[BPF] annotate DIType metadata for builtin preseve_array_access_index()

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.

Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D65664

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@367724 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CGExpr.cpp b/lib/CodeGen/CGExpr.cpp
index 5a4b1188b71147d90ec651efd617154c6fa8417e..8a171e6a3531e8001288c417ce5efcc65321b40f 100644 (file)
--- a/lib/CodeGen/CGExpr.cpp
+++ b/lib/CodeGen/CGExpr.cpp
@@ -3400,6 +3400,7 @@ static Address emitArraySubscriptGEP(CodeGenFunction &CGF, Address addr,
                                      ArrayRef<llvm::Value *> indices,
                                      QualType eltType, bool inbounds,
                                      bool signedIndices, SourceLocation loc,
+                                     QualType *arrayType = nullptr,
                                      const llvm::Twine &name = "arrayidx") {
   // All the indices except that last must be zero.
 #ifndef NDEBUG
@@ -3428,9 +3429,12 @@ static Address emitArraySubscriptGEP(CodeGenFunction &CGF, Address addr,
   } else {
     // Remember the original array subscript for bpf target
     unsigned idx = LastIndex->getZExtValue();
+    llvm::DIType *DbgInfo = nullptr;
+    if (arrayType)
+      DbgInfo = CGF.getDebugInfo()->getOrCreateStandaloneType(*arrayType, loc);
     eltPtr = CGF.Builder.CreatePreserveArrayAccessIndex(addr.getPointer(),
                                                         indices.size() - 1,
-                                                        idx);
+                                                        idx, DbgInfo);
   }
 
   return Address(eltPtr, eltAlign);
@@ -3567,19 +3571,21 @@ LValue CodeGenFunction::EmitArraySubscriptExpr(const ArraySubscriptExpr *E,
     auto *Idx = EmitIdxAfterBase(/*Promote*/true);
 
     // Propagate the alignment from the array itself to the result.
+    QualType arrayType = Array->getType();
     Addr = emitArraySubscriptGEP(
         *this, ArrayLV.getAddress(), {CGM.getSize(CharUnits::Zero()), Idx},
         E->getType(), !getLangOpts().isSignedOverflowDefined(), SignedIndices,
-        E->getExprLoc());
+        E->getExprLoc(), &arrayType);
     EltBaseInfo = ArrayLV.getBaseInfo();
     EltTBAAInfo = CGM.getTBAAInfoForSubobject(ArrayLV, E->getType());
   } else {
     // The base must be a pointer; emit it with an estimate of its alignment.
     Addr = EmitPointerWithAlignment(E->getBase(), &EltBaseInfo, &EltTBAAInfo);
     auto *Idx = EmitIdxAfterBase(/*Promote*/true);
+    QualType ptrType = E->getBase()->getType();
     Addr = emitArraySubscriptGEP(*this, Addr, Idx, E->getType(),
                                  !getLangOpts().isSignedOverflowDefined(),
-                                 SignedIndices, E->getExprLoc());
+                                 SignedIndices, E->getExprLoc(), &ptrType);
   }
 
   LValue LV = MakeAddrLValue(Addr, E->getType(), EltBaseInfo, EltTBAAInfo);

diff --git a/test/CodeGen/builtin-preserve-access-index-array.c b/test/CodeGen/builtin-preserve-access-index-array.c
new file mode 100644 (file)
index 0000000..a449b28
--- /dev/null
+++ b/test/CodeGen/builtin-preserve-access-index-array.c
@@ -0,0 +1,18 @@
+// RUN: %clang -target x86_64 -emit-llvm -S -g %s -o - | FileCheck %s
+
+#define _(x) (__builtin_preserve_access_index(x))
+
+struct s1 {
+  char a;
+  int b[4];
+};
+
+const void *unit1(struct s1 *arg) {
+  return _(&arg->b[2]);
+}
+// CHECK: define dso_local i8* @unit1
+// CHECK: call [4 x i32]* @llvm.preserve.struct.access.index.p0a4i32.p0s_struct.s1s(%struct.s1* %{{[0-9a-z]+}}, i32 1, i32 1), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[STRUCT_S1:[0-9]+]]
+// CHECK: call i32* @llvm.preserve.array.access.index.p0i32.p0a4i32([4 x i32]* %{{[0-9a-z]+}}, i32 1, i32 2), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[ARRAY:[0-9]+]]
+//
+// CHECK: ![[ARRAY]] = !DICompositeType(tag: DW_TAG_array_type
+// CHECK: ![[STRUCT_S1]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s1"

