Files
Jonas Devlieghere 77b0b29955 [lldb] Return an empty extractor for unmappable subset requests (#205596)
DataExtractor::GetSubsetExtractorSP always returns a valid, non-null
extractor, and every caller relies on that: they dereference the result
directly rather than checking for null. The VirtualDataExtractor
override broke this contract. When the requested range had no backing in
the lookup table (e.g. the virtual offset fell in a gap, or the range
crossed an entry boundary) it returned an empty shared_ptr, turning each
caller's dereference into a null-pointer access.

It also asserted on those cases. But the offsets passed to a subset
request are derived from parsed file contents, which may be truncated or
inconsistent. A range that cannot be mapped is therefore ordinary input,
not a programming error, and must not abort an assertions-enabled build.

Return a valid but empty extractor instead. Reads see zero bytes and the
caller's existing size checks skip the data, matching the graceful
degradation the base class already provides for out-of-range offsets.

Assisted-by: Claude
2026-06-25 08:16:26 -07:00

318 lines
12 KiB
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
//
//===----------------------------------------------------------------------===//
#include "lldb/Utility/VirtualDataExtractor.h"
#include <cassert>
using namespace lldb;
using namespace lldb_private;
VirtualDataExtractor::VirtualDataExtractor(const void *data,
offset_t data_length,
ByteOrder byte_order,
uint32_t addr_size,
LookupTable lookup_table)
: DataExtractor(data, data_length, byte_order, addr_size),
m_lookup_table(std::move(lookup_table)) {
m_lookup_table.Sort();
}
VirtualDataExtractor::VirtualDataExtractor(const DataBufferSP &data_sp,
ByteOrder byte_order,
uint32_t addr_size,
LookupTable lookup_table)
: DataExtractor(data_sp, byte_order, addr_size),
m_lookup_table(std::move(lookup_table)) {
m_lookup_table.Sort();
}
VirtualDataExtractor::VirtualDataExtractor(const DataBufferSP &data_sp,
LookupTable lookup_table)
: DataExtractor(data_sp), m_lookup_table(std::move(lookup_table)) {
m_lookup_table.Sort();
}
const VirtualDataExtractor::LookupTable::Entry *
VirtualDataExtractor::FindEntry(offset_t virtual_addr) const {
// Use RangeDataVector's binary search instead of linear search.
return m_lookup_table.FindEntryThatContains(virtual_addr);
}
bool VirtualDataExtractor::ValidateVirtualRead(offset_t virtual_addr,
offset_t length) const {
const LookupTable::Entry *entry = FindEntry(virtual_addr);
if (!entry)
return false;
// Assert that the read does not cross entry boundaries.
// RangeData.Contains() checks if a range is fully contained.
assert(entry->Contains(LookupTable::Range(virtual_addr, length)) &&
"Read crosses lookup table entry boundary");
// Also validate that the physical offset is within the data buffer.
// RangeData.data contains the physical offset.
offset_t physical_offset = entry->data + (virtual_addr - entry->base);
return ValidOffsetForDataOfSize(physical_offset, length);
}
const void *VirtualDataExtractor::GetData(offset_t *offset_ptr,
offset_t length) const {
// Override to treat offset as virtual address.
if (!offset_ptr)
return nullptr;
offset_t virtual_addr = *offset_ptr;
if (!ValidateVirtualRead(virtual_addr, length))
return nullptr;
const LookupTable::Entry *entry = FindEntry(virtual_addr);
assert(entry && "ValidateVirtualRead should have found an entry");
offset_t physical_offset = entry->data + (virtual_addr - entry->base);
// Use base class PeekData directly to avoid recursion.
const void *result = DataExtractor::PeekData(physical_offset, length);
if (result) {
// Advance the virtual offset pointer.
