maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/lldb/source/Symbol/DWARFCallFrameInfo.cpp

940 lines
37 KiB
C++
Raw Normal View History

Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
//===-- DWARFCallFrameInfo.cpp ----------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
// C Includes
// C++ Includes
#include <list>
#include "lldb/Core/ArchSpec.h"
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
#include "lldb/Core/Log.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Core/Module.h"
Added code in the Host layer that can report system log messages so that we don't have "fprintf (stderr, ...)" calls sprinkled everywhere. Changed all needed locations over to using this. For non-darwin, we log to stderr only. On darwin, we log to stderr _and_ to ASL (Apple System Log facility). This will allow GUI apps to have a place for these error and warning messages to go, and also allows the command line apps to log directly to the terminal. llvm-svn: 147596
2012-01-05 11:57:59 +08:00
#include "lldb/Core/Section.h"
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
#include "lldb/Core/Section.h"
Change DWARFCallFrameInfo from using a vector of AddressRanges to track the EH FDEs for the functions in a module to using a RangeDataVector, a more light-weight data structure that only refers to File addresses. Makes the initial FDE scan about 3x faster, uses less memory. <rdar://problem/13465650> llvm-svn: 177585
2013-03-21 05:57:42 +08:00
#include "lldb/Core/Timer.h"
Added code in the Host layer that can report system log messages so that we don't have "fprintf (stderr, ...)" calls sprinkled everywhere. Changed all needed locations over to using this. For non-darwin, we log to stderr only. On darwin, we log to stderr _and_ to ASL (Apple System Log facility). This will allow GUI apps to have a place for these error and warning messages to go, and also allows the command line apps to log directly to the terminal. llvm-svn: 147596
2012-01-05 11:57:59 +08:00
#include "lldb/Host/Host.h"
#include "lldb/Symbol/DWARFCallFrameInfo.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Symbol/ObjectFile.h"
Added code in the Host layer that can report system log messages so that we don't have "fprintf (stderr, ...)" calls sprinkled everywhere. Changed all needed locations over to using this. For non-darwin, we log to stderr only. On darwin, we log to stderr _and_ to ASL (Apple System Log facility). This will allow GUI apps to have a place for these error and warning messages to go, and also allows the command line apps to log directly to the terminal. llvm-svn: 147596
2012-01-05 11:57:59 +08:00
#include "lldb/Symbol/UnwindPlan.h"
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
#include "lldb/Target/RegisterContext.h"
#include "lldb/Target/Thread.h"
using namespace lldb;
using namespace lldb_private;
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
DWARFCallFrameInfo::DWARFCallFrameInfo(ObjectFile &objfile,
SectionSP &section_sp,
lldb::RegisterKind reg_kind,
bool is_eh_frame)
: m_objfile(objfile), m_section_sp(section_sp),
m_reg_kind(reg_kind), // The flavor of registers that the CFI data uses
// (enum RegisterKind)
m_flags(), m_cie_map(), m_cfi_data(), m_cfi_data_initialized(false),
m_fde_index(), m_fde_index_initialized(false),
m_is_eh_frame(is_eh_frame) {}
DWARFCallFrameInfo::~DWARFCallFrameInfo() {}
bool DWARFCallFrameInfo::GetUnwindPlan(Address addr, UnwindPlan &unwind_plan) {
FDEEntryMap::Entry fde_entry;
// Make sure that the Address we're searching for is the same object file
// as this DWARFCallFrameInfo, we only store File offsets in m_fde_index.
ModuleSP module_sp = addr.GetModule();
if (module_sp.get() == nullptr || module_sp->GetObjectFile() == nullptr ||
module_sp->GetObjectFile() != &m_objfile)
return false;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
if (GetFDEEntryByFileAddress(addr.GetFileAddress(), fde_entry) == false)
return false;
return FDEToUnwindPlan(fde_entry.data, addr, unwind_plan);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
bool DWARFCallFrameInfo::GetAddressRange(Address addr, AddressRange &range) {
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// Make sure that the Address we're searching for is the same object file
// as this DWARFCallFrameInfo, we only store File offsets in m_fde_index.
ModuleSP module_sp = addr.GetModule();
if (module_sp.get() == nullptr || module_sp->GetObjectFile() == nullptr ||
module_sp->GetObjectFile() != &m_objfile)
return false;
Change DWARFCallFrameInfo from using a vector of AddressRanges to track the EH FDEs for the functions in a module to using a RangeDataVector, a more light-weight data structure that only refers to File addresses. Makes the initial FDE scan about 3x faster, uses less memory. <rdar://problem/13465650> llvm-svn: 177585
2013-03-21 05:57:42 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
if (m_section_sp.get() == nullptr || m_section_sp->IsEncrypted())
return false;
GetFDEIndex();
FDEEntryMap::Entry *fde_entry =
m_fde_index.FindEntryThatContains(addr.GetFileAddress());
if (!fde_entry)
return false;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
range = AddressRange(fde_entry->base, fde_entry->size,
m_objfile.GetSectionList());
return true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
bool DWARFCallFrameInfo::GetFDEEntryByFileAddress(
addr_t file_addr, FDEEntryMap::Entry &fde_entry) {
if (m_section_sp.get() == nullptr || m_section_sp->IsEncrypted())
return false;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
GetFDEIndex();
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
if (m_fde_index.IsEmpty())
return false;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
FDEEntryMap::Entry *fde = m_fde_index.FindEntryThatContains(file_addr);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
if (fde == nullptr)
return false;
Change DWARFCallFrameInfo from using a vector of AddressRanges to track the EH FDEs for the functions in a module to using a RangeDataVector, a more light-weight data structure that only refers to File addresses. Makes the initial FDE scan about 3x faster, uses less memory. <rdar://problem/13465650> llvm-svn: 177585
2013-03-21 05:57:42 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
fde_entry = *fde;
return true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
void DWARFCallFrameInfo::GetFunctionAddressAndSizeVector(
FunctionAddressAndSizeVector &function_info) {
GetFDEIndex();
const size_t count = m_fde_index.GetSize();
function_info.Clear();
if (count > 0)
function_info.Reserve(count);
for (size_t i = 0; i < count; ++i) {
const FDEEntryMap::Entry *func_offset_data_entry =
m_fde_index.GetEntryAtIndex(i);
if (func_offset_data_entry) {
FunctionAddressAndSizeVector::Entry function_offset_entry(
func_offset_data_entry->base, func_offset_data_entry->size);
function_info.Append(function_offset_entry);
