang/test/Fir/ignore-missing-type-descriptor.fir
@@ -18,5 +18,5 @@ func.func @test_embox(%addr: !fir.ref<!some_freestyle_type>) {
 // CHECK-SAME: ptr %[[ADDR:.*]])
 // CHECK: insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }
 // CHECK-SAME: { ptr undef, i64 ptrtoint (ptr getelementptr (%some_not_mangled_type, ptr null, i32 1) to i64),
-// CHECK-SAME: i32 20180515, i8 0, i8 42, i8 0, i8 1, ptr null, [1 x i64] undef },
+// CHECK-SAME: i32 20180515, i8 0, i8 42, i8 0, i8 1, ptr null, [1 x i64] zeroinitializer },
 // CHECK-SAME: ptr %[[ADDR]], 0
diff --git a/flang/test/Fir/polymorphic.fir b/flang/test/Fir/polymorphic.fir
index ecdcdeb..fc891c3 100644
--- a/flang/test/Fir/polymorphic.fir
+++ b/flang/test/Fir/polymorphic.fir
@@ -13,7 +13,7 @@ func.func @_QMpolymorphic_testPtest_allocate_unlimited_polymorphic_non_derived()
 // CHECK-LABEL: define void @_QMpolymorphic_testPtest_allocate_unlimited_polymorphic_non_derived(){{.*}}{
 // CHECK:   %[[MEM:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }
 // CHECK:   %[[DESC:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }, i64 1
-// CHECK:   store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } { ptr null, i64 0, i32 20180515, i8 0, i8 -1, i8 1, i8 1, ptr null, [1 x i64] undef }, ptr %[[MEM]]
+// CHECK:   store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } { ptr null, i64 0, i32 20180515, i8 0, i8 -1, i8 1, i8 1, ptr null, [1 x i64] zeroinitializer }, ptr %[[MEM]]
 // CHECK:   %[[LOADED:.*]] = load { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }, ptr %[[MEM]], align 8
 // CHECK:   store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[LOADED]], ptr %[[DESC]]
 // CHECK:   ret void
@@ -100,7 +100,8 @@ func.func @_QMunlimitedPsub1(%arg0: !fir.class<!fir.array<?xnone>> {fir.bindc_na
 // CHECK: %[[TYPE_CODE_TRUNC:.*]] = trunc i32 %[[TYPE_CODE]] to i8
 // CHECK: %{{.*}} = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %{{.*}}, i8 %[[TYPE_CODE_TRUNC]], 4
 // CHECK: %{{.*}} = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %{{.*}}, ptr %[[TYPE_DESC]], 7
-// CHECK: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %24, ptr %[[BOX]]
+// CHECK: %{{.*}} = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %{{.*}}, i64 0, 8, 0
+// CHECK: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %{{.*}}, ptr %[[BOX]]
 
 
 fir.global internal @_QFEx : !fir.class<!fir.ptr<!fir.array<?xnone>>> {
@@ -154,7 +155,7 @@ func.func @_QQmain() {
 // CHECK-LABEL: define void @_QQmain(){{.*}}{
 // CHECK: %[[CLASS_NONE:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }
 // CHECK: %[[DESC:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }, i64 1
-// CHECK: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } { ptr @_QMmod1Ea, i64 ptrtoint (ptr getelementptr (%_QMmod1TtK2, ptr null, i32 1) to i64), i32 20180515, i8 0, i8 42, i8 1, i8 1, ptr @_QMmod1E.dt.t.2, [1 x i64] undef }, ptr %[[CLASS_NONE]], align 8
+// CHECK: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } { ptr @_QMmod1Ea, i64 ptrtoint (ptr getelementptr (%_QMmod1TtK2, ptr null, i32 1) to i64), i32 20180515, i8 0, i8 42, i8 1, i8 1, ptr @_QMmod1E.dt.t.2, [1 x i64] zeroinitializer }, ptr %[[CLASS_NONE]], align 8
 // CHECK: %[[LOAD:.*]] = load { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }, ptr %[[CLASS_NONE]]
 // CHECK: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[LOAD]], ptr %[[DESC]]
 // CHECK: call void @_QMmod1Psub1(ptr %[[DESC]])
@@ -194,4 +195,4 @@ func.func @_QQembox_input_type(%arg0 : !fir.ref<!fir.type<_QMmod1Tp2{v:!fir.arra
 }
 
 // CHECK-LABEL: define void @_QQembox_input_type
-// CHECK: %{{.*}} = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } { ptr undef, i64 ptrtoint (ptr getelementptr (%_QMmod1Tp2, ptr null, i32 1) to i64), i32 20180515, i8 0, i8 42, i8 0, i8 1, ptr @_QMmod1E.dt.p2, [1 x i64] undef }, ptr %{{.*}}, 0