*offset_ptr += length;
}
return result;
}
offset_t VirtualDataExtractor::SetData(const void *bytes, lldb::offset_t length,
lldb::ByteOrder byte_order) {
// Invoked from the base class ctor.
if (!m_data_sp || m_start == nullptr)
return DataExtractor::SetData(bytes, length, byte_order);
// A no-op SetData that is setting the same data buffer again.
if (!m_data_sp && m_start == bytes && length == GetVirtualByteSize())
return GetVirtualByteSize();
assert("SetData(1) called on VirtualDataExtractor that already had data" &&
false);
DataExtractor::SetData(bytes, length, byte_order);
ResetLookupTableToMatchPhysical();
return GetVirtualByteSize();
}
offset_t VirtualDataExtractor::SetData(const DataExtractor &data,
lldb::offset_t offset,
lldb::offset_t length) {
// Invoked from the base class ctor
if (!m_data_sp || m_start == nullptr)
return DataExtractor::SetData(data, offset, length);
// A no-op SetData that is setting the same data buffer again
if (m_data_sp && data.GetSharedDataBuffer().get() == m_data_sp.get() &&
offset == 0 && length == GetVirtualByteSize())
return GetVirtualByteSize();
assert("SetData(2) called on VirtualDataExtractor that already had data" &&
false);
DataExtractor::SetData(data, offset, length);
ResetLookupTableToMatchPhysical();
return GetVirtualByteSize();
}
offset_t VirtualDataExtractor::SetData(const lldb::DataBufferSP &data_sp,
lldb::offset_t offset,
lldb::offset_t length) {
// Invoked from the base class ctor
if (!m_data_sp || m_start == nullptr)
return DataExtractor::SetData(data_sp, offset, length);
// A no-op SetData that is setting the same data buffer again
if (m_data_sp && data_sp.get() == m_data_sp.get() && offset == 0 &&
length == GetVirtualByteSize())
return GetVirtualByteSize();
assert("SetData(3) called on VirtualDataExtractor that already had data" &&
false);
DataExtractor::SetData(data_sp, offset, length);
ResetLookupTableToMatchPhysical();
return GetVirtualByteSize();
}
void VirtualDataExtractor::ResetLookupTableToMatchPhysical() {
// calling SetData on a VirtualDataExtractor that already has a
// data buffer means the LookupTable needs to be either replaced, or
// if we assume the buffer is a subset of the original, we need to
// update all the entries to have correct new offsets into the buffer
// and remove entries that are outside the new range.
// For now, zero out the LookupTable and behave as if this is a simple
// DataExtractor.
m_lookup_table.Clear();
m_lookup_table.Append(
VirtualDataExtractor::LookupTable::Entry{0, GetPhysicalByteSize(), 0});
}
uint64_t VirtualDataExtractor::GetVirtualByteSize() const {
offset_t lowest = -1ULL;
offset_t highest = 0;
for (const auto ent : m_lookup_table) {
lowest = std::min(lowest, ent.base);
highest = std::max(highest, ent.base + ent.size);
}
return highest - lowest;
}
uint64_t VirtualDataExtractor::GetPhysicalByteSize() const {
return m_end - m_start;
}
offset_t VirtualDataExtractor::VirtualBytesLeft(offset_t virtual_offset) const {
const offset_t size = GetVirtualByteSize();
if (size > virtual_offset)
return size - virtual_offset;
return 0;
}
offset_t
VirtualDataExtractor::PhysicalBytesLeft(offset_t physical_offset) const {
const offset_t size = m_end - m_start;
if (size > physical_offset)
return size - physical_offset;
return 0;
}
const uint8_t *VirtualDataExtractor::PeekData(offset_t offset,
offset_t length) const {
// Override to treat offset as virtual address.
if (!ValidateVirtualRead(offset, length))
return nullptr;
const LookupTable::Entry *entry = FindEntry(offset);
assert(entry && "ValidateVirtualRead should have found an entry");
offset_t physical_offset = entry->data + (offset - entry->base);
// Use the base class PeekData with the physical offset.
