diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst index 822e761444db7..ef3464e657031 100644 --- a/llvm/docs/LangRef.rst +++ b/llvm/docs/LangRef.rst @@ -650,48 +650,136 @@ literal types are uniqued in recent versions of LLVM. .. _nointptrtype: -Non-Integral Pointer Type -------------------------- +Non-Integral and Unstable Pointer Types +--------------------------------------- -Note: non-integral pointer types are a work in progress, and they should be -considered experimental at this time. +Note: non-integral/unstable pointer types are a work in progress, and they +should be considered experimental at this time. LLVM IR optionally allows the frontend to denote pointers in certain address -spaces as "non-integral" via the :ref:`datalayout string`. -Non-integral pointer types represent pointers that have an *unspecified* bitwise -representation; that is, the integral representation may be target dependent or -unstable (not backed by a fixed integer). +spaces as "unstable", "non-integral", or "non-integral with external state" +(or combinations of these) via the :ref:`datalayout string`. + +The exact implications of these properties are target-specific, but the +following IR semantics and restrictions to optimization passes apply: + +Unstable pointer representation +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Pointers in this address space have an *unspecified* bitwise representation +(i.e. not backed by a fixed integer). The bitwise pattern of such pointers is +allowed to change in a target-specific way. For example, this could be a pointer +type used with copying garbage collection where the garbage collector could +update the pointer at any time in the collection sweep. ``inttoptr`` and ``ptrtoint`` instructions have the same semantics as for integral (i.e. normal) pointers in that they convert integers to and from -corresponding pointer types, but there are additional implications to be -aware of. Because the bit-representation of a non-integral pointer may -not be stable, two identical casts of the same operand may or may not +corresponding pointer types, but there are additional implications to be aware +of. + +For "unstable" pointer representations, the bit-representation of the pointer +may not be stable, so two identical casts of the same operand may or may not return the same value. Said differently, the conversion to or from the -non-integral type depends on environmental state in an implementation +"unstable" pointer type depends on environmental state in an implementation defined manner. - If the frontend wishes to observe a *particular* value following a cast, the generated IR must fence with the underlying environment in an implementation defined manner. (In practice, this tends to require ``noinline`` routines for such operations.) From the perspective of the optimizer, ``inttoptr`` and ``ptrtoint`` for -non-integral types are analogous to ones on integral types with one +"unstable" pointer types are analogous to ones on integral types with one key exception: the optimizer may not, in general, insert new dynamic occurrences of such casts. If a new cast is inserted, the optimizer would need to either ensure that a) all possible values are valid, or b) appropriate fencing is inserted. Since the appropriate fencing is implementation defined, the optimizer can't do the latter. The former is challenging as many commonly expected properties, such as -``ptrtoint(v)-ptrtoint(v) == 0``, don't hold for non-integral types. +``ptrtoint(v)-ptrtoint(v) == 0``, don't hold for "unstable" pointer types. Similar restrictions apply to intrinsics that might examine the pointer bits, such as :ref:`llvm.ptrmask`. -The alignment information provided by the frontend for a non-integral pointer +The alignment information provided by the frontend for an "unstable" pointer (typically using attributes or metadata) must be valid for every possible representation of the pointer. +Non-integral pointer representation +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Pointers are not represented as just an address, but may instead