================
@@ -42,6 +42,66 @@ using namespace CodeGen;
namespace {
class ConstExprEmitter;
+llvm::Constant *getPadding(const CodeGenModule &CGM, CharUnits PadSize) {
+ if (!CGM.getLangOpts().CPlusPlus) {
+ // In C23 (N3096) $6.7.10:
+ // """
+ // If any object is initialized with an empty iniitializer, then it is
+ // subject to default initialization:
+ // - if it is an aggregate, every member is initialized (recursively)
+ // according to these rules, and any padding is initialized to zero bits;
+ // - if it is a union, the first named member is initialized (recursively)
+ // according to these rules, and any padding is initialized to zero bits.
+ //
+ // If the aggregate or union contains elements or members that are
+ // aggregates or unions, these rules apply recursively to the subaggregates
+ // or contained unions.
+ //
+ // If there are fewer initializers in a brace-enclosed list than there are
+ // elements or members of an aggregate, or fewer characters in a string
+ // literal used to initialize an array of known size than there are
elements
+ // in the array, the remainder of the aggregate is subject to default
+ // initialization.
+ // """
+ //
+ // From my understanding, the standard is ambiguous in the following two
+ // areas:
+ // 1. For a union type with empty initializer, if the first named member is
+ // not the largest member, then the bytes comes after the first named
member
+ // but before padding are left unspecified. An example is:
+ // union U { int a; long long b;};
+ // union U u = {}; // The first 4 bytes are 0, but 4-8 bytes are left
+ // unspecified.
+ //
+ // 2. It only mentions padding for empty initializer, but doesn't mention
+ // padding for a non empty initialization list. And if the aggregation or
+ // union contains elements or members that are aggregates or unions, and
+ // some are non empty initializers, while others are empty initiailizers,
+ // the padding initialization is unclear. An example is:
+ // struct S1 { int a; long long b; };
+ // struct S2 { char c; struct S1 s1; };
+ // // The values for paddings between s2.c and s2.s1.a, between s2.s1.a
+ // and s2.s1.b are unclear.
+ // struct S2 s2 = { 'c' };
+ //
+ // Here we choose to zero initiailize left bytes of a union type. Because
+ // projects like the Linux kernel are relying on this behavior. If we don't
+ // explicitly zero initialize them, the undef values can be optimized to
+ // return gabage data. We also choose to zero initialize paddings for
+ // aggregates and unions, no matter they are initialized by empty
+ // initializers or non empty initializers. This can provide a consistent
+ // behavior. So projects like the Linux kernel can rely on it.
+ if (PadSize == CharUnits::One())
+ return llvm::ConstantInt::get(CGM.CharTy, 0);
+ llvm::Type *Ty = llvm::ArrayType::get(CGM.CharTy, PadSize.getQuantity());
+ return llvm::ConstantAggregateZero::get(Ty);
----------------
efriedma-quic wrote:
Constant::getNullValue() to unify the codepaths a bit.
https://github.com/llvm/llvm-project/pull/97121
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