Add a new method GetFunctionAddressAndSizeVector to DWARFCallFrameInfo. This returns a vector of <file address, size> entries for all of the functions in the module that have an eh_frame FDE. Update ObjectFileMachO to use the eh_frame FDE function addresses if the LC_FUNCTION_STARTS section is missing, to fill in the start addresses of any symbols that have been stripped from the binary. Generally speaking, lldb works best if it knows the actual start address of every function in a module - it's especially important for unwinding, where lldb inspects the instructions in the prologue of the function. In a stripped binary, it is deprived of this information and it reduces the quality of our unwinds and saved register retrieval. Other ObjectFile users may want to use the function addresses from DWARFCallFrameInfo to fill in any stripped symbols like ObjectFileMachO does already. <rdar://problem/13365659> llvm-svn: 177624
2013-03-21 11:36:01 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
}
Add a new method GetFunctionAddressAndSizeVector to DWARFCallFrameInfo. This returns a vector of <file address, size> entries for all of the functions in the module that have an eh_frame FDE. Update ObjectFileMachO to use the eh_frame FDE function addresses if the LC_FUNCTION_STARTS section is missing, to fill in the start addresses of any symbols that have been stripped from the binary. Generally speaking, lldb works best if it knows the actual start address of every function in a module - it's especially important for unwinding, where lldb inspects the instructions in the prologue of the function. In a stripped binary, it is deprived of this information and it reduces the quality of our unwinds and saved register retrieval. Other ObjectFile users may want to use the function addresses from DWARFCallFrameInfo to fill in any stripped symbols like ObjectFileMachO does already. <rdar://problem/13365659> llvm-svn: 177624
2013-03-21 11:36:01 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
const DWARFCallFrameInfo::CIE *
DWARFCallFrameInfo::GetCIE(dw_offset_t cie_offset) {
cie_map_t::iterator pos = m_cie_map.find(cie_offset);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
if (pos != m_cie_map.end()) {
// Parse and cache the CIE
if (pos->second.get() == nullptr)
pos->second = ParseCIE(cie_offset);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
return pos->second.get();
}
return nullptr;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
The first part of an lldb native stack unwinder. The Unwind and RegisterContext subclasses still need to be finished; none of this code is used by lldb at this point (unless you call into it by hand). The ObjectFile class now has an UnwindTable object. The UnwindTable object has a series of FuncUnwinders objects (Function Unwinders) -- one for each function in that ObjectFile we've backtraced through during this debug session. The FuncUnwinders object has a few different UnwindPlans. UnwindPlans are a generic way of describing how to find the canonical address of a given function's stack frame (the CFA idea from DWARF/eh_frame) and how to restore the caller frame's register values, if they have been saved by this function. UnwindPlans are created from different sources. One source is the eh_frame exception handling information generated by the compiler for unwinding an exception throw. Another source is an assembly language inspection class (UnwindAssemblyProfiler, uses the Plugin architecture) which looks at the instructions in the funciton prologue and describes the stack movements/register saves that are done. Two additional types of UnwindPlans that are worth noting are the "fast" stack UnwindPlan which is useful for making a first pass over a thread's stack, determining how many stack frames there are and retrieving the pc and CFA values for each frame (enough to create StackFrameIDs). Only a minimal set of registers is recovered during a fast stack walk. The final UnwindPlan is an architectural default unwind plan. These are provided by the ArchDefaultUnwindPlan class (which uses the plugin architecture). When no symbol/function address range can be found for a given pc value -- when we have no eh_frame information and when we don't have a start address so we can't examine the assembly language instrucitons -- we have to make a best guess about how to unwind. That's when we use the architectural default UnwindPlan. On x86_64, this would be to assume that rbp is used as a stack pointer and we can use that to find the caller's frame pointer and pc value. It's a last-ditch best guess about how to unwind out of a frame. There are heuristics about when to use one UnwindPlan versues the other -- this will all happen in the still-begin-written UnwindLLDB subclass of Unwind which runs the UnwindPlans. llvm-svn: 113581
2010-09-10 15:49:16 +08:00
DWARFCallFrameInfo::CIESP
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
DWARFCallFrameInfo::ParseCIE(const dw_offset_t cie_offset) {
CIESP cie_sp(new CIE(cie_offset));
lldb::offset_t offset = cie_offset;
if (m_cfi_data_initialized == false)
GetCFIData();
uint32_t length = m_cfi_data.GetU32(&offset);
dw_offset_t cie_id, end_offset;
bool is_64bit = (length == UINT32_MAX);
if (is_64bit) {
length = m_cfi_data.GetU64(&offset);
cie_id = m_cfi_data.GetU64(&offset);
end_offset = cie_offset + length + 12;
} else {
cie_id = m_cfi_data.GetU32(&offset);
end_offset = cie_offset + length + 4;
}
if (length > 0 && ((!m_is_eh_frame && cie_id == UINT32_MAX) ||
(m_is_eh_frame && cie_id == 0ul))) {
size_t i;
// cie.offset = cie_offset;
// cie.length = length;
// cie.cieID = cieID;
cie_sp->ptr_encoding = DW_EH_PE_absptr; // default
cie_sp->version = m_cfi_data.GetU8(&offset);
for (i = 0; i < CFI_AUG_MAX_SIZE; ++i) {
cie_sp->augmentation[i] = m_cfi_data.GetU8(&offset);
if (cie_sp->augmentation[i] == '\0') {
// Zero out remaining bytes in augmentation string
for (size_t j = i + 1; j < CFI_AUG_MAX_SIZE; ++j)
cie_sp->augmentation[j] = '\0';
break;
}
Add 64-bit eh_frame section CFI support. In practice, 64bit eh_frame is not used even for x86_64 binaries. The main reason is in eh_frame we almost always use pc-relative addressing, so addresses are within 32bits and gcc just sticks to 32bit eh_frame. I generated 64bit eh_frame for Android Java runtime and unwind successfully in gdb, and in lldb with this patch. Patch by Tong Shen. llvm-svn: 216409
2014-08-26 05:39:30 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
if (i == CFI_AUG_MAX_SIZE &&
cie_sp->augmentation[CFI_AUG_MAX_SIZE - 1] != '\0') {
Host::SystemLog(Host::eSystemLogError,
"CIE parse error: CIE augmentation string was too large "
"for the fixed sized buffer of %d bytes.\n",
CFI_AUG_MAX_SIZE);
return cie_sp;
}
cie_sp->code_align = (uint32_t)m_cfi_data.GetULEB128(&offset);
cie_sp->data_align = (int32_t)m_cfi_data.GetSLEB128(&offset);
cie_sp->return_addr_reg_num = m_cfi_data.GetU8(&offset);
if (cie_sp->augmentation[0]) {
// Get the length of the eh_frame augmentation data
// which starts with a ULEB128 length in bytes
const size_t aug_data_len = (size_t)m_cfi_data.GetULEB128(&offset);
const size_t aug_data_end = offset + aug_data_len;
const size_t aug_str_len = strlen(cie_sp->augmentation);
// A 'z' may be present as the first character of the string.
