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/DataExtractor.cpp | |
| 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/DataExtractor.cpp')
| -rw-r--r-- | third_party/llvm-project/DataExtractor.cpp | 218 |
1 files changed, 218 insertions, 0 deletions
diff --git a/third_party/llvm-project/DataExtractor.cpp b/third_party/llvm-project/DataExtractor.cpp new file mode 100644 index 000000000..a98297cdb --- /dev/null +++ b/third_party/llvm-project/DataExtractor.cpp @@ -0,0 +1,218 @@ +//===-- DataExtractor.cpp -------------------------------------------------===// +// +// 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 +// +//===----------------------------------------------------------------------===// + +#include "llvm/Support/DataExtractor.h" +#include "llvm/Support/Errc.h" +#include "llvm/Support/ErrorHandling.h" +#include "llvm/Support/Host.h" +#include "llvm/Support/LEB128.h" +#include "llvm/Support/SwapByteOrder.h" + +using namespace llvm; + +static void unexpectedEndReached(Error *E) { + if (E) + *E = createStringError(errc::illegal_byte_sequence, + "unexpected end of data"); +} + +static bool isError(Error *E) { return E && *E; } + +template <typename T> +static T getU(uint64_t *offset_ptr, const DataExtractor *de, + bool isLittleEndian, const char *Data, llvm::Error *Err) { + ErrorAsOutParameter ErrAsOut(Err); + T val = 0; + if (isError(Err)) + return val; + + uint64_t offset = *offset_ptr; + if (!de->isValidOffsetForDataOfSize(offset, sizeof(T))) { + unexpectedEndReached(Err); + return val; + } + std::memcpy(&val, &Data[offset], sizeof(val)); + if (sys::IsLittleEndianHost != isLittleEndian) + sys::swapByteOrder(val); + + // Advance the offset + *offset_ptr += sizeof(val); + return val; +} + +template <typename T> +static T *getUs(uint64_t *offset_ptr, T *dst, uint32_t count, + const DataExtractor *de, bool isLittleEndian, const char *Data, + llvm::Error *Err) { + ErrorAsOutParameter ErrAsOut(Err); + if (isError(Err)) + return nullptr; + + uint64_t offset = *offset_ptr; + + if (!de->isValidOffsetForDataOfSize(offset, sizeof(*dst) * count)) { + unexpectedEndReached(Err); + return nullptr; + } + for (T *value_ptr = dst, *end = dst + count; value_ptr != end; + ++value_ptr, offset += sizeof(*dst)) + *value_ptr = getU<T>(offset_ptr, de, isLittleEndian, Data, Err); + // Advance the offset + *offset_ptr = offset; + // Return a non-NULL pointer to the converted data as an indicator of + // success + return dst; +} + +uint8_t DataExtractor::getU8(uint64_t *offset_ptr, llvm::Error *Err) const { + return getU<uint8_t>(offset_ptr, this, IsLittleEndian, Data.data(), Err); +} + +uint8_t * +DataExtractor::getU8(uint64_t *offset_ptr, uint8_t *dst, uint32_t count) const { + return getUs<uint8_t>(offset_ptr, dst, count, this, IsLittleEndian, + Data.data(), nullptr); +} + +uint8_t *DataExtractor::getU8(Cursor &C, uint8_t *Dst, uint32_t Count) const { + return getUs<uint8_t>(&C.Offset, Dst, Count, this, IsLittleEndian, + Data.data(), &C.Err); +} + +uint16_t DataExtractor::getU16(uint64_t *offset_ptr, llvm::Error *Err) const { + return getU<uint16_t>(offset_ptr, this, IsLittleEndian, Data.data(), Err); +} + +uint16_t *DataExtractor::getU16(uint64_t *offset_ptr, uint16_t *dst, + uint32_t count) const { + return getUs<uint16_t>(offset_ptr, dst, count, this, IsLittleEndian, + Data.data(), nullptr); +} + +uint32_t DataExtractor::getU24(uint64_t *offset_ptr) const { + uint24_t ExtractedVal = + getU<uint24_t>(offset_ptr, this, IsLittleEndian, Data.data(), nullptr); + // The 3 bytes are in the correct byte order for the host. + return ExtractedVal.getAsUint32(sys::IsLittleEndianHost); +} + +uint32_t DataExtractor::getU32(uint64_t *offset_ptr, llvm::Error *Err) const { + return getU<uint32_t>(offset_ptr, this, IsLittleEndian, Data.data(), Err); +} + +uint32_t *DataExtractor::getU32(uint64_t *offset_ptr, uint32_t *dst, + uint32_t count) const { + return getUs<uint32_t>(offset_ptr, dst, count, this, IsLittleEndian, + Data.data(), nullptr); +} + +uint64_t DataExtractor::getU64(uint64_t *offset_ptr, llvm::Error *Err) const { + return getU<uint64_t>(offset_ptr, this, IsLittleEndian, Data.data(), Err); +} + +uint64_t *DataExtractor::getU64(uint64_t *offset_ptr, uint64_t *dst, + uint32_t count) const { + return getUs<uint64_t>(offset_ptr, dst, count, this, IsLittleEndian, + Data.data(), nullptr); +} + +uint64_t DataExtractor::getUnsigned(uint64_t *offset_ptr, uint32_t byte_size, + llvm::Error *Err) const { + switch (byte_size) { + case 1: + return getU8(offset_ptr, Err); + case 2: + return getU16(offset_ptr, Err); + case 4: + return getU32(offset_ptr, Err); + case 8: + return getU64(offset_ptr, Err); + } + llvm_unreachable("getUnsigned unhandled case!"); +} + +int64_t +DataExtractor::getSigned(uint64_t *offset_ptr, uint32_t byte_size) const { + switch (byte_size) { + case 1: + return (int8_t)getU8(offset_ptr); + case 2: + return (int16_t)getU16(offset_ptr); + case 4: + return (int32_t)getU32(offset_ptr); + case 8: + return (int64_t)getU64(offset_ptr); + } + llvm_unreachable("getSigned unhandled case!"); +} + +const char *DataExtractor::getCStr(uint64_t *offset_ptr) const { + uint64_t offset = *offset_ptr; + StringRef::size_type pos = Data.find('\0', offset); + if (pos != StringRef::npos) { + *offset_ptr = pos + 1; + return Data.data() + offset; + } + return nullptr; +} + +StringRef DataExtractor::getCStrRef(uint64_t *offset_ptr) const { + uint64_t Start = *offset_ptr; + StringRef::size_type Pos = Data.find('\0', Start); + if (Pos != StringRef::npos) { + *offset_ptr = Pos + 1; + return StringRef(Data.data() + Start, Pos - Start); + } + return StringRef(); +} + +uint64_t DataExtractor::getULEB128(uint64_t *offset_ptr, + llvm::Error *Err) const { + assert(*offset_ptr <= Data.size()); + ErrorAsOutParameter ErrAsOut(Err); + if (isError(Err)) + return 0; + + const char *error; + unsigned bytes_read; + uint64_t result = decodeULEB128( + reinterpret_cast<const uint8_t *>(Data.data() + *offset_ptr), &bytes_read, + reinterpret_cast<const uint8_t *>(Data.data() + Data.size()), &error); + if (error) { + if (Err) + *Err = createStringError(errc::illegal_byte_sequence, error); + return 0; + } + *offset_ptr += bytes_read; + return result; +} + +int64_t DataExtractor::getSLEB128(uint64_t *offset_ptr) const { + assert(*offset_ptr <= Data.size()); + + const char *error; + unsigned bytes_read; + int64_t result = decodeSLEB128( + reinterpret_cast<const uint8_t *>(Data.data() + *offset_ptr), &bytes_read, + reinterpret_cast<const uint8_t *>(Data.data() + Data.size()), &error); + if (error) + return 0; + *offset_ptr += bytes_read; + return result; +} + +void DataExtractor::skip(Cursor &C, uint64_t Length) const { + ErrorAsOutParameter ErrAsOut(&C.Err); + if (isError(&C.Err)) + return; + + if (isValidOffsetForDataOfSize(C.Offset, Length)) + C.Offset += Length; + else + unexpectedEndReached(&C.Err); +} |