include +additional metadata such as bounds information or a temporal identifier. +Examples include AMDGPU buffer descriptors with a 128-bit fat pointer and a +32-bit offset, or CHERI capabilities that contain bounds, permissions and a +type field (as well as an out-of-band validity bit, see next section). + +In most cases pointers with a non-integral representation behave exactly the +same as an integral pointer, the only difference is that it is not possible to +create a pointer just from an address unless all the metadata bits were +also recreated correctly. + +"Non-integral" pointers also impose restrictions on transformation passes, but +in general these are less restrictive than for "unstable" pointers. The main +difference compared to integral pointers is that the address width of a +non-integral pointer is not equal to the bitwise representation, so extracting +the address needs to truncate to the index width of the pointer. + +Note: Currently all supported targets require that truncating the ``ptrtoint`` +result to address width yields the memory address of the pointer but this may +not hold for all future targets so optimizations should not rely on this. + +Unlike "unstable" pointers, the bit-wise representation is stable and +``ptrtoint(x)`` always yields a deterministic value. +This means transformation passes are still permitted to insert new ``ptrtoint`` +instructions. + +Non-integral pointers with external state +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +A special case of non-integral pointers is ones that include external state +(such as implicit bounds information or a type tag) with a target-defined size. +An example of such a type is a CHERI capability, where there is an additional +validity bit that is part of all pointer-typed registers, but is located in +memory at an implementation-defined address separate from the pointer itself. +Another example would be a fat-pointer scheme where pointers remain plain +integers, but the associated bounds are stored in an out-of-band table. + +The following restrictions apply to IR level optimization passes: + +The ``inttoptr`` instruction does not recreate the external state and therefore +it is target dependent whether it can be used to create a dereferenceable +pointer. In general passes should assume that the result of such an inttoptr +is not dereferenceable. For example, on CHERI targets an ``inttoptr`` will +yield a capability with the external state (the validity tag bit) set to zero, +which will cause any dereference to trap. +The ``ptrtoint`` instruction also only returns the "in-band" state and omits +all external state. +These two properties mean that ``inttoptr(ptrtoint(x))`` cannot be folded to +``x`` since the ``ptrtoint`` operation does not include the external state +needed to reconstruct the original pointer and ``inttoptr`` cannot set it. + +When a ``store ptr addrspace(N) %p, ptr @dst`` of such a non-integral pointer +is performed, the external metadata is also stored to an implementation-defined +location. Similarly, a ``%val = load ptr addrspace(N), ptr @dst`` will fetch the +external metadata and make it available for all uses of ``%val``. +Similarly, the ``llvm.memcpy`` and ``llvm.memmove`` intrinsics also transfer the +external state. This is essential to allow frontends to efficiently emit copies +of structures containing such pointers, since expanding all these copies as +individual loads and stores would affect compilation speed and inhibit +optimizations. + +Notionally, these external bits are part of the pointer, but since +``inttoptr`` / ``ptrtoint``` only operate on the "in-band" bits of the pointer +and the external bits are not explicitly exposed, they are not included in the +size specified in the :ref:`datalayout string`. + +When a pointer type has external state, all roundtrips via memory must +be performed as loads and stores of the correct type since stores of other +types may not propagate the external data. +Therefore it is not legal to convert an existing load/store (or a ``llvm.memcpy`` / +``llvm.memmove`` intrinsic) of pointer types with external state to a load/store +of an integer type with same bitwidth, as that may drop the external state. + + .. _globalvars: Global Variables @@ -3167,8 +3255,8 @@ as follows: ``A