// If present, the Augmentation Data field shall be present.
// The contents of the Augmentation Data shall be interpreted
// according to other characters in the Augmentation String.
if (cie_sp->augmentation[0] == 'z') {
// Extract the Augmentation Data
size_t aug_str_idx = 0;
for (aug_str_idx = 1; aug_str_idx < aug_str_len; aug_str_idx++) {
char aug = cie_sp->augmentation[aug_str_idx];
switch (aug) {
case 'L':
// Indicates the presence of one argument in the
// Augmentation Data of the CIE, and a corresponding
// argument in the Augmentation Data of the FDE. The
// argument in the Augmentation Data of the CIE is
// 1-byte and represents the pointer encoding used
// for the argument in the Augmentation Data of the
// FDE, which is the address of a language-specific
// data area (LSDA). The size of the LSDA pointer is
// specified by the pointer encoding used.
cie_sp->lsda_addr_encoding = m_cfi_data.GetU8(&offset);
break;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case 'P':
// Indicates the presence of two arguments in the
// Augmentation Data of the CIE. The first argument
// is 1-byte and represents the pointer encoding
// used for the second argument, which is the
// address of a personality routine handler. The
// size of the personality routine pointer is
// specified by the pointer encoding used.
//
// The address of the personality function will
// be stored at this location. Pre-execution, it
// will be all zero's so don't read it until we're
// trying to do an unwind & the reloc has been
// resolved.
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
uint8_t arg_ptr_encoding = m_cfi_data.GetU8(&offset);
const lldb::addr_t pc_rel_addr = m_section_sp->GetFileAddress();
cie_sp->personality_loc = m_cfi_data.GetGNUEHPointer(
&offset, arg_ptr_encoding, pc_rel_addr, LLDB_INVALID_ADDRESS,
LLDB_INVALID_ADDRESS);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
break;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case 'R':
// A 'R' may be present at any position after the
// first character of the string. The Augmentation
// Data shall include a 1 byte argument that
// represents the pointer encoding for the address
// pointers used in the FDE.
// Example: 0x1B == DW_EH_PE_pcrel | DW_EH_PE_sdata4
cie_sp->ptr_encoding = m_cfi_data.GetU8(&offset);
break;
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
} else if (strcmp(cie_sp->augmentation, "eh") == 0) {
// If the Augmentation string has the value "eh", then
// the EH Data field shall be present
}
// Set the offset to be the end of the augmentation data just in case
// we didn't understand any of the data.
offset = (uint32_t)aug_data_end;
}
The first part of an lldb native stack unwinder. The Unwind and RegisterContext subclasses still need to be finished; none of this code is used by lldb at this point (unless you call into it by hand). The ObjectFile class now has an UnwindTable object. The UnwindTable object has a series of FuncUnwinders objects (Function Unwinders) -- one for each function in that ObjectFile we've backtraced through during this debug session. The FuncUnwinders object has a few different UnwindPlans. UnwindPlans are a generic way of describing how to find the canonical address of a given function's stack frame (the CFA idea from DWARF/eh_frame) and how to restore the caller frame's register values, if they have been saved by this function. UnwindPlans are created from different sources. One source is the eh_frame exception handling information generated by the compiler for unwinding an exception throw. Another source is an assembly language inspection class (UnwindAssemblyProfiler, uses the Plugin architecture) which looks at the instructions in the funciton prologue and describes the stack movements/register saves that are done. Two additional types of UnwindPlans that are worth noting are the "fast" stack UnwindPlan which is useful for making a first pass over a thread's stack, determining how many stack frames there are and retrieving the pc and CFA values for each frame (enough to create StackFrameIDs). Only a minimal set of registers is recovered during a fast stack walk. The final UnwindPlan is an architectural default unwind plan. These are provided by the ArchDefaultUnwindPlan class (which uses the plugin architecture). When no symbol/function address range can be found for a given pc value -- when we have no eh_frame information and when we don't have a start address so we can't examine the assembly language instrucitons -- we have to make a best guess about how to unwind. That's when we use the architectural default UnwindPlan. On x86_64, this would be to assume that rbp is used as a stack pointer and we can use that to find the caller's frame pointer and pc value. It's a last-ditch best guess about how to unwind out of a frame. There are heuristics about when to use one UnwindPlan versues the other -- this will all happen in the still-begin-written UnwindLLDB subclass of Unwind which runs the UnwindPlans. llvm-svn: 113581
2010-09-10 15:49:16 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
if (end_offset > offset) {
cie_sp->inst_offset = offset;
cie_sp->inst_length = end_offset - offset;
}
while (offset < end_offset) {
uint8_t inst = m_cfi_data.GetU8(&offset);
uint8_t primary_opcode = inst & 0xC0;
uint8_t extended_opcode = inst & 0x3F;
if (!HandleCommonDwarfOpcode(primary_opcode, extended_opcode,
cie_sp->data_align, offset,
cie_sp->initial_row))
break; // Stop if we hit an unrecognized opcode
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
return cie_sp;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
void DWARFCallFrameInfo::GetCFIData() {
if (m_cfi_data_initialized == false) {
Log *log(GetLogIfAllCategoriesSet(LIBLLDB_LOG_UNWIND));
if (log)
m_objfile.GetModule()->LogMessage(log, "Reading EH frame info");
m_objfile.ReadSectionData(m_section_sp.get(), m_cfi_data);
m_cfi_data_initialized = true;
}
Centralize the code the reads the CFI so that we always log. llvm-svn: 147330
2011-12-29 08:05:26 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// Scan through the eh_frame or debug_frame section looking for FDEs and noting
// the start/end addresses
// of the functions and a pointer back to the function's FDE for later
// expansion.