+// CHECK: %{{.*}} = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } { ptr undef, i64 ptrtoint (ptr getelementptr (%_QMmod1Tp2, ptr null, i32 1) to i64), i32 20180515, i8 0, i8 42, i8 0, i8 1, ptr @_QMmod1E.dt.p2, [1 x i64] zeroinitializer }, ptr %{{.*}}, 0
diff --git a/flang/test/Fir/tbaa.fir b/flang/test/Fir/tbaa.fir
index 4474bbb..048f53f 100644
--- a/flang/test/Fir/tbaa.fir
+++ b/flang/test/Fir/tbaa.fir
@@ -67,7 +67,8 @@ module {
 // CHECK:           %[[VAL_36:.*]] = llvm.mlir.constant(1 : i32) : i32
 // CHECK:           %[[VAL_37:.*]] = llvm.trunc %[[VAL_36]] : i32 to i8
 // CHECK:           %[[VAL_38:.*]] = llvm.insertvalue %[[VAL_37]], %[[VAL_35]][6] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, ptr, array<1 x i64>)>
-// CHECK:           %[[VAL_40:.*]] = llvm.insertvalue %[[VAL_19]], %[[VAL_38]][7] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, ptr, array<1 x i64>)>
+// CHECK:           %[[VAL_40B:.*]] = llvm.insertvalue %[[VAL_19]], %[[VAL_38]][7] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, ptr, array<1 x i64>)>
+// CHECK:           %[[VAL_40:.*]] = llvm.insertvalue %{{.*}}, %[[VAL_40B]][8, 0] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, ptr, array<1 x i64>)>
 // CHECK:           %[[VAL_42:.*]] = llvm.insertvalue %[[VAL_14]], %[[VAL_40]][0] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, ptr, array<1 x i64>)>
 // CHECK:           llvm.store %[[VAL_42]], %[[VAL_2]] {tbaa = [#[[$BOXT]]]} : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, ptr, array<1 x i64>)>, !llvm.ptr
 // CHECK:           %[[VAL_43:.*]] = llvm.getelementptr %[[VAL_2]][0, 4] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, ptr, array<1 x i64>)>
@@ -166,7 +167,8 @@ module {
 // CHECK:           %[[VAL_40:.*]] = llvm.mlir.constant(1 : i32) : i32
 // CHECK:           %[[VAL_41:.*]] = llvm.trunc %[[VAL_40]] : i32 to i8
 // CHECK:           %[[VAL_42:.*]] = llvm.insertvalue %[[VAL_41]], %[[VAL_39]][6] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
-// CHECK:           %[[VAL_44:.*]] = llvm.insertvalue %[[VAL_27]], %[[VAL_42]][8] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
+// CHECK:           %[[VAL_44B:.*]] = llvm.insertvalue %[[VAL_27]], %[[VAL_42]][8] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
+// CHECK:           %[[VAL_44:.*]] = llvm.insertvalue %{{.*}}, %[[VAL_44B]][9, 0] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
 // CHECK:           %[[VAL_45:.*]] = llvm.getelementptr %[[VAL_3]][0, 7, 0, 0] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
 // CHECK:           %[[VAL_46:.*]] = llvm.load %[[VAL_45]] {tbaa = [#[[$BOXT]]]} : !llvm.ptr -> i64
 // CHECK:           %[[VAL_47:.*]] = llvm.getelementptr %[[VAL_3]][0, 7, 0, 1] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
@@ -218,7 +220,8 @@ module {
 // CHECK:           %[[VAL_17:.*]] = llvm.trunc %[[VAL_16]] : i32 to i8
 // CHECK:           %[[VAL_18:.*]] = llvm.insertvalue %[[VAL_17]], %[[VAL_15]][6] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
 // CHECK:           %[[VAL_19:.*]] = llvm.mlir.zero : !llvm.ptr
-// CHECK:           %[[VAL_21:.*]] = llvm.insertvalue %[[VAL_19]], %[[VAL_18]][8] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
+// CHECK:           %[[VAL_21B:.*]] = llvm.insertvalue %[[VAL_19]], %[[VAL_18]][8] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
+// CHECK:           %[[VAL_21:.*]] = llvm.insertvalue %{{.*}}, %[[VAL_21B]][9, 0] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
 // CHECK:           %[[VAL_22:.*]] = llvm.mlir.constant(0 : i64) : i64
 // CHECK:           %[[VAL_23:.*]] = llvm.mlir.constant(1 : i64) : i64
 // CHECK:           %[[VAL_24:.*]] = llvm.insertvalue %[[VAL_23]], %[[VAL_21]][7, 0, 0] : !llvm.struct<(ptr, i64, i32, i8, i8, i8, i8, array<1 x array<3 x i64>>, ptr, array<1 x i64>)>
diff --git a/flang/test/Fir/type-descriptor.fir b/flang/test/Fir/type-descriptor.fir
index c536209..6551efe 100644
--- a/flang/test/Fir/type-descriptor.fir
+++ b/flang/test/Fir/type-descriptor.fir
