llvm-project/llvm/lib/AsmParser/LLToken.h

225 lines
5.5 KiB
C
Raw Normal View History

//===- LLToken.h - Token Codes for LLVM Assembly Files ----------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the enums for the .ll lexer.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_ASMPARSER_LLTOKEN_H
#define LLVM_LIB_ASMPARSER_LLTOKEN_H
namespace llvm {
namespace lltok {
enum Kind {
// Markers
Eof, Error,
// Tokens with no info.
dotdotdot, // ...
equal, comma, // = ,
star, // *
lsquare, rsquare, // [ ]
lbrace, rbrace, // { }
less, greater, // < >
lparen, rparen, // ( )
exclaim, // !
bar, // |
kw_x,
kw_true, kw_false,
kw_declare, kw_define,
kw_global, kw_constant,
Remove the linker_private and linker_private_weak linkages. These linkages were introduced some time ago, but it was never very clear what exactly their semantics were or what they should be used for. Some investigation found these uses: * utf-16 strings in clang. * non-unnamed_addr strings produced by the sanitizers. It turns out they were just working around a more fundamental problem. For some sections a MachO linker needs a symbol in order to split the section into atoms, and llvm had no idea that was the case. I fixed that in r201700 and it is now safe to use the private linkage. When the object ends up in a section that requires symbols, llvm will use a 'l' prefix instead of a 'L' prefix and things just work. With that, these linkages were already dead, but there was a potential future user in the objc metadata information. I am still looking at CGObjcMac.cpp, but at this point I am convinced that linker_private and linker_private_weak are not what they need. The objc uses are currently split in * Regular symbols (no '\01' prefix). LLVM already directly provides whatever semantics they need. * Uses of a private name (start with "\01L" or "\01l") and private linkage. We can drop the "\01L" and "\01l" prefixes as soon as llvm agrees with clang on L being ok or not for a given section. I have two patches in code review for this. * Uses of private name and weak linkage. The last case is the one that one could think would fit one of these linkages. That is not the case. The semantics are * the linker will merge these symbol by *name*. * the linker will hide them in the final DSO. Given that the merging is done by name, any of the private (or internal) linkages would be a bad match. They allow llvm to rename the symbols, and that is really not what we want. From the llvm point of view, these objects should really be (linkonce|weak)(_odr)?. For now, just keeping the "\01l" prefix is probably the best for these symbols. If we one day want to have a more direct support in llvm, IMHO what we should add is not a linkage, it is just a hidden_symbol attribute. It would be applicable to multiple linkages. For example, on weak it would produce the current behavior we have for objc metadata. On internal, it would be equivalent to private (and we should then remove private). llvm-svn: 203866
2014-03-14 07:18:37 +08:00
kw_private,
kw_internal,
kw_linkonce, kw_linkonce_odr,
kw_weak, // Used as a linkage, and a modifier for "cmpxchg".