`` Specifies the address space of objects created by '``alloca``'. Defaults to the default address space of 0. -``p[n]::[:[:]]`` - This specifies the properties of a pointer in address space ``n``. +``p[][]::[:[:]]`` + This specifies the properties of a pointer in address space ``as``. The ```` parameter specifies the size of the bitwise representation. For :ref:`non-integral pointers ` the representation size may be larger than the address width of the underlying address space (e.g. to @@ -3181,9 +3269,14 @@ as follows: default index size is equal to the pointer size. The index size also specifies the width of addresses in this address space. All sizes are in bits. - The address space, ``n``, is optional, and if not specified, - denotes the default address space 0. The value of ``n`` must be - in the range [1,2^24). + The address space, ````, is optional, and if not specified, denotes the + default address space 0. The value of ```` must be in the range [1,2^24). + The optional ```` are used to specify properties of pointers in this + address space: the character ``u`` marks pointers as having an unstable + representation, ``n`` marks pointers as non-integral (i.e. having + additional metadata), ``e`` marks pointers having external state + (``n`` must also be set). See :ref:`Non-Integral Pointer Types `. + ``i:[:]`` This specifies the alignment for an integer type of a given bit ````. The value of ```` must be in the range [1,2^24). @@ -3236,9 +3329,11 @@ as follows: this set are considered to support most general arithmetic operations efficiently. ``ni:
:
:
...`` - This specifies pointer types with the specified address spaces - as :ref:`Non-Integral Pointer Type ` s. The ``0`` - address space cannot be specified as non-integral. + This marks pointer types with the specified address spaces + as :ref:`non-integral and unstable `. + The ``0`` address space cannot be specified as non-integral. + It is only supported for backwards compatibility, the flags of the ``p`` + specifier should be used instead for new code. ```` is a lower bound on what is required for a type to be considered aligned. This is used in various places, such as: diff --git a/llvm/include/llvm/IR/DataLayout.h b/llvm/include/llvm/IR/DataLayout.h index 2992484c47d06..6f4981e2b65b6 100644 --- a/llvm/include/llvm/IR/DataLayout.h +++ b/llvm/include/llvm/IR/DataLayout.h @@ -79,10 +79,19 @@ class DataLayout { Align PrefAlign; uint32_t IndexBitWidth; /// Pointers in this address space don't have a well-defined bitwise - /// representation (e.g. may be relocated by a copying garbage collector). - /// Additionally, they may also be non-integral (i.e. containing additional - /// metadata such as bounds information/permissions). - bool IsNonIntegral; + /// representation (e.g. they may be relocated by a copying garbage + /// collector and thus have different addresses at different times). + bool HasUnstableRepresentation; + /// Pointers in this address space are non-integral, i.e. don't have a + /// integer representation that simply maps to the address. An example of + /// this would be e.g. AMDGPU buffer fat pointers with bounds information + /// and various flags or CHERI capabilities that contain bounds+permissions. + bool HasNonIntegralRepresentation; + /// Pointers in this address space have additional state bits that are + /// located at a target-defined location when stored in memory. An example + /// of this would be CHERI capabilities where the validity bit is stored + /// separately from the pointer address+bounds information. + bool HasExternalState; LLVM_ABI bool operator==(const PointerSpec &Other) const; }; @@ -149,7 +158,8 @@ class DataLayout { /// Sets or updates the specification for pointer in the given address space. void setPointerSpec(uint32_t AddrSpace, uint32_t BitWidth, Align ABIAlign, Align PrefAlign, uint32_t IndexBitWidth, - bool IsNonIntegral); + bool