@@ -14,7 +14,7 @@ fir.global internal @_QFfooEx : !fir.box<!fir.heap<!sometype>> {
 }
 // CHECK: @_QFfooEx = internal global { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }
 // CHECK-SAME: { ptr null, i64 ptrtoint (ptr getelementptr (%_QFfooTsometype, ptr null, i32 1) to i64),
-// CHECK-SAME: i32 20180515, i8 0, i8 42, i8 2, i8 1, ptr @_QFfooE.dt.sometype, [1 x i64] undef }
+// CHECK-SAME: i32 20180515, i8 0, i8 42, i8 2, i8 1, ptr @_QFfooE.dt.sometype, [1 x i64] zeroinitializer }
 
 !some_pdt_type = !fir.type<_QFfooTsome_pdt_typeK42K43{num:i32,values:!fir.box<!fir.ptr<!fir.array<?x?xf32>>>}>
 fir.global internal @_QFfooE.dt.some_pdt_type.42.43 constant : i8
@@ -26,4 +26,4 @@ fir.global internal @_QFfooEx2 : !fir.box<!fir.heap<!some_pdt_type>> {
 }
 // CHECK: @_QFfooEx2 = internal global { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }
 // CHECK-SAME: { ptr null, i64 ptrtoint (ptr getelementptr (%_QFfooTsome_pdt_typeK42K43, ptr null, i32 1) to i64),
-// CHECK-SAME: i32 20180515, i8 0, i8 42, i8 2, i8 1, ptr @_QFfooE.dt.some_pdt_type.42.43, [1 x i64] undef }
+// CHECK-SAME: i32 20180515, i8 0, i8 42, i8 2, i8 1, ptr @_QFfooE.dt.some_pdt_type.42.43, [1 x i64] zeroinitializer }
diff --git a/flang/test/Lower/allocatable-polymorphic.f90 b/flang/test/Lower/allocatable-polymorphic.f90
index f430214..6ba0b13 100644
--- a/flang/test/Lower/allocatable-polymorphic.f90
+++ b/flang/test/Lower/allocatable-polymorphic.f90
@@ -649,7 +649,8 @@ end
 ! LLVM: %[[BOX3:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX2]], i8 %[[TYPE_CODE_TRUNC]], 4
 ! LLVM: %[[BOX4:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX3]], i8 0, 5
 ! LLVM: %[[BOX5:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX4]], i8 1, 6
-! LLVM: %[[BOX6:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX5]], ptr %[[TDESC_C3]], 7
+! LLVM: %[[BOX6A:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX5]], ptr %[[TDESC_C3]], 7
+! LLVM: %[[BOX6:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX6A]], i64 0, 8, 0
 ! LLVM: %[[BOX7:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX6]], ptr %{{.*}}, 0
 ! LLVM: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX7]], ptr %{{.*}}
 ! LLVM: call void %{{.*}}(ptr %{{.*}})
@@ -669,7 +670,8 @@ end
 ! LLVM: %[[BOX3:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX2]], i8 %[[TYPE_CODE_TRUNC]], 4
 ! LLVM: %[[BOX4:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX3]], i8 0, 5
 ! LLVM: %[[BOX5:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX4]], i8 1, 6
-! LLVM: %[[BOX6:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX5]], ptr %[[TDESC_C4]], 7
+! LLVM: %[[BOX6A:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX5]], ptr %[[TDESC_C4]], 7
+! LLVM: %[[BOX6:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX6A]], i64 0, 8, 0
 ! LLVM: %[[BOX7:.*]] = insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX6]], ptr %{{.*}}, 0
 ! LLVM: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[BOX7]], ptr %{{.*}}
 ! LLVM: call void %{{.*}}(ptr %{{.*}})
@@ -679,7 +681,7 @@ end
 ! allocatable.
 
 ! LLVM-LABEL: define void @_QMpolyPtest_deallocate()
-! LLVM: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } { ptr null, i64 ptrtoint (ptr getelementptr (%_QMpolyTp1, ptr null, i32 1) to i64), i32 20180515, i8 0, i8 42, i8 2, i8 1, ptr @_QMpolyE.dt.p1, [1 x i64] undef }, ptr %[[ALLOCA1:[0-9]*]]
+! LLVM: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } { ptr null, i64 ptrtoint (ptr getelementptr (%_QMpolyTp1, ptr null, i32 1) to i64), i32 20180515, i8 0, i8 42, i8 2, i8 1, ptr @_QMpolyE.dt.p1, [1 x i64] zeroinitializer }, ptr %[[ALLOCA1:[0-9]*]]
 ! LLVM: %[[LOAD:.*]] = load { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }, ptr %[[ALLOCA1]]
 ! LLVM: store { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] } %[[LOAD]], ptr %[[ALLOCA2:[0-9]*]]
 ! LLVM: %{{.*}} = call {} @_FortranAAllocatableInitDerivedForAllocate(ptr %[[ALLOCA2]], ptr @_QMpolyE.dt.p1, i32 0, i32 0)