diff options
| author | Alon Zakai <azakai@google.com> | 2019-12-19 09:04:08 -0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2019-12-19 09:04:08 -0800 |
| commit | 4d28d3f32e7f213e300b24bc61c3f0ac9d6e1ab6 (patch) | |
| tree | 91bffc2d47b1fe4bba01e7ada77006ef340bd138 /third_party/llvm-project/include/llvm/Support/LEB128.h | |
| parent | 0048f5b004ddf50e750aa335d0be314a73852058 (diff) | |
| download | binaryen-4d28d3f32e7f213e300b24bc61c3f0ac9d6e1ab6.tar.gz binaryen-4d28d3f32e7f213e300b24bc61c3f0ac9d6e1ab6.tar.bz2 binaryen-4d28d3f32e7f213e300b24bc61c3f0ac9d6e1ab6.zip | |
DWARF parsing and writing support using LLVM (#2520)
This imports LLVM code for DWARF handling. That code has the
Apache 2 license like us. It's also the same code used to
emit DWARF in the common toolchain, so it seems like a safe choice.
This adds two passes: --dwarfdump which runs the same code LLVM
runs for llvm-dwarfdump. This shows we can parse it ok, and will
be useful for debugging. And --dwarfupdate writes out the DWARF
sections (unchanged from what we read, so it just roundtrips - for
updating we need #2515).
This puts LLVM in thirdparty which is added here.
All the LLVM code is behind USE_LLVM_DWARF, which is on
by default, but off in JS for now, as it increases code size by 20%.
This current approach imports the LLVM files directly. This is not
how they are intended to be used, so it required a bunch of
local changes - more than I expected actually, for the platform-specific
stuff. For now this seems to work, so it may be good enough, but
in the long term we may want to switch to linking against libllvm.
A downside to doing that is that binaryen users would need to
have an LLVM build, and even in the waterfall builds we'd have a
problem - while we ship LLVM there anyhow, we constantly update
it, which means that binaryen would need to be on latest llvm all
the time too (which otherwise, given DWARF is quite stable, we
might not need to constantly update).
An even larger issue is that as I did this work I learned about how
DWARF works in LLVM, and while the reading code is easy to
reuse, the writing code is trickier. The main code path is heavily
integrated with the MC layer, which we don't have - we might want
to create a "fake MC layer" for that, but it sounds hard. Instead,
there is the YAML path which is used mostly for testing, and which
can convert DWARF to and from YAML and from binary. Using
the non-YAML parts there, we can convert binary DWARF to
the YAML layer's nice Info data, then convert that to binary. This
works, however, this is not the path LLVM uses normally, and it
supports only some basic DWARF sections - I had to add ranges
support, in fact. So if we need more complex things, we may end
up needing to use the MC layer approach, or consider some other
DWARF library. However, hopefully that should not affect the core
binaryen code which just calls a library for DWARF stuff.
Helps #2400
Diffstat (limited to 'third_party/llvm-project/include/llvm/Support/LEB128.h')
| -rw-r--r-- | third_party/llvm-project/include/llvm/Support/LEB128.h | 198 |
1 files changed, 198 insertions, 0 deletions
diff --git a/third_party/llvm-project/include/llvm/Support/LEB128.h b/third_party/llvm-project/include/llvm/Support/LEB128.h new file mode 100644 index 000000000..a02b83ca9 --- /dev/null +++ b/third_party/llvm-project/include/llvm/Support/LEB128.h @@ -0,0 +1,198 @@ +//===- llvm/Support/LEB128.h - [SU]LEB128 utility functions -----*- C++ -*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// +// +// This file declares some utility functions for encoding SLEB128 and +// ULEB128 values. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_SUPPORT_LEB128_H +#define LLVM_SUPPORT_LEB128_H + +#include "llvm/Support/raw_ostream.h" + +namespace llvm { + +/// Utility function to encode a SLEB128 value to an output stream. Returns +/// the length in bytes of the encoded value. +inline unsigned encodeSLEB128(int64_t Value, raw_ostream &OS, + unsigned PadTo = 0) { + bool More; + unsigned Count = 0; + do { + uint8_t Byte = Value & 0x7f; + // NOTE: this assumes that this signed shift is an arithmetic right shift. + Value >>= 7; + More = !