diff --git a/test/CodeGen/builtin-preserve-access-index.c b/test/CodeGen/builtin-preserve-access-index.c
index 954a3b827d25a3284a6d22fee93f9eee528d52cb..10844166a6f0ac8aa79da91f914f676ced23fc37 100644 (file)
--- a/test/CodeGen/builtin-preserve-access-index.c
+++ b/test/CodeGen/builtin-preserve-access-index.c
@@ -31,16 +31,16 @@ const void *unit4(const int *arg) {
 }
 // CHECK: define dso_local i8* @unit4
 // CHECK-NOT: getelementptr
-// CHECK: call i32* @llvm.preserve.array.access.index.p0i32.p0i32(i32* %{{[0-9a-z]+}}, i32 0, i32 1)
+// CHECK: call i32* @llvm.preserve.array.access.index.p0i32.p0i32(i32* %{{[0-9a-z]+}}, i32 0, i32 1), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[POINTER:[0-9]+]]
 
 const void *unit5(const int *arg[5]) {
   return _(&arg[1][2]);
 }
 // CHECK: define dso_local i8* @unit5
 // CHECK-NOT: getelementptr
-// CHECK: call i32** @llvm.preserve.array.access.index.p0p0i32.p0p0i32(i32** %{{[0-9a-z]+}}, i32 0, i32 1)
+// CHECK: call i32** @llvm.preserve.array.access.index.p0p0i32.p0p0i32(i32** %{{[0-9a-z]+}}, i32 0, i32 1), !dbg !{{[0-9]+}}, !llvm.preserve.access.index !{{[0-9]+}}
 // CHECK-NOT: getelementptr
-// CHECK: call i32* @llvm.preserve.array.access.index.p0i32.p0i32(i32* %{{[0-9a-z]+}}, i32 0, i32 2)
+// CHECK: call i32* @llvm.preserve.array.access.index.p0i32.p0i32(i32* %{{[0-9a-z]+}}, i32 0, i32 2), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[POINTER:[0-9]+]]
 
 struct s1 {
   char a;
@@ -141,7 +141,7 @@ const void *unit13(struct s4 *arg) {
 // CHECK: define dso_local i8* @unit13
 // CHECK: call %union.u* @llvm.preserve.struct.access.index.p0s_union.us.p0s_struct.s4s(%struct.s4* %{{[0-9a-z]+}}, i32 1, i32 1), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[STRUCT_S4:[0-9]+]]
 // CHECK: call %union.u* @llvm.preserve.union.access.index.p0s_union.us.p0s_union.us(%union.u* %{{[0-9a-z]+}}, i32 0), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[UNION_I_U:[0-9]+]]
-// CHECK: call i32* @llvm.preserve.array.access.index.p0i32.p0a4i32([4 x i32]* %{{[0-9a-z]+}}, i32 1, i32 2)
+// CHECK: call i32* @llvm.preserve.array.access.index.p0i32.p0a4i32([4 x i32]* %{{[0-9a-z]+}}, i32 1, i32 2), !dbg !{{[0-9]+}}, !llvm.preserve.access.index !{{[0-9]+}}
 