HasUnstableRepr, bool HasNonIntegralRepr, + bool HasExternalState); /// Internal helper to get alignment for integer of given bitwidth. LLVM_ABI Align getIntegerAlignment(uint32_t BitWidth, bool abi_or_pref) const; @@ -357,19 +367,80 @@ class DataLayout { /// \sa DataLayout::getAddressSizeInBits unsigned getAddressSize(unsigned AS) const { return getIndexSize(AS); } - /// Return the address spaces containing non-integral pointers. Pointers in - /// this address space don't have a well-defined bitwise representation. - SmallVector getNonIntegralAddressSpaces() const { + /// Return the address spaces with special pointer semantics (such as being + /// unstable or non-integral). + SmallVector getNonStandardAddressSpaces() const { SmallVector AddrSpaces; for (const PointerSpec &PS : PointerSpecs) { - if (PS.IsNonIntegral) + if (PS.HasNonIntegralRepresentation || PS.HasUnstableRepresentation || + PS.HasExternalState) AddrSpaces.push_back(PS.AddrSpace); } return AddrSpaces; } + /// Returns whether this address space is "non-integral" and "unstable". + /// This means that passes should not introduce inttoptr or ptrtoint + /// instructions operating on pointers of this address space. + /// TODO: remove this function after migrating to finer-grained properties. bool isNonIntegralAddressSpace(unsigned AddrSpace) const { - return getPointerSpec(AddrSpace).IsNonIntegral; + return hasUnstableRepresentation(AddrSpace) || + hasNonIntegralRepresentation(AddrSpace); + } + + /// Returns whether this address space has an "unstable" pointer + /// representation. The bitwise pattern of such pointers is allowed to change + /// in a target-specific way. For example, this could be used for copying + /// garbage collection where the garbage collector could update the pointer + /// value as part of the collection sweep. + bool hasUnstableRepresentation(unsigned AddrSpace) const { + return getPointerSpec(AddrSpace).HasUnstableRepresentation; + } + + /// Returns whether this address space has a non-integral pointer + /// representation, i.e. the pointer is not just an integer address but some + /// other bitwise representation. Examples include AMDGPU buffer descriptors + /// with a 128-bit fat pointer and a 32-bit offset or CHERI capabilities that + /// contain bounds, permissions and an out-of-band validity bit. In general, + /// these pointers cannot be re-created from just an integer value. + bool hasNonIntegralRepresentation(unsigned AddrSpace) const { + return getPointerSpec(AddrSpace).HasNonIntegralRepresentation; + } + + /// Returns whether this address space has external state (implies being + /// a non-integral pointer representation). + /// These pointer types must be loaded and stored using appropriate + /// instructions and cannot use integer loads/stores as this would not + /// propagate the out-of-band state. An example of such a pointer type is a + /// CHERI capability that contain bounds, permissions and an out-of-band + /// validity bit that is invalidated whenever an integer/FP store is performed + /// to the associated memory location. + bool hasExternalState(unsigned AddrSpace) const { + return getPointerSpec(AddrSpace).HasExternalState; + } + + /// Returns whether passes should avoid introducing `inttoptr` instructions + /// for this address space. + /// + /// This is currently the case for non-integral pointer representations with + /// external state (hasExternalState()) since `inttoptr` cannot recreate the + /// external state bits. + /// New `inttoptr` instructions should also be avoided for "unstable" bitwise + /// representations (hasUnstableRepresentation()) unless the pass knows it is + /// within a critical section that retains the current representation. + bool shouldAvoidIntToPtr(unsigned AddrSpace) const { + return hasUnstableRepresentation(AddrSpace) || hasExternalState(AddrSpace); + } + + /// Returns whether passes should avoid introducing `ptrtoint` instructions + /// for this address space. + /// + /// This is currently the case for pointer address spaces that have an + /// "unstable" representation (hasUnstableRepresentation()) since