kw_weak_odr, kw_appending,
kw_dllimport, kw_dllexport, kw_common, kw_available_externally,
kw_default, kw_hidden, kw_protected,
kw_unnamed_addr,
kw_externally_initialized,
kw_extern_weak,
kw_external, kw_thread_local,
kw_localdynamic, kw_initialexec, kw_localexec,
kw_zeroinitializer,
kw_undef, kw_null,
kw_to,
kw_caller,
kw_tail,
kw_musttail,
kw_target,
kw_triple,
kw_unwind,
kw_deplibs, // FIXME: Remove in 4.0
kw_datalayout,
kw_volatile,
kw_atomic,
kw_unordered, kw_monotonic, kw_acquire, kw_release, kw_acq_rel, kw_seq_cst,
kw_singlethread,
kw_nnan,
kw_ninf,
kw_nsz,
kw_arcp,
kw_fast,
kw_nuw,
kw_nsw,
kw_exact,
kw_inbounds,
kw_align,
kw_addrspace,
kw_section,
kw_alias,
kw_module,
kw_asm,
kw_sideeffect,
kw_alignstack,
kw_inteldialect,
kw_gc,
kw_prefix,
Prologue support Patch by Ben Gamari! This redefines the `prefix` attribute introduced previously and introduces a `prologue` attribute. There are a two primary usecases that these attributes aim to serve, 1. Function prologue sigils 2. Function hot-patching: Enable the user to insert `nop` operations at the beginning of the function which can later be safely replaced with a call to some instrumentation facility 3. Runtime metadata: Allow a compiler to insert data for use by the runtime during execution. GHC is one example of a compiler that needs this functionality for its tables-next-to-code functionality. Previously `prefix` served cases (1) and (2) quite well by allowing the user to introduce arbitrary data at the entrypoint but before the function body. Case (3), however, was poorly handled by this approach as it required that prefix data was valid executable code. Here we redefine the notion of prefix data to instead be data which occurs immediately before the function entrypoint (i.e. the symbol address). Since prefix data now occurs before the function entrypoint, there is no need for the data to be valid code. The previous notion of prefix data now goes under the name "prologue data" to emphasize its duality with the function epilogue. The intention here is to handle cases (1) and (2) with prologue data and case (3) with prefix data. References ---------- This idea arose out of discussions[1] with Reid Kleckner in response to a proposal to introduce the notion of symbol offsets to enable handling of case (3). [1] http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-May/073235.html Test Plan: testsuite Differential Revision: http://reviews.llvm.org/D6454 llvm-svn: 223189
2014-12-03 10:08:38 +08:00
kw_prologue,
kw_c,
kw_cc, kw_ccc, kw_fastcc, kw_coldcc,
kw_intel_ocl_bicc,
kw_x86_stdcallcc, kw_x86_fastcallcc, kw_x86_thiscallcc, kw_x86_vectorcallcc,
kw_arm_apcscc, kw_arm_aapcscc, kw_arm_aapcs_vfpcc,
kw_msp430_intrcc,
kw_ptx_kernel, kw_ptx_device,
kw_spir_kernel, kw_spir_func,
kw_x86_64_sysvcc, kw_x86_64_win64cc,
kw_webkit_jscc, kw_anyregcc,
kw_preserve_mostcc, kw_preserve_allcc,
kw_ghccc,
// Attributes:
kw_attributes,
kw_alwaysinline,
kw_argmemonly,
kw_sanitize_address,
kw_builtin,
kw_byval,
kw_inalloca,
kw_cold,
kw_convergent,
kw_dereferenceable,
kw_dereferenceable_or_null,
kw_inlinehint,
kw_inreg,
kw_jumptable,
kw_minsize,
kw_naked,
kw_nest,
kw_noalias,
kw_nobuiltin,
kw_nocapture,
kw_noduplicate,
kw_noimplicitfloat,
kw_noinline,
kw_nonlazybind,
kw_nonnull,
kw_noredzone,
kw_noreturn,
kw_nounwind,
kw_optnone,
kw_optsize,
kw_readnone,
kw_readonly,
kw_returned,
kw_returns_twice,
kw_signext,
kw_ssp,
kw_sspreq,
kw_sspstrong,
