[BPF] annotate DIType metadata for builtin preseve_array_access_index()

[yonghong-song]

Summary

Previously, debuginfo types are annotated to
IR builtin preserve_struct_access_index() and
preserve_union_access_index(), but not
preserve_array_access_index(). The debug info
is useful to identify the root type name which
later will be used for type comparison.

For user access without explicit type conversions,
the previous scheme works as we can ignore intermediate
compiler generated type conversions (e.g., from union types to
union members) and still generate correct access index string.

The issue comes with user explicit type conversions, e.g.,
converting an array to a structure like below:

struct t { int a; char b[40]; };
struct p { int c; int d; };
struct t *var = ...;
... __builtin_preserve_access_index(&(((struct p *)&(var->b[0]))->d)) ...

Although BPF backend can derive the type of &(var->b[0]),
explicit type annotation make checking more consistent
and less error prone.

Another benefit is for multiple dimension array handling.
For example,

struct p { int c; int d; } g[8][9][10];
... __builtin_preserve_access_index(&g[2][3][4].d) ...

It would be possible to calculate the number of "struct p"'s
before accessing its member "d" if array debug info is
available as it contains each dimension range.

This patch enables to annotate IR builtin preserve_array_access_index()
with proper debuginfo type. The unit test case and language reference
is updated as well.

[yonghong-song]

The clang change https://reviews.llvm.org/D65615.
The BPF backend change https://reviews.llvm.org/D65618.

[yonghong-song]

abandon this one. use git monorepo https://reviews.llvm.org/D65664 since we have llvm/clang inter-dependence here.

docs/LangRef.rst

 Overview:
 """""""""
 
 The '``llvm.preserve.array.access.index``' intrinsic returns the getelementptr address
 based on array base ``base``, array dimension ``dim`` and the last access index ``index``
 into the array. The return type ``ret_type`` is a pointer type to the array element.
 The array ``dim`` and ``index`` are preserved which is more robust than
 getelementptr instruction which may be subject to compiler transformation.
+The ``llvm.preserve.access.index`` type of metadata is attached to this call instruction
+to provide array or pointer debuginfo type.
+The metadata is a ``DICompositeType`` or ``DIDerivedType`` representing the
+debuginfo version of ``type``.
 
 Arguments:
 """"""""""
 
 The ``base`` is the array base address.  The ``dim`` is the array dimension.
 The ``base`` is a pointer if ``dim`` equals 0.
 The ``index`` is the last access index into the array or pointer.
 

include/llvm/IR/IRBuilder.h

assert(ExtractedTy->getBitWidth() <= IntTy->getBitWidth() &&
            "Cannot extract to a larger integer!");
     if (ExtractedTy != IntTy) {
       V = CreateTrunc(V, ExtractedTy, Name + ".trunc");
     }
     return V;
   }
 
   Value *CreatePreserveArrayAccessIndex(Value *Base, unsigned Dimension,
-                                        unsigned LastIndex) {
+                                        unsigned LastIndex, MDNode *DbgInfo) {
     assert(isa<PointerType>(Base->getType()) &&
            "Invalid Base ptr type for preserve.array.access.index.");
     auto *BaseType = Base->getType();
 
     Value *LastIndexV = getInt32(LastIndex);
     Constant *Zero = ConstantInt::get(Type::getInt32Ty(Context), 0);
     SmallVector<Value *, 4> IdxList;
     for (unsigned I = 0; I < Dimension; ++I)
       IdxList.push_back(Zero);
     IdxList.push_back(LastIndexV);
 
     Type *ResultType =
         GetElementPtrInst::getGEPReturnType(Base, IdxList);
 
     Module *M = BB->getParent()->getParent();
     Function *FnPreserveArrayAccessIndex = Intrinsic::getDeclaration(
         M, Intrinsic::preserve_array_access_index, {ResultType, BaseType});
 
     Value *DimV = getInt32(Dimension);
     CallInst *Fn =
         CreateCall(FnPreserveArrayAccessIndex, {Base, DimV, LastIndexV});
+    Fn->setMetadata(LLVMContext::MD_preserve_access_index, DbgInfo);
 
     return Fn;
   }
 
   Value *CreatePreserveUnionAccessIndex(Value *Base, unsigned FieldIndex,
                                         MDNode *DbgInfo) {
     assert(isa<PointerType>(Base->getType()) &&
            "Invalid Base ptr type for preserve.union.access.index.");

test/CodeGen/BPF/CORE/intrinsic-array.ll

 ; RUN: llc -march=bpfel -filetype=asm -o - %s | FileCheck %s
 ;
 ; Source code:
 ;   #define _(x) (__builtin_preserve_access_index(x))
 ;   struct s { int a; int b; };
 ;   int get_value(const void *addr);
 ;   int test(struct s *arg) { return get_value(_(&arg[2].b)); }
 ; Compiler flag to generate IR:
 ;   clang -target bpf -S -O2 -g -emit-llvm test.c
 
 %struct.s = type { i32, i32 }
 
 ; Function Attrs: nounwind
 define dso_local i32 @test(%struct.s* %arg) local_unnamed_addr #0 !dbg !7 {
 entry:
   call void @llvm.dbg.value(metadata %struct.s* %arg, metadata !17, metadata !DIExpression()), !dbg !18
-  %0 = tail call %struct.s* @llvm.preserve.array.access.index.p0s_struct.ss.p0s_struct.ss(%struct.s* %arg, i32 0, i32 2), !dbg !19
+  %0 = tail call %struct.s* @llvm.preserve.array.access.index.p0s_struct.ss.p0s_struct.ss(%struct.s* %arg, i32 0, i32 2), !dbg !19, !llvm.preserve.access.index !11
   %1 = tail call i32* @llvm.preserve.struct.access.index.p0i32.p0s_struct.ss(%struct.s* %0, i32 1, i32 1), !dbg !19, !llvm.preserve.access.index !12
   %2 = bitcast i32* %1 to i8*, !dbg !19
   %call = tail call i32 @get_value(i8* %2) #4, !dbg !20
   ret i32 %call, !dbg !21
 }
 ; CHECK-LABEL: test
 ; CHECK:       [[RELOC:.Ltmp[0-9]+]]
 ; CHECK:       r2 = 20