The first part of an lldb native stack unwinder. The Unwind and RegisterContext subclasses still need to be finished; none of this code is used by lldb at this point (unless you call into it by hand). The ObjectFile class now has an UnwindTable object. The UnwindTable object has a series of FuncUnwinders objects (Function Unwinders) -- one for each function in that ObjectFile we've backtraced through during this debug session. The FuncUnwinders object has a few different UnwindPlans. UnwindPlans are a generic way of describing how to find the canonical address of a given function's stack frame (the CFA idea from DWARF/eh_frame) and how to restore the caller frame's register values, if they have been saved by this function. UnwindPlans are created from different sources. One source is the eh_frame exception handling information generated by the compiler for unwinding an exception throw. Another source is an assembly language inspection class (UnwindAssemblyProfiler, uses the Plugin architecture) which looks at the instructions in the funciton prologue and describes the stack movements/register saves that are done. Two additional types of UnwindPlans that are worth noting are the "fast" stack UnwindPlan which is useful for making a first pass over a thread's stack, determining how many stack frames there are and retrieving the pc and CFA values for each frame (enough to create StackFrameIDs). Only a minimal set of registers is recovered during a fast stack walk. The final UnwindPlan is an architectural default unwind plan. These are provided by the ArchDefaultUnwindPlan class (which uses the plugin architecture). When no symbol/function address range can be found for a given pc value -- when we have no eh_frame information and when we don't have a start address so we can't examine the assembly language instrucitons -- we have to make a best guess about how to unwind. That's when we use the architectural default UnwindPlan. On x86_64, this would be to assume that rbp is used as a stack pointer and we can use that to find the caller's frame pointer and pc value. It's a last-ditch best guess about how to unwind out of a frame. There are heuristics about when to use one UnwindPlan versues the other -- this will all happen in the still-begin-written UnwindLLDB subclass of Unwind which runs the UnwindPlans. llvm-svn: 113581
2010-09-10 15:49:16 +08:00
// Internalize CIEs as we come across them.
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
void DWARFCallFrameInfo::GetFDEIndex() {
if (m_section_sp.get() == nullptr || m_section_sp->IsEncrypted())
return;
if (m_fde_index_initialized)
return;
std::lock_guard<std::mutex> guard(m_fde_index_mutex);
if (m_fde_index_initialized) // if two threads hit the locker
return;
Timer scoped_timer(LLVM_PRETTY_FUNCTION, "%s - %s", LLVM_PRETTY_FUNCTION,
m_objfile.GetFileSpec().GetFilename().AsCString(""));
bool clear_address_zeroth_bit = false;
ArchSpec arch;
if (m_objfile.GetArchitecture(arch)) {
if (arch.GetTriple().getArch() == llvm::Triple::arm ||
arch.GetTriple().getArch() == llvm::Triple::thumb)
clear_address_zeroth_bit = true;
}
lldb::offset_t offset = 0;
if (m_cfi_data_initialized == false)
GetCFIData();
while (m_cfi_data.ValidOffsetForDataOfSize(offset, 8)) {
const dw_offset_t current_entry = offset;
dw_offset_t cie_id, next_entry, cie_offset;
uint32_t len = m_cfi_data.GetU32(&offset);
bool is_64bit = (len == UINT32_MAX);
if (is_64bit) {
len = m_cfi_data.GetU64(&offset);
cie_id = m_cfi_data.GetU64(&offset);
next_entry = current_entry + len + 12;
cie_offset = current_entry + 12 - cie_id;
} else {
cie_id = m_cfi_data.GetU32(&offset);
next_entry = current_entry + len + 4;
cie_offset = current_entry + 4 - cie_id;
}
second pass over removal of Mutex and Condition llvm-svn: 270024
2016-05-19 13:13:57 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
if (next_entry > m_cfi_data.GetByteSize() + 1) {
Host::SystemLog(Host::eSystemLogError, "error: Invalid fde/cie next "
"entry offset of 0x%x found in "
"cie/fde at 0x%x\n",
next_entry, current_entry);
// Don't trust anything in this eh_frame section if we find blatantly
// invalid data.
m_fde_index.Clear();
m_fde_index_initialized = true;
return;
}
if (cie_offset > m_cfi_data.GetByteSize()) {
Host::SystemLog(
Host::eSystemLogError,
"error: Invalid cie offset of 0x%x found in cie/fde at 0x%x\n",
cie_offset, current_entry);
// Don't trust anything in this eh_frame section if we find blatantly
// invalid data.