Protection against stack-based memory corruption errors using SafeStack This patch adds the safe stack instrumentation pass to LLVM, which separates the program stack into a safe stack, which stores return addresses, register spills, and local variables that are statically verified to be accessed in a safe way, and the unsafe stack, which stores everything else. Such separation makes it much harder for an attacker to corrupt objects on the safe stack, including function pointers stored in spilled registers and return addresses. You can find more information about the safe stack, as well as other parts of or control-flow hijack protection technique in our OSDI paper on code-pointer integrity (http://dslab.epfl.ch/pubs/cpi.pdf) and our project website (http://levee.epfl.ch). The overhead of our implementation of the safe stack is very close to zero (0.01% on the Phoronix benchmarks). This is lower than the overhead of stack cookies, which are supported by LLVM and are commonly used today, yet the security guarantees of the safe stack are strictly stronger than stack cookies. In some cases, the safe stack improves performance due to better cache locality. Our current implementation of the safe stack is stable and robust, we used it to recompile multiple projects on Linux including Chromium, and we also recompiled the entire FreeBSD user-space system and more than 100 packages. We ran unit tests on the FreeBSD system and many of the packages and observed no errors caused by the safe stack. The safe stack is also fully binary compatible with non-instrumented code and can be applied to parts of a program selectively. This patch is our implementation of the safe stack on top of LLVM. The patches make the following changes: - Add the safestack function attribute, similar to the ssp, sspstrong and sspreq attributes. - Add the SafeStack instrumentation pass that applies the safe stack to all functions that have the safestack attribute. This pass moves all unsafe local variables to the unsafe stack with a separate stack pointer, whereas all safe variables remain on the regular stack that is managed by LLVM as usual. - Invoke the pass as the last stage before code generation (at the same time the existing cookie-based stack protector pass is invoked). - Add unit tests for the safe stack. Original patch by Volodymyr Kuznetsov and others at the Dependable Systems Lab at EPFL; updates and upstreaming by myself. Differential Revision: http://reviews.llvm.org/D6094 llvm-svn: 239761
2015-06-16 05:07:11 +08:00
kw_safestack,
kw_sret,
kw_sanitize_thread,
kw_sanitize_memory,
kw_uwtable,
kw_zeroext,
kw_type,
kw_opaque,
kw_comdat,
// Comdat types
kw_any,
kw_exactmatch,
kw_largest,
kw_noduplicates,
kw_samesize,
kw_eq, kw_ne, kw_slt, kw_sgt, kw_sle, kw_sge, kw_ult, kw_ugt, kw_ule,
kw_uge, kw_oeq, kw_one, kw_olt, kw_ogt, kw_ole, kw_oge, kw_ord, kw_uno,
kw_ueq, kw_une,
// atomicrmw operations that aren't also instruction keywords.
kw_xchg, kw_nand, kw_max, kw_min, kw_umax, kw_umin,
// Instruction Opcodes (Opcode in UIntVal).
kw_add, kw_fadd, kw_sub, kw_fsub, kw_mul, kw_fmul,
kw_udiv, kw_sdiv, kw_fdiv,
kw_urem, kw_srem, kw_frem, kw_shl, kw_lshr, kw_ashr,
kw_and, kw_or, kw_xor, kw_icmp, kw_fcmp,
kw_phi, kw_call,
kw_trunc, kw_zext, kw_sext, kw_fptrunc, kw_fpext, kw_uitofp, kw_sitofp,
kw_fptoui, kw_fptosi, kw_inttoptr, kw_ptrtoint, kw_bitcast,
kw_addrspacecast,
kw_select, kw_va_arg,
kw_landingpad, kw_personality, kw_cleanup, kw_catch, kw_filter,
kw_ret, kw_br, kw_switch, kw_indirectbr, kw_invoke, kw_resume,
kw_unreachable, kw_cleanupret, kw_catchret, kw_catchpad,
kw_terminatepad, kw_cleanuppad, kw_catchendpad, kw_cleanupendpad,
kw_alloca, kw_load, kw_store, kw_fence, kw_cmpxchg, kw_atomicrmw,
kw_getelementptr,
kw_extractelement, kw_insertelement, kw_shufflevector,
kw_extractvalue, kw_insertvalue, kw_blockaddress,
// Metadata types.
kw_distinct,
// Use-list order directives.
kw_uselistorder, kw_uselistorder_bb,
// Unsigned Valued tokens (UIntVal).
GlobalID, // @42
LocalVarID, // %42
AttrGrpID, // #42
// String valued tokens (StrVal).
LabelStr, // foo:
GlobalVar, // @foo @"foo"
ComdatVar, // $foo
LocalVar, // %foo %"foo"
MetadataVar, // !foo
StringConstant, // "foo"
DwarfTag, // DW_TAG_foo
DwarfAttEncoding, // DW_ATE_foo
DwarfVirtuality, // DW_VIRTUALITY_foo
DwarfLang, // DW_LANG_foo
DwarfOp, // DW_OP_foo
DIFlag, // DIFlagFoo
// Type valued tokens (TyVal).
Type,
APFloat, // APFloatVal
APSInt // APSInt
};
} // end namespace lltok
} // end namespace llvm
#endif