the + /// bitwise pattern of such pointers could change unless the pass knows it is + /// within a critical section that retains the current representation. + bool shouldAvoidPtrToInt(unsigned AddrSpace) const { + return hasUnstableRepresentation(AddrSpace); } bool isNonIntegralPointerType(PointerType *PT) const { @@ -377,10 +448,20 @@ class DataLayout { } bool isNonIntegralPointerType(Type *Ty) const { - auto *PTy = dyn_cast(Ty); + auto *PTy = dyn_cast(Ty->getScalarType()); return PTy && isNonIntegralPointerType(PTy); } + bool shouldAvoidPtrToInt(Type *Ty) const { + auto *PTy = dyn_cast(Ty->getScalarType()); + return PTy && shouldAvoidPtrToInt(PTy->getPointerAddressSpace()); + } + + bool shouldAvoidIntToPtr(Type *Ty) const { + auto *PTy = dyn_cast(Ty->getScalarType()); + return PTy && shouldAvoidIntToPtr(PTy->getPointerAddressSpace()); + } + /// The size in bits of the pointer representation in a given address space. /// This is not necessarily the same as the integer address of a pointer (e.g. /// for fat pointers). diff --git a/llvm/lib/IR/DataLayout.cpp b/llvm/lib/IR/DataLayout.cpp index dbd6d81ad2e24..c6a3425e6fa1f 100644 --- a/llvm/lib/IR/DataLayout.cpp +++ b/llvm/lib/IR/DataLayout.cpp @@ -151,7 +151,9 @@ bool DataLayout::PointerSpec::operator==(const PointerSpec &Other) const { return AddrSpace == Other.AddrSpace && BitWidth == Other.BitWidth && ABIAlign == Other.ABIAlign && PrefAlign == Other.PrefAlign && IndexBitWidth == Other.IndexBitWidth && - IsNonIntegral == Other.IsNonIntegral; + HasUnstableRepresentation == Other.HasUnstableRepresentation && + HasNonIntegralRepresentation == Other.HasNonIntegralRepresentation && + HasExternalState == Other.HasExternalState; } namespace { @@ -207,7 +209,8 @@ constexpr DataLayout::PrimitiveSpec DefaultVectorSpecs[] = { // Default pointer type specifications. constexpr DataLayout::PointerSpec DefaultPointerSpecs[] = { // p0:64:64:64:64 - {0, 64, Align::Constant<8>(), Align::Constant<8>(), 64, false}, + {0, 64, Align::Constant<8>(), Align::Constant<8>(), 64, false, false, + false}, }; DataLayout::DataLayout() @@ -418,9 +421,35 @@ Error DataLayout::parsePointerSpec(StringRef Spec) { // Address space. Optional, defaults to 0. unsigned AddrSpace = 0; - if (!Components[0].empty()) - if (Error Err = parseAddrSpace(Components[0], AddrSpace)) - return Err; + bool ExternalState = false; + bool UnstableRepr = false; + bool NonIntegralRepr = false; + StringRef AddrSpaceStr = Components[0]; + while (!AddrSpaceStr.empty()) { + char C = AddrSpaceStr.front(); + if (C == 'e') { + ExternalState = true; + } else if (C == 'n') { + NonIntegralRepr = true; + } else if (C == 'u') { + UnstableRepr = true; + } else if (isAlpha(C)) { + return createStringError("'%c' is not a valid pointer specification flag", + C); + } else { + break; // not a valid flag, remaining must be the address space number. + } + AddrSpaceStr = AddrSpaceStr.drop_front(1); + } + if (!AddrSpaceStr.empty()) + if (Error Err = parseAddrSpace(AddrSpaceStr, AddrSpace)) + return Err; // Failed to parse the remaining characters as a number + if (AddrSpace == 0 && (NonIntegralRepr || UnstableRepr)) + return createStringError( + "address space 0 cannot be non-integral or unstable"); + if (ExternalState && !NonIntegralRepr) + return createStringError( + "pointers with external state must be non-integral"); // Size. Required, cannot be zero. unsigned BitWidth; @@ -454,7 +483,7 @@ Error DataLayout::parsePointerSpec(StringRef Spec) { "index size cannot be larger than the pointer size"); setPointerSpec(AddrSpace, BitWidth, ABIAlign, PrefAlign, IndexBitWidth, - false); + UnstableRepr, NonIntegralRepr, ExternalState); return Error::success(); } @@ -630,7 +659,7 @@ Error DataLayout::parseLayoutString(StringRef LayoutString) { // the spec for AS0, and we then update that to mark it non-integral. const PointerSpec &PS = getPointerSpec(AS); setPointerSpec(AS, PS.BitWidth, PS.ABIAlign, PS.PrefAlign, PS.IndexBitWidth, - true); + true, true, false); } return Error::success(); @@ -678,17 +707,22 @@ DataLayout::getPointerSpec(uint32_t AddrSpace) const { void