m_fde_index.Clear();
m_fde_index_initialized = true;
return;
}
Add an unwind log Printf to note when an eh_frame section is loaded/parsed. Should add timers to this eventually. Delay getting a full UnwindPlan if it's possible to unwind with just a fast UnwindPlan. This keeps us from reading the eh_frame section unless we hit something built -fomit-frame pointer or we hit a frame with no symbol (read: no start address) available. It doesn't look like it is correctly falling back to using the full UnwindPlan to provide additional registers that the fast UnwindPlan doesn't supply; e.g. go to the middle of a stack and ask for r12 and it will show you the value of r12 in frame 0. That's a bug for tomorrow. llvm-svn: 117361
2010-10-26 20:01:35 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
if (cie_id == 0 || cie_id == UINT32_MAX || len == 0) {
m_cie_map[current_entry] = ParseCIE(current_entry);
offset = next_entry;
continue;
}
Change DWARFCallFrameInfo from using a vector of AddressRanges to track the EH FDEs for the functions in a module to using a RangeDataVector, a more light-weight data structure that only refers to File addresses. Makes the initial FDE scan about 3x faster, uses less memory. <rdar://problem/13465650> llvm-svn: 177585
2013-03-21 05:57:42 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
const CIE *cie = GetCIE(cie_offset);
if (cie) {
const lldb::addr_t pc_rel_addr = m_section_sp->GetFileAddress();
const lldb::addr_t text_addr = LLDB_INVALID_ADDRESS;
const lldb::addr_t data_addr = LLDB_INVALID_ADDRESS;
lldb::addr_t addr = m_cfi_data.GetGNUEHPointer(
&offset, cie->ptr_encoding, pc_rel_addr, text_addr, data_addr);
if (clear_address_zeroth_bit)
addr &= ~1ull;
lldb::addr_t length = m_cfi_data.GetGNUEHPointer(
&offset, cie->ptr_encoding & DW_EH_PE_MASK_ENCODING, pc_rel_addr,
text_addr, data_addr);
FDEEntryMap::Entry fde(addr, length, current_entry);
m_fde_index.Append(fde);
} else {
Host::SystemLog(Host::eSystemLogError, "error: unable to find CIE at "
"0x%8.8x for cie_id = 0x%8.8x for "
"entry at 0x%8.8x.\n",
cie_offset, cie_id, current_entry);
Add support for using armv7 compact unwind information as an asynchronous unwind plan source. Two small fixes to the compact unwind dumper tool for armv7 encodings. A change to DWARFCallFrameInfo to strip the 0th bit on addresses in eh_frame sections when armv7. In the clang generated examples I have, the 0th bit is set for thumb functions and that's causing the unwinder to pick the wrong function for eh_frame info. llvm-svn: 271970
2016-06-07 10:19:54 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
offset = next_entry;
}
m_fde_index.Sort();
m_fde_index_initialized = true;
}
Add support for using armv7 compact unwind information as an asynchronous unwind plan source. Two small fixes to the compact unwind dumper tool for armv7 encodings. A change to DWARFCallFrameInfo to strip the 0th bit on addresses in eh_frame sections when armv7. In the clang generated examples I have, the 0th bit is set for thumb functions and that's causing the unwinder to pick the wrong function for eh_frame info. llvm-svn: 271970
2016-06-07 10:19:54 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
bool DWARFCallFrameInfo::FDEToUnwindPlan(dw_offset_t dwarf_offset,
Address startaddr,
UnwindPlan &unwind_plan) {
Log *log = GetLogIfAllCategoriesSet(LIBLLDB_LOG_UNWIND);
lldb::offset_t offset = dwarf_offset;
lldb::offset_t current_entry = offset;
if (m_section_sp.get() == nullptr || m_section_sp->IsEncrypted())
return false;
if (m_cfi_data_initialized == false)
GetCFIData();
uint32_t length = m_cfi_data.GetU32(&offset);
dw_offset_t cie_offset;
bool is_64bit = (length == UINT32_MAX);
if (is_64bit) {
length = m_cfi_data.GetU64(&offset);
cie_offset = m_cfi_data.GetU64(&offset);
} else {
cie_offset = m_cfi_data.GetU32(&offset);
}
assert(cie_offset != 0 && cie_offset != UINT32_MAX);
// Translate the CIE_id from the eh_frame format, which
// is relative to the FDE offset, into a __eh_frame section
// offset
if (m_is_eh_frame) {
unwind_plan.SetSourceName("eh_frame CFI");
cie_offset = current_entry + (is_64bit ? 12 : 4) - cie_offset;
unwind_plan.SetUnwindPlanValidAtAllInstructions(eLazyBoolNo);
} else {
unwind_plan.SetSourceName("DWARF CFI");
// In theory the debug_frame info should be valid at all call sites
// ("asynchronous unwind info" as it is sometimes called) but in practice
// gcc et al all emit call frame info for the prologue and call sites, but
// not for the epilogue or all the other locations during the function
// reliably.
unwind_plan.SetUnwindPlanValidAtAllInstructions(eLazyBoolNo);
}
unwind_plan.SetSourcedFromCompiler(eLazyBoolYes);
const CIE *cie = GetCIE(cie_offset);
assert(cie != nullptr);
const dw_offset_t end_offset = current_entry + length + (is_64bit ? 12 : 4);
const lldb::addr_t pc_rel_addr = m_section_sp->GetFileAddress();
const lldb::addr_t text_addr = LLDB_INVALID_ADDRESS;
const lldb::addr_t data_addr = LLDB_INVALID_ADDRESS;
lldb::addr_t range_base = m_cfi_data.GetGNUEHPointer(
&offset, cie->ptr_encoding, pc_rel_addr, text_addr, data_addr);
lldb::addr_t range_len = m_cfi_data.GetGNUEHPointer(
&offset, cie->ptr_encoding & DW_EH_PE_MASK_ENCODING, pc_rel_addr,
text_addr, data_addr);
AddressRange range(range_base, m_objfile.GetAddressByteSize(),
m_objfile.GetSectionList());
range.SetByteSize(range_len);
addr_t lsda_data_file_address = LLDB_INVALID_ADDRESS;
if (cie->augmentation[0] == 'z') {
uint32_t aug_data_len = (uint32_t)m_cfi_data.GetULEB128(&offset);
if (aug_data_len != 0 && cie->lsda_addr_encoding != DW_EH_PE_omit) {
offset_t saved_offset = offset;
lsda_data_file_address = m_cfi_data.GetGNUEHPointer(
&offset, cie->lsda_addr_encoding, pc_rel_addr, text_addr, data_addr);
if (offset - saved_offset != aug_data_len) {
// There is more in the augmentation region than we know how to process;
// don't read anything.