 const void *unit14(union u3 *arg) {
   return _(&arg->c.b[2]);
@@ -149,13 +149,13 @@ const void *unit14(union u3 *arg) {
 // CHECK: define dso_local i8* @unit14
 // CHECK: call %union.u3* @llvm.preserve.union.access.index.p0s_union.u3s.p0s_union.u3s(%union.u3* %{{[0-9a-z]+}}, i32 0), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[UNION_U3:[0-9]+]]
 // CHECK: call [4 x i32]* @llvm.preserve.struct.access.index.p0a4i32.p0s_struct.ss(%struct.s* %{{[0-9a-z]+}}, i32 0, i32 0), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[STRUCT_I_S:[0-9]+]]
-// CHECK: call i32* @llvm.preserve.array.access.index.p0i32.p0a4i32([4 x i32]* %{{[0-9a-z]+}}, i32 1, i32 2)
+// CHECK: call i32* @llvm.preserve.array.access.index.p0i32.p0a4i32([4 x i32]* %{{[0-9a-z]+}}, i32 1, i32 2), !dbg !{{[0-9]+}}, !llvm.preserve.access.index !{{[0-9]+}}
 
 const void *unit15(struct s4 *arg) {
   return _(&arg[2].c.a);
 }
 // CHECK: define dso_local i8* @unit15
-// CHECK: call %struct.s4* @llvm.preserve.array.access.index.p0s_struct.s4s.p0s_struct.s4s(%struct.s4* %{{[0-9a-z]+}}, i32 0, i32 2)
+// CHECK: call %struct.s4* @llvm.preserve.array.access.index.p0s_struct.s4s.p0s_struct.s4s(%struct.s4* %{{[0-9a-z]+}}, i32 0, i32 2), !dbg !{{[0-9]+}}, !llvm.preserve.access.index !{{[0-9]+}}
 // CHECK: call %union.u* @llvm.preserve.struct.access.index.p0s_union.us.p0s_struct.s4s(%struct.s4* %{{[0-9a-z]+}}, i32 1, i32 1), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[STRUCT_S4]]
 // CHECK: call %union.u* @llvm.preserve.union.access.index.p0s_union.us.p0s_union.us(%union.u* %{{[0-9a-z]+}}, i32 1), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[UNION_I_U]]
 
@@ -163,15 +163,16 @@ const void *unit16(union u3 *arg) {
   return _(&arg[2].a);
 }
 // CHECK: define dso_local i8* @unit16
-// CHECK: call %union.u3* @llvm.preserve.array.access.index.p0s_union.u3s.p0s_union.u3s(%union.u3* %{{[0-9a-z]+}}, i32 0, i32 2)
+// CHECK: call %union.u3* @llvm.preserve.array.access.index.p0s_union.u3s.p0s_union.u3s(%union.u3* %{{[0-9a-z]+}}, i32 0, i32 2), !dbg !{{[0-9]+}}, !llvm.preserve.access.index !{{[0-9]+}}
 // CHECK: call %union.u3* @llvm.preserve.union.access.index.p0s_union.u3s.p0s_union.u3s(%union.u3* %{{[0-9a-z]+}}, i32 1), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[UNION_U3]]
 
+// CHECK: ![[POINTER]] = !DIDerivedType(tag: DW_TAG_pointer_type
+// CHECK: ![[STRUCT_S4]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s4"
+// CHECK: ![[UNION_I_U]] = distinct !DICompositeType(tag: DW_TAG_union_type, name: "u"
+// CHECK: ![[UNION_U3]] = distinct !DICompositeType(tag: DW_TAG_union_type, name: "u3"
+// CHECK: ![[STRUCT_I_S]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s"
 // CHECK: ![[STRUCT_S1]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s1"
 // CHECK: ![[STRUCT_S2]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s2"
 // CHECK: ![[STRUCT_S3]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s3"
 // CHECK: ![[UNION_U1]] = distinct !DICompositeType(tag: DW_TAG_union_type, name: "u1"
 // CHECK: ![[UNION_U2]] = distinct !DICompositeType(tag: DW_TAG_union_type, name: "u2"
-// CHECK: ![[STRUCT_S4]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s4"
-// CHECK: ![[UNION_I_U]] = distinct !DICompositeType(tag: DW_TAG_union_type, name: "u"
-// CHECK: ![[UNION_U3]] = distinct !DICompositeType(tag: DW_TAG_union_type, name: "u3"
-// CHECK: ![[STRUCT_I_S]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s"