teemperor created this revision.
teemperor added reviewers: dvlahovski, zturner.
It's possible to hit an unaligned memory read when reading `source_length` as
the `data` array is only aligned with 2 bytes (it's actually a UTF16 array).
This patch memcpy's `source_length` into a local variable to prevent this:
MinidumpTypes.cpp:49:23: runtime error: load of misaligned address
0x7f0f4792692a for type 'const uint32_t' (aka 'const unsigned int'), which
requires 4 byte alignment
https://reviews.llvm.org/D42348
Files:
source/Plugins/Process/minidump/MinidumpTypes.cpp
Index: source/Plugins/Process/minidump/MinidumpTypes.cpp
===================================================================
--- source/Plugins/Process/minidump/MinidumpTypes.cpp
+++ source/Plugins/Process/minidump/MinidumpTypes.cpp
@@ -44,19 +44,24 @@
lldb_private::minidump::parseMinidumpString(llvm::ArrayRef<uint8_t> &data) {
std::string result;
- const uint32_t *source_length;
- Status error = consumeObject(data, source_length);
- if (error.Fail() || *source_length > data.size() || *source_length % 2 != 0)
+ const uint32_t *source_length_ptr;
+ Status error = consumeObject(data, source_length_ptr);
+
+ // Copy non-aligned source_length data into aligned memory.
+ uint32_t source_length;
+ std::memcpy(&source_length, source_length_ptr, sizeof(source_length));
+
+ if (error.Fail() || source_length > data.size() || source_length % 2 != 0)
return llvm::None;
auto source_start = reinterpret_cast<const llvm::UTF16 *>(data.data());
// source_length is the length of the string in bytes
// we need the length of the string in UTF-16 characters/code points (16 bits
// per char)
// that's why it's divided by 2
- const auto source_end = source_start + (*source_length) / 2;
+ const auto source_end = source_start + source_length / 2;
// resize to worst case length
- result.resize(UNI_MAX_UTF8_BYTES_PER_CODE_POINT * (*source_length) / 2);
+ result.resize(UNI_MAX_UTF8_BYTES_PER_CODE_POINT * source_length / 2);
auto result_start = reinterpret_cast<llvm::UTF8 *>(&result[0]);
const auto result_end = result_start + result.size();
llvm::ConvertUTF16toUTF8(&source_start, source_end, &result_start,
result_end,
Index: source/Plugins/Process/minidump/MinidumpTypes.cpp
===================================================================
--- source/Plugins/Process/minidump/MinidumpTypes.cpp
+++ source/Plugins/Process/minidump/MinidumpTypes.cpp
@@ -44,19 +44,24 @@
lldb_private::minidump::parseMinidumpString(llvm::ArrayRef<uint8_t> &data) {
std::string result;
- const uint32_t *source_length;
- Status error = consumeObject(data, source_length);
- if (error.Fail() || *source_length > data.size() || *source_length % 2 != 0)
+ const uint32_t *source_length_ptr;
+ Status error = consumeObject(data, source_length_ptr);
+
+ // Copy non-aligned source_length data into aligned memory.
+ uint32_t source_length;
+ std::memcpy(&source_length, source_length_ptr, sizeof(source_length));
+
+ if (error.Fail() || source_length > data.size() || source_length % 2 != 0)
return llvm::None;
auto source_start = reinterpret_cast<const llvm::UTF16 *>(data.data());
// source_length is the length of the string in bytes
// we need the length of the string in UTF-16 characters/code points (16 bits
// per char)
// that's why it's divided by 2
- const auto source_end = source_start + (*source_length) / 2;
+ const auto source_end = source_start + source_length / 2;
// resize to worst case length
- result.resize(UNI_MAX_UTF8_BYTES_PER_CODE_POINT * (*source_length) / 2);
+ result.resize(UNI_MAX_UTF8_BYTES_PER_CODE_POINT * source_length / 2);
auto result_start = reinterpret_cast<llvm::UTF8 *>(&result[0]);
const auto result_end = result_start + result.size();
llvm::ConvertUTF16toUTF8(&source_start, source_end, &result_start, result_end,
_______________________________________________
lldb-commits mailing list
lldb-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/lldb-commits