lsda_data_file_address = LLDB_INVALID_ADDRESS;
}
offset = saved_offset;
}
offset += aug_data_len;
}
Address lsda_data;
Address personality_function_ptr;
if (lsda_data_file_address != LLDB_INVALID_ADDRESS &&
cie->personality_loc != LLDB_INVALID_ADDRESS) {
m_objfile.GetModule()->ResolveFileAddress(lsda_data_file_address,
lsda_data);
m_objfile.GetModule()->ResolveFileAddress(cie->personality_loc,
personality_function_ptr);
}
if (lsda_data.IsValid() && personality_function_ptr.IsValid()) {
unwind_plan.SetLSDAAddress(lsda_data);
unwind_plan.SetPersonalityFunctionPtr(personality_function_ptr);
}
uint32_t code_align = cie->code_align;
int32_t data_align = cie->data_align;
unwind_plan.SetPlanValidAddressRange(range);
UnwindPlan::Row *cie_initial_row = new UnwindPlan::Row;
*cie_initial_row = cie->initial_row;
UnwindPlan::RowSP row(cie_initial_row);
unwind_plan.SetRegisterKind(m_reg_kind);
unwind_plan.SetReturnAddressRegister(cie->return_addr_reg_num);
std::vector<UnwindPlan::RowSP> stack;
UnwindPlan::Row::RegisterLocation reg_location;
while (m_cfi_data.ValidOffset(offset) && offset < end_offset) {
uint8_t inst = m_cfi_data.GetU8(&offset);
uint8_t primary_opcode = inst & 0xC0;
uint8_t extended_opcode = inst & 0x3F;
if (!HandleCommonDwarfOpcode(primary_opcode, extended_opcode, data_align,
offset, *row)) {
if (primary_opcode) {
switch (primary_opcode) {
case DW_CFA_advance_loc: // (Row Creation Instruction)
{ // 0x40 - high 2 bits are 0x1, lower 6 bits are delta
// takes a single argument that represents a constant delta. The
// required action is to create a new table row with a location
// value that is computed by taking the current entry's location
// value and adding (delta * code_align). All other
// values in the new row are initially identical to the current row.
unwind_plan.AppendRow(row);
UnwindPlan::Row *newrow = new UnwindPlan::Row;
*newrow = *row.get();
row.reset(newrow);
row->SlideOffset(extended_opcode * code_align);
break;
Add 64-bit eh_frame section CFI support. In practice, 64bit eh_frame is not used even for x86_64 binaries. The main reason is in eh_frame we almost always use pc-relative addressing, so addresses are within 32bits and gcc just sticks to 32bit eh_frame. I generated 64bit eh_frame for Android Java runtime and unwind successfully in gdb, and in lldb with this patch. Patch by Tong Shen. llvm-svn: 216409
2014-08-26 05:39:30 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_restore: { // 0xC0 - high 2 bits are 0x3, lower 6 bits are
// register
// takes a single argument that represents a register number. The
// required action is to change the rule for the indicated register
// to the rule assigned it by the initial_instructions in the CIE.
uint32_t reg_num = extended_opcode;
// We only keep enough register locations around to
// unwind what is in our thread, and these are organized
// by the register index in that state, so we need to convert our
// eh_frame register number from the EH frame info, to a register
// index
if (unwind_plan.IsValidRowIndex(0) &&
unwind_plan.GetRowAtIndex(0)->GetRegisterInfo(reg_num,
reg_location))
row->SetRegisterInfo(reg_num, reg_location);
break;
}
}
} else {
switch (extended_opcode) {
case DW_CFA_set_loc: // 0x1 (Row Creation Instruction)
Add a tiny bit of hardening to the eh_frame and compact unwind parsing. When we're seeing offsets that exceed the size of our section, don't try to use that unwind info. <rdar://problem/20113673> llvm-svn: 233886
2015-04-02 12:35:32 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// DW_CFA_set_loc takes a single argument that represents an address.
// The required action is to create a new table row using the
// specified address as the location. All other values in the new row
// are initially identical to the current row. The new location value
// should always be greater than the current one.
unwind_plan.AppendRow(row);
UnwindPlan::Row *newrow = new UnwindPlan::Row;
*newrow = *row.get();
row.reset(newrow);
row->SetOffset(m_cfi_data.GetPointer(&offset) -
startaddr.GetFileAddress());
break;
Add a tiny bit of hardening to the eh_frame and compact unwind parsing. When we're seeing offsets that exceed the size of our section, don't try to use that unwind info. <rdar://problem/20113673> llvm-svn: 233886
2015-04-02 12:35:32 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_advance_loc1: // 0x2 (Row Creation Instruction)
Add a tiny bit of hardening to the eh_frame and compact unwind parsing. When we're seeing offsets that exceed the size of our section, don't try to use that unwind info. <rdar://problem/20113673> llvm-svn: 233886
2015-04-02 12:35:32 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// takes a single uword argument that represents a constant delta.
// This instruction is identical to DW_CFA_advance_loc except for the
// encoding and size of the delta argument.
unwind_plan.AppendRow(row);
UnwindPlan::Row *newrow = new UnwindPlan::Row;
*newrow = *row.get();
row.reset(newrow);
row->SlideOffset(m_cfi_data.GetU8(&offset) * code_align);
break;
Add a tiny bit of hardening to the eh_frame and compact unwind parsing. When we're seeing offsets that exceed the size of our section, don't try to use that unwind info. <rdar://problem/20113673> llvm-svn: 233886
2015-04-02 12:35:32 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_advance_loc2: // 0x3 (Row Creation Instruction)
The first part of an lldb native stack unwinder. The Unwind and RegisterContext subclasses still need to be finished; none of this code is used by lldb at this point (unless you call into it by hand). The ObjectFile class now has an UnwindTable object. The UnwindTable object has a series of FuncUnwinders objects (Function Unwinders) -- one for each function in that ObjectFile we've backtraced through during this debug session. The FuncUnwinders object has a few different UnwindPlans. UnwindPlans are a generic way of describing how to find the canonical address of a given function's stack frame (the CFA idea from DWARF/eh_frame) and how to restore the caller frame's register values, if they have been saved by this function. UnwindPlans are created from different sources. One source is the eh_frame exception handling information generated by the compiler for unwinding an exception throw. Another source is an assembly language inspection class (UnwindAssemblyProfiler, uses the Plugin architecture) which looks at the instructions in the funciton prologue and describes the stack movements/register saves that are done. Two additional types of UnwindPlans that are worth noting are the "fast" stack UnwindPlan which is useful for making a first pass over a thread's stack, determining how many stack frames there are and retrieving the pc and CFA values for each frame (enough to create StackFrameIDs). Only a minimal set of registers is recovered during a fast stack walk. The final UnwindPlan is an architectural default unwind plan. These are provided by the ArchDefaultUnwindPlan class (which uses the plugin architecture). When no symbol/function address range can be found for a given pc value -- when we have no eh_frame information and when we don't have a start address so we can't examine the assembly language instrucitons -- we have to make a best guess about how to unwind. That's when we use the architectural default UnwindPlan. On x86_64, this would be to assume that rbp is used as a stack pointer and we can use that to find the caller's frame pointer and pc value. It's a last-ditch best guess about how to unwind out of a frame. There are heuristics about when to use one UnwindPlan versues the other -- this will all happen in the still-begin-written UnwindLLDB subclass of Unwind which runs the UnwindPlans. llvm-svn: 113581
2010-09-10 15:49:16 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// takes a single uword argument that represents a constant delta.