((((Value == 0 ) && ((Byte & 0x40) == 0)) || + ((Value == -1) && ((Byte & 0x40) != 0)))); + Count++; + if (More || Count < PadTo) + Byte |= 0x80; // Mark this byte to show that more bytes will follow. + OS << char(Byte); + } while (More); + + // Pad with 0x80 and emit a terminating byte at the end. + if (Count < PadTo) { + uint8_t PadValue = Value < 0 ? 0x7f : 0x00; + for (; Count < PadTo - 1; ++Count) + OS << char(PadValue | 0x80); + OS << char(PadValue); + Count++; + } + return Count; +} + +/// Utility function to encode a SLEB128 value to a buffer. Returns +/// the length in bytes of the encoded value. +inline unsigned encodeSLEB128(int64_t Value, uint8_t *p, unsigned PadTo = 0) { + uint8_t *orig_p = p; + unsigned Count = 0; + bool More; + do { + uint8_t Byte = Value & 0x7f; + // NOTE: this assumes that this signed shift is an arithmetic right shift. + Value >>= 7; + More = !((((Value == 0 ) && ((Byte & 0x40) == 0)) || + ((Value == -1) && ((Byte & 0x40) != 0)))); + Count++; + if (More || Count < PadTo) + Byte |= 0x80; // Mark this byte to show that more bytes will follow. + *p++ = Byte; + } while (More); + + // Pad with 0x80 and emit a terminating byte at the end. + if (Count < PadTo) { + uint8_t PadValue = Value < 0 ? 0x7f : 0x00; + for (; Count < PadTo - 1; ++Count) + *p++ = (PadValue | 0x80); + *p++ = PadValue; + } + return (unsigned)(p - orig_p); +} + +/// Utility function to encode a ULEB128 value to an output stream. Returns +/// the length in bytes of the encoded value. +inline unsigned encodeULEB128(uint64_t Value, raw_ostream &OS, + unsigned PadTo = 0) { + unsigned Count = 0; + do { + uint8_t Byte = Value & 0x7f; + Value >>= 7; + Count++; + if (Value != 0 || Count < PadTo) + Byte |= 0x80; // Mark this byte to show that more bytes will follow. + OS << char(Byte); + } while (Value != 0); + + // Pad with 0x80 and emit a null byte at the end. + if (Count < PadTo) { + for (; Count < PadTo - 1; ++Count) + OS << '\x80'; + OS << '\x00'; + Count++; + } + return Count; +} + +/// Utility function to encode a ULEB128 value to a buffer. Returns +/// the length in bytes of the encoded value. +inline unsigned encodeULEB128(uint64_t Value, uint8_t *p, + unsigned PadTo = 0) { + uint8_t *orig_p = p; + unsigned Count = 0; + do { + uint8_t Byte = Value & 0x7f; + Value >>= 7; + Count++; + if (Value != 0 || Count < PadTo) + Byte |= 0x80; // Mark this byte to show that more bytes will follow. + *p++ = Byte; + } while (Value != 0); + + // Pad with 0x80 and emit a null byte at the end. + if (Count < PadTo) { + for (; Count < PadTo - 1; ++Count) + *p++ = '\x80'; + *p++ = '\x00'; + } + + return (unsigned)(p - orig_p); +} + +/// Utility function to decode a ULEB128 value. +inline uint64_t decodeULEB128(const uint8_t *p, unsigned *n = nullptr, + const uint8_t *end = nullptr, + const char **error = nullptr) { + const uint8_t *orig_p = p; + uint64_t Value = 0; + unsigned Shift = 0; + if (error) + *error = nullptr; + do { + if (end && p == end) { + if (error) + *error = "malformed uleb128, extends past end"; + if (n) + *n = (unsigned)(p - orig_p); + return 0; + } + uint64_t Slice = *p & 0x7f; + if (Shift >= 64 || Slice << Shift >> Shift != Slice) { + if (error) + *error = "uleb128 too big for uint64"; + if (n) + *n = (unsigned)(p - orig_p); + return 0; + } + Value += uint64_t(*p & 0x7f) << Shift; + Shift += 7; + } while (*p++ >= 128); + if (n) + *n = (unsigned)(p - orig_p); + return Value; +} + +/// Utility function to decode a SLEB128 value. +inline int64_t decodeSLEB128(const uint8_t *p, unsigned *n = nullptr, + const uint8_t *end = nullptr, + const char **error = nullptr) { + const uint8_t *orig_p = p; + int64_t Value = 0; + unsigned Shift = 0; + uint8_t Byte; + if (error) + *error = nullptr; + do { + if (end && p == end) { + if (error) + *error = "malformed sleb128, extends past end"; + if (n) + *n = (unsigned)(p - orig_p); + return 0; + } + Byte = *p++; + Value |= (uint64_t(Byte & 0x7f) << Shift); + Shift += 7; + } while (Byte >= 128); + // Sign extend negative numbers if needed. + if (Shift < 64 && (Byte & 0x40)) + Value |= (-1ULL) << Shift; + if (n) + *n = (unsigned)(p - orig_p); + return Value; +} + +/// Utility function to get the size of the ULEB128-encoded value. +extern unsigned getULEB128Size(uint64_t Value); + +/// Utility function to get the size of the SLEB128-encoded value. +extern unsigned getSLEB128Size(int64_t Value); + +} // namespace llvm + +#endif // LLVM_SYSTEM_LEB128_H |