DataLayout::setPointerSpec(uint32_t AddrSpace, uint32_t BitWidth, Align ABIAlign, Align PrefAlign, - uint32_t IndexBitWidth, bool IsNonIntegral) { + uint32_t IndexBitWidth, bool HasUnstableRepr, + bool HasNonIntegralRepr, + bool HasExternalState) { auto I = lower_bound(PointerSpecs, AddrSpace, LessPointerAddrSpace()); if (I == PointerSpecs.end() || I->AddrSpace != AddrSpace) { PointerSpecs.insert(I, PointerSpec{AddrSpace, BitWidth, ABIAlign, PrefAlign, - IndexBitWidth, IsNonIntegral}); + IndexBitWidth, HasUnstableRepr, + HasNonIntegralRepr, HasExternalState}); } else { I->BitWidth = BitWidth; I->ABIAlign = ABIAlign; I->PrefAlign = PrefAlign; I->IndexBitWidth = IndexBitWidth; - I->IsNonIntegral = IsNonIntegral; + I->HasUnstableRepresentation = HasUnstableRepr; + I->HasExternalState = HasExternalState; + I->HasNonIntegralRepresentation = HasNonIntegralRepr; } } diff --git a/llvm/unittests/IR/DataLayoutTest.cpp b/llvm/unittests/IR/DataLayoutTest.cpp index afa72a53ab2c0..5355e5b32b56f 100644 --- a/llvm/unittests/IR/DataLayoutTest.cpp +++ b/llvm/unittests/IR/DataLayoutTest.cpp @@ -320,7 +320,8 @@ TEST(DataLayout, ParsePointerSpec) { "\"p[]::[:[:]]\"")); // address space - for (StringRef Str : {"p0x0:32:32", "px:32:32:32", "p16777216:32:32:32:32"}) + for (StringRef Str : + {"p0x0:32:32", "p10_000:32:32:32", "p16777216:32:32:32:32"}) EXPECT_THAT_EXPECTED( DataLayout::parse(Str), FailedWithMessage("address space must be a 24-bit integer")); @@ -401,6 +402,30 @@ TEST(DataLayout, ParsePointerSpec) { EXPECT_THAT_EXPECTED( DataLayout::parse(Str), FailedWithMessage("index size cannot be larger than the pointer size")); + + // Only 'e', 'u', and 'n' flags are valid. + EXPECT_THAT_EXPECTED( + DataLayout::parse("pa:32:32"), + FailedWithMessage("'a' is not a valid pointer specification flag")); + EXPECT_THAT_EXPECTED( + DataLayout::parse("pnX:32:32"), + FailedWithMessage("'X' is not a valid pointer specification flag")); + // Flags must be before the address space number. + EXPECT_THAT_EXPECTED( + DataLayout::parse("p2n:32:32"), + FailedWithMessage("address space must be a 24-bit integer")); + + EXPECT_THAT_EXPECTED( + DataLayout::parse("pe2:64:64"), + FailedWithMessage("pointers with external state must be non-integral")); + + // AS0 cannot be non-integral. + for (StringRef Str : {"pn:64:64", "pu:64:64", "puen:64:64", "pnu:64:64", + "pen0:64:64", "pu0:64:64", "pun0:64:64", "penu0:64:64"}) + EXPECT_THAT_EXPECTED( + DataLayout::parse(Str), + FailedWithMessage( + "address space 0 cannot be non-integral or unstable")); } TEST(DataLayoutTest, ParseNativeIntegersSpec) { @@ -557,17 +582,123 @@ TEST(DataLayout, GetPointerPrefAlignment) { TEST(DataLayout, IsNonIntegralAddressSpace) { DataLayout Default; - EXPECT_THAT(Default.getNonIntegralAddressSpaces(), ::testing::SizeIs(0)); + EXPECT_THAT(Default.getNonStandardAddressSpaces(), ::testing::SizeIs(0)); EXPECT_FALSE(Default.isNonIntegralAddressSpace(0)); EXPECT_FALSE(Default.isNonIntegralAddressSpace(1)); DataLayout Custom = cantFail(DataLayout::parse("ni:2:16777215")); - EXPECT_THAT(Custom.getNonIntegralAddressSpaces(), + EXPECT_THAT(Custom.getNonStandardAddressSpaces(), ::testing::ElementsAreArray({2U, 16777215U})); EXPECT_FALSE(Custom.isNonIntegralAddressSpace(0)); EXPECT_FALSE(Custom.isNonIntegralAddressSpace(1)); EXPECT_TRUE(Custom.isNonIntegralAddressSpace(2)); EXPECT_TRUE(Custom.isNonIntegralAddressSpace(16777215)); + + // Pointers can be marked as non-integral using 'pn' + Custom = cantFail(DataLayout::parse("pn2:64:64:64:32")); + EXPECT_TRUE(Custom.isNonIntegralAddressSpace(2)); + EXPECT_TRUE(Custom.hasNonIntegralRepresentation(2)); + EXPECT_FALSE(Custom.hasUnstableRepresentation(2)); + EXPECT_FALSE(Custom.hasExternalState(2)); + EXPECT_FALSE(Custom.shouldAvoidIntToPtr(2)); + EXPECT_FALSE(Custom.shouldAvoidPtrToInt(2)); + EXPECT_THAT(Custom.getNonStandardAddressSpaces(), + ::testing::ElementsAreArray({2U})); + + // Pointers can be marked as unstable using 'pu' + Custom = cantFail(DataLayout::parse("pu2:64:64:64:32")); + EXPECT_TRUE(Custom.isNonIntegralAddressSpace(2)); + EXPECT_TRUE(Custom.hasUnstableRepresentation(2)); + EXPECT_FALSE(Custom.hasNonIntegralRepresentation(2)); + EXPECT_FALSE(Custom.hasExternalState(2)); + EXPECT_TRUE(Custom.shouldAvoidPtrToInt(2)); + EXPECT_TRUE(Custom.shouldAvoidIntToPtr(2)); + EXPECT_THAT(Custom.getNonStandardAddressSpaces(), + ::testing::ElementsAreArray({2U})); + + // Both properties can also be set using 'pnu'/'pun' + for (const auto *Layout : {"pnu2:64:64:64:32", "pun2:64:64:64:32"}) { + DataLayout DL = cantFail(DataLayout::parse(Layout)); + EXPECT_TRUE(DL.isNonIntegralAddressSpace(2)); + EXPECT_TRUE(DL.hasNonIntegralRepresentation(2)); + EXPECT_TRUE(DL.hasUnstableRepresentation(2)); + EXPECT_FALSE(DL.hasExternalState(2)); + EXPECT_THAT(DL.getNonStandardAddressSpaces(), + ::testing::ElementsAreArray({2U})); + } + + // Non-integral pointers with have external state ('e' flag, requires 'n'). + for (const auto *Layout : {"pen2:64:64:64:32", "pne2:64:64:64:32"}) { + DataLayout DL = cantFail(DataLayout::parse(Layout)); + EXPECT_TRUE(DL.isNonIntegralAddressSpace(2)); + EXPECT_TRUE(DL.hasExternalState(2)); + EXPECT_TRUE(DL.hasNonIntegralRepresentation(2)); + EXPECT_FALSE(DL.hasUnstableRepresentation(2)); + EXPECT_THAT(DL.getNonStandardAddressSpaces(), + ::testing::ElementsAreArray({2U})); + } + EXPECT_THAT_EXPECTED( + DataLayout::parse("pe:64:64:64:32"), + FailedWithMessage("pointers with external state must be non-integral")); + + // For backwards compatibility, the ni DataLayout part overrides any + // p[e][n][u]. + for (const auto *Layout : + {"ni:2-pn2:64:64:64:32", "ni:2-pnu2:64:64:64:32", "ni:2-pu2:64:64:64:32", + "pn2:64:64:64:32-ni:2", "pnu2:64:64:64:32-ni:2", "pu2:64:64:64:32-ni:2", + "pen2:64:64:64:32-ni:2", "pne2:64:64:64:32-ni:2", + "pene2:64:64:64:32-pu2:64:64:64:32-ni:2"}) { + DataLayout DL = cantFail(DataLayout::parse(Layout)); + EXPECT_TRUE(DL.isNonIntegralAddressSpace(2)); + EXPECT_TRUE(DL.hasNonIntegralRepresentation(2)); + EXPECT_TRUE(DL.hasUnstableRepresentation(2)); + // The external state property is new and not expected for existing uses of + // non-integral pointers, so existing :ni data layouts should not set it. + EXPECT_FALSE(DL.hasExternalState(2)); + EXPECT_THAT(DL.getNonStandardAddressSpaces(), + ::testing::ElementsAreArray({2U})); + } +} + +TEST(DataLayout, NonIntegralHelpers) { + DataLayout DL = cantFail(DataLayout::parse( + "pn1:128:128:128:64-pu2:32:32:32:32-pnu3:64:64:64:32-pen4:64:64:64:32")); + EXPECT_THAT(DL.getNonStandardAddressSpaces(), + ::testing::ElementsAreArray({1u, 2u, 3u, 4u})); + struct Result { + unsigned Addrspace; + bool NonIntegral; + bool Unstable; + bool ExternalState; + unsigned Size; + } ExpectedResults[] = { + {0, false, false, false, 64}, {1, true, false, false, 128}, + {2, false, true, false, 32}, {3, true, true, false, 64}, + {4, true, false, true, 64}, + }; + LLVMContext Ctx; + for (const auto &Exp : ExpectedResults) { + EXPECT_EQ(Exp.NonIntegral, DL.hasNonIntegralRepresentation(Exp.Addrspace)); + EXPECT_EQ(Exp.Unstable, DL.hasUnstableRepresentation(Exp.Addrspace)); + EXPECT_EQ(Exp.ExternalState, DL.hasExternalState(Exp.Addrspace)); + bool AvoidIntToPtr = Exp.Unstable || Exp.ExternalState; + EXPECT_EQ(AvoidIntToPtr, DL.shouldAvoidIntToPtr(Exp.Addrspace)); + bool AvoidPtrToInt = Exp.Unstable; + EXPECT_EQ(AvoidPtrToInt, DL.shouldAvoidPtrToInt(Exp.Addrspace)); + Type *PtrTy = PointerType::get(Ctx, Exp.Addrspace); + Type *PtrVecTy = VectorType::get(PtrTy, 2, /*Scalable=*/false); + Type *ScalablePtrVecTy = VectorType::get(PtrTy, 1, /*Scalable=*/true); + for (Type *Ty : {PtrTy, PtrVecTy, ScalablePtrVecTy}) { + EXPECT_EQ(AvoidPtrToInt, DL.shouldAvoidPtrToInt(Ty)); + EXPECT_EQ(AvoidIntToPtr, DL.shouldAvoidIntToPtr(Ty)); + // The old API should return true for both unstable and non-integral. + EXPECT_EQ(Exp.Unstable || Exp.NonIntegral, + DL.isNonIntegralPointerType(Ty)); + } + // Both helpers gracefully handle non-pointer, non-vector-of-pointers: + EXPECT_FALSE(DL.shouldAvoidPtrToInt(IntegerType::getInt1Ty(Ctx))); + EXPECT_FALSE(DL.shouldAvoidIntToPtr(IntegerType::getInt1Ty(Ctx))); + } } TEST(DataLayoutTest, CopyAssignmentInvalidatesStructLayout) {