// This instruction is identical to DW_CFA_advance_loc except for the
// encoding and size of the delta argument.
unwind_plan.AppendRow(row);
UnwindPlan::Row *newrow = new UnwindPlan::Row;
*newrow = *row.get();
row.reset(newrow);
row->SlideOffset(m_cfi_data.GetU16(&offset) * code_align);
break;
The first part of an lldb native stack unwinder. The Unwind and RegisterContext subclasses still need to be finished; none of this code is used by lldb at this point (unless you call into it by hand). The ObjectFile class now has an UnwindTable object. The UnwindTable object has a series of FuncUnwinders objects (Function Unwinders) -- one for each function in that ObjectFile we've backtraced through during this debug session. The FuncUnwinders object has a few different UnwindPlans. UnwindPlans are a generic way of describing how to find the canonical address of a given function's stack frame (the CFA idea from DWARF/eh_frame) and how to restore the caller frame's register values, if they have been saved by this function. UnwindPlans are created from different sources. One source is the eh_frame exception handling information generated by the compiler for unwinding an exception throw. Another source is an assembly language inspection class (UnwindAssemblyProfiler, uses the Plugin architecture) which looks at the instructions in the funciton prologue and describes the stack movements/register saves that are done. Two additional types of UnwindPlans that are worth noting are the "fast" stack UnwindPlan which is useful for making a first pass over a thread's stack, determining how many stack frames there are and retrieving the pc and CFA values for each frame (enough to create StackFrameIDs). Only a minimal set of registers is recovered during a fast stack walk. The final UnwindPlan is an architectural default unwind plan. These are provided by the ArchDefaultUnwindPlan class (which uses the plugin architecture). When no symbol/function address range can be found for a given pc value -- when we have no eh_frame information and when we don't have a start address so we can't examine the assembly language instrucitons -- we have to make a best guess about how to unwind. That's when we use the architectural default UnwindPlan. On x86_64, this would be to assume that rbp is used as a stack pointer and we can use that to find the caller's frame pointer and pc value. It's a last-ditch best guess about how to unwind out of a frame. There are heuristics about when to use one UnwindPlan versues the other -- this will all happen in the still-begin-written UnwindLLDB subclass of Unwind which runs the UnwindPlans. llvm-svn: 113581
2010-09-10 15:49:16 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_advance_loc4: // 0x4 (Row Creation Instruction)
Improved the packet throughput when debugging with GDB remote by over 3x on darwin (not sure about other platforms). Modified the communication and connection classes to not require the BytesAvailable function. Now the "Read(...)" function has a timeout in microseconds. Fixed a lot of assertions that were firing off in certain cases and replaced them with error output and code that can deal with the assertion case. llvm-svn: 133224
2011-06-17 09:22:15 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// takes a single uword argument that represents a constant delta.
// This instruction is identical to DW_CFA_advance_loc except for the
// encoding and size of the delta argument.
unwind_plan.AppendRow(row);
UnwindPlan::Row *newrow = new UnwindPlan::Row;
*newrow = *row.get();
row.reset(newrow);
row->SlideOffset(m_cfi_data.GetU32(&offset) * code_align);
break;
}
Improved the packet throughput when debugging with GDB remote by over 3x on darwin (not sure about other platforms). Modified the communication and connection classes to not require the BytesAvailable function. Now the "Read(...)" function has a timeout in microseconds. Fixed a lot of assertions that were firing off in certain cases and replaced them with error output and code that can deal with the assertion case. llvm-svn: 133224
2011-06-17 09:22:15 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_restore_extended: // 0x6
{
// takes a single unsigned LEB128 argument that represents a register
// number. This instruction is identical to DW_CFA_restore except for
// the encoding and size of the register argument.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
if (unwind_plan.IsValidRowIndex(0) &&
unwind_plan.GetRowAtIndex(0)->GetRegisterInfo(reg_num,
reg_location))
row->SetRegisterInfo(reg_num, reg_location);
break;
}
Add support for using armv7 compact unwind information as an asynchronous unwind plan source. Two small fixes to the compact unwind dumper tool for armv7 encodings. A change to DWARFCallFrameInfo to strip the 0th bit on addresses in eh_frame sections when armv7. In the clang generated examples I have, the 0th bit is set for thumb functions and that's causing the unwinder to pick the wrong function for eh_frame info. llvm-svn: 271970
2016-06-07 10:19:54 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_remember_state: // 0xA
{
// These instructions define a stack of information. Encountering the
// DW_CFA_remember_state instruction means to save the rules for every
// register on the current row on the stack. Encountering the
// DW_CFA_restore_state instruction means to pop the set of rules off
// the stack and place them in the current row. (This operation is
// useful for compilers that move epilogue code into the body of a
// function.)
stack.push_back(row);
UnwindPlan::Row *newrow = new UnwindPlan::Row;
*newrow = *row.get();
row.reset(newrow);
break;
Improved the packet throughput when debugging with GDB remote by over 3x on darwin (not sure about other platforms). Modified the communication and connection classes to not require the BytesAvailable function. Now the "Read(...)" function has a timeout in microseconds. Fixed a lot of assertions that were firing off in certain cases and replaced them with error output and code that can deal with the assertion case. llvm-svn: 133224
2011-06-17 09:22:15 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_restore_state: // 0xB
Improved the packet throughput when debugging with GDB remote by over 3x on darwin (not sure about other platforms). Modified the communication and connection classes to not require the BytesAvailable function. Now the "Read(...)" function has a timeout in microseconds. Fixed a lot of assertions that were firing off in certain cases and replaced them with error output and code that can deal with the assertion case. llvm-svn: 133224
2011-06-17 09:22:15 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// These instructions define a stack of information. Encountering the
// DW_CFA_remember_state instruction means to save the rules for every
// register on the current row on the stack. Encountering the
// DW_CFA_restore_state instruction means to pop the set of rules off
// the stack and place them in the current row. (This operation is
// useful for compilers that move epilogue code into the body of a
// function.)