return DataExtractor::PeekData(physical_offset, length);
}
uint8_t VirtualDataExtractor::GetU8_unchecked(offset_t *offset_ptr) const {
offset_t virtual_addr = *offset_ptr;
const LookupTable::Entry *entry = FindEntry(virtual_addr);
assert(entry && "Unchecked methods require valid virtual address");
offset_t physical_offset = entry->data + (virtual_addr - entry->base);
uint8_t result = DataExtractor::GetU8_unchecked(&physical_offset);
*offset_ptr += 1;
return result;
}
uint16_t VirtualDataExtractor::GetU16_unchecked(offset_t *offset_ptr) const {
offset_t virtual_addr = *offset_ptr;
const LookupTable::Entry *entry = FindEntry(virtual_addr);
assert(entry && "Unchecked methods require valid virtual address");
offset_t physical_offset = entry->data + (virtual_addr - entry->base);
uint16_t result = DataExtractor::GetU16_unchecked(&physical_offset);
*offset_ptr += 2;
return result;
}
uint32_t VirtualDataExtractor::GetU32_unchecked(offset_t *offset_ptr) const {
offset_t virtual_addr = *offset_ptr;
const LookupTable::Entry *entry = FindEntry(virtual_addr);
assert(entry && "Unchecked methods require valid virtual address");
offset_t physical_offset = entry->data + (virtual_addr - entry->base);
uint32_t result = DataExtractor::GetU32_unchecked(&physical_offset);
*offset_ptr += 4;
return result;
}
uint64_t VirtualDataExtractor::GetU64_unchecked(offset_t *offset_ptr) const {
offset_t virtual_addr = *offset_ptr;
const LookupTable::Entry *entry = FindEntry(virtual_addr);
assert(entry && "Unchecked methods require valid virtual address");
offset_t physical_offset = entry->data + (virtual_addr - entry->base);
uint64_t result = DataExtractor::GetU64_unchecked(&physical_offset);
*offset_ptr += 8;
return result;
}
/// A subset request that can't be mapped still returns a valid, non-null
/// extractor, because most callers dereference the result directly.
static DataExtractorSP MakeEmptySubsetExtractor(ByteOrder byte_order,
uint32_t addr_size) {
auto empty_sp = std::make_shared<DataExtractor>();
empty_sp->SetByteOrder(byte_order);
empty_sp->SetAddressByteSize(addr_size);
return empty_sp;
}
DataExtractorSP
VirtualDataExtractor::GetSubsetExtractorSP(offset_t virtual_offset,
offset_t virtual_length) {
const LookupTable::Entry *entry = FindEntry(virtual_offset);
if (!entry)
return MakeEmptySubsetExtractor(GetByteOrder(), GetAddressByteSize());
// Entry::data is the offset into the DataBuffer's actual start/end range
// Entry::base is the virtual address at the start of this region of data
offset_t offset_into_entry_range = virtual_offset - entry->base;
// A subset may not span more than one entry; a range that overflows this
// entry is unmappable.
if (offset_into_entry_range + virtual_length > entry->size)
return MakeEmptySubsetExtractor(GetByteOrder(), GetAddressByteSize());
// We could support a Subset VirtualDataExtractor which covered
// multiple LookupTable virtual entries, but we'd need to mutate
// all of the LookupTable entries that were properly included in
// the Subset, a bit tricky. So we won't implement that until it's
// needed.
offset_t physical_start = entry->data + offset_into_entry_range;
std::shared_ptr<DataExtractor> new_sp = std::make_shared<DataExtractor>(
GetSharedDataBuffer(), GetByteOrder(), GetAddressByteSize());
new_sp->SetData(GetSharedDataBuffer(), physical_start, virtual_length);
return new_sp;
}
// Return a DataExtractorSP that contains a single LookupTable's entry; all
// bytes are guaranteed to be readable.
DataExtractorSP
VirtualDataExtractor::GetSubsetExtractorSP(offset_t virtual_offset) {
const LookupTable::Entry *entry = FindEntry(virtual_offset);
if (!entry)
return MakeEmptySubsetExtractor(GetByteOrder(), GetAddressByteSize());
// Entry::data is the offset into the DataBuffer's actual start/end range
// Entry::base is the virtual address at the start of this region of data
offset_t offset_into_entry_range = virtual_offset - entry->base;
offset_t physical_start = entry->data + offset_into_entry_range;
std::shared_ptr<DataExtractor> new_sp = std::make_shared<DataExtractor>(
GetSharedDataBuffer(), GetByteOrder(), GetAddressByteSize());
new_sp->SetData(GetSharedDataBuffer(), physical_start,
entry->size - offset_into_entry_range);
return new_sp;
}
// Return an ArrayRef to the first contiguous region of the LookupTable
// only. The LookupTable entries may have gaps of unmapped data, and we
// can't include those in the ArrayRef or something may touch those pages.
llvm::ArrayRef<uint8_t> VirtualDataExtractor::GetData() const {
const LookupTable::Entry *entry = FindEntry(0);
assert(entry &&
"VirtualDataExtractor GetData requires valid virtual address");
if (!entry)
return {};
return {m_start + static_cast<size_t>(entry->data), static_cast<size_t>(entry->size)};
}