if (stack.empty()) {
if (log)
log->Printf("DWARFCallFrameInfo::%s(dwarf_offset: %" PRIx32
", startaddr: %" PRIx64
" encountered DW_CFA_restore_state but state stack "
"is empty. Corrupt unwind info?",
__FUNCTION__, dwarf_offset,
startaddr.GetFileAddress());
break;
}
lldb::addr_t offset = row->GetOffset();
row = stack.back();
stack.pop_back();
row->SetOffset(offset);
break;
Improved the packet throughput when debugging with GDB remote by over 3x on darwin (not sure about other platforms). Modified the communication and connection classes to not require the BytesAvailable function. Now the "Read(...)" function has a timeout in microseconds. Fixed a lot of assertions that were firing off in certain cases and replaced them with error output and code that can deal with the assertion case. llvm-svn: 133224
2011-06-17 09:22:15 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_GNU_args_size: // 0x2e
{
// The DW_CFA_GNU_args_size instruction takes an unsigned LEB128
// operand
// representing an argument size. This instruction specifies the total
// of
// the size of the arguments which have been pushed onto the stack.
// TODO: Figure out how we should handle this.
m_cfi_data.GetULEB128(&offset);
break;
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_val_offset: // 0x14
case DW_CFA_val_offset_sf: // 0x15
default:
break;
}
}
}
}
unwind_plan.AppendRow(row);
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
return true;
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
bool DWARFCallFrameInfo::HandleCommonDwarfOpcode(uint8_t primary_opcode,
uint8_t extended_opcode,
int32_t data_align,
lldb::offset_t &offset,
UnwindPlan::Row &row) {
UnwindPlan::Row::RegisterLocation reg_location;
if (primary_opcode) {
switch (primary_opcode) {
case DW_CFA_offset: { // 0x80 - high 2 bits are 0x2, lower 6 bits are
// register
// takes two arguments: an unsigned LEB128 constant representing a
// factored offset and a register number. The required action is to
// change the rule for the register indicated by the register number
// to be an offset(N) rule with a value of
// (N = factored offset * data_align).
uint8_t reg_num = extended_opcode;
int32_t op_offset = (int32_t)m_cfi_data.GetULEB128(&offset) * data_align;
reg_location.SetAtCFAPlusOffset(op_offset);
row.SetRegisterInfo(reg_num, reg_location);
return true;
Add 64-bit eh_frame section CFI support. In practice, 64bit eh_frame is not used even for x86_64 binaries. The main reason is in eh_frame we almost always use pc-relative addressing, so addresses are within 32bits and gcc just sticks to 32bit eh_frame. I generated 64bit eh_frame for Android Java runtime and unwind successfully in gdb, and in lldb with this patch. Patch by Tong Shen. llvm-svn: 216409
2014-08-26 05:39:30 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
}
} else {
switch (extended_opcode) {
case DW_CFA_nop: // 0x0
return true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_offset_extended: // 0x5
Check in the native lldb unwinder. Not yet enabled as the default unwinder but there are no known backtrace problems with the code at this point. Added 'log enable lldb unwind' to help diagnose backtrace problems; this output needs a little refining but it's a good first step. eh_frame information is currently read unconditionally - the code is structured to allow this to be delayed until it's actually needed. There is a performance hit when you have to parse the eh_frame information for any largeish executable/library so it's necessary to avoid if possible. It's confusing having both the UnwindPlan::RegisterLocation struct and the RegisterConextLLDB::RegisterLocation struct, I need to rename one of them. The writing of registers isn't done in the RegisterConextLLDB subclass yet; neither is the running of complex DWARF expressions from eh_frame (e.g. used for _sigtramp on Mac OS X). llvm-svn: 117256
2010-10-25 19:12:07 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// takes two unsigned LEB128 arguments representing a register number
// and a factored offset. This instruction is identical to DW_CFA_offset
// except for the encoding and size of the register argument.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
int32_t op_offset = (int32_t)m_cfi_data.GetULEB128(&offset) * data_align;
UnwindPlan::Row::RegisterLocation reg_location;
reg_location.SetAtCFAPlusOffset(op_offset);
row.SetRegisterInfo(reg_num, reg_location);
return true;
Check in the native lldb unwinder. Not yet enabled as the default unwinder but there are no known backtrace problems with the code at this point. Added 'log enable lldb unwind' to help diagnose backtrace problems; this output needs a little refining but it's a good first step. eh_frame information is currently read unconditionally - the code is structured to allow this to be delayed until it's actually needed. There is a performance hit when you have to parse the eh_frame information for any largeish executable/library so it's necessary to avoid if possible. It's confusing having both the UnwindPlan::RegisterLocation struct and the RegisterConextLLDB::RegisterLocation struct, I need to rename one of them. The writing of registers isn't done in the RegisterConextLLDB subclass yet; neither is the running of complex DWARF expressions from eh_frame (e.g. used for _sigtramp on Mac OS X). llvm-svn: 117256
2010-10-25 19:12:07 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_undefined: // 0x7
Check in the native lldb unwinder. Not yet enabled as the default unwinder but there are no known backtrace problems with the code at this point. Added 'log enable lldb unwind' to help diagnose backtrace problems; this output needs a little refining but it's a good first step. eh_frame information is currently read unconditionally - the code is structured to allow this to be delayed until it's actually needed. There is a performance hit when you have to parse the eh_frame information for any largeish executable/library so it's necessary to avoid if possible. It's confusing having both the UnwindPlan::RegisterLocation struct and the RegisterConextLLDB::RegisterLocation struct, I need to rename one of them. The writing of registers isn't done in the RegisterConextLLDB subclass yet; neither is the running of complex DWARF expressions from eh_frame (e.g. used for _sigtramp on Mac OS X). llvm-svn: 117256
2010-10-25 19:12:07 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// takes a single unsigned LEB128 argument that represents a register
// number. The required action is to set the rule for the specified
// register to undefined.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
UnwindPlan::Row::RegisterLocation reg_location;
reg_location.SetUndefined();
row.SetRegisterInfo(reg_num, reg_location);
return true;
Check in the native lldb unwinder. Not yet enabled as the default unwinder but there are no known backtrace problems with the code at this point. Added 'log enable lldb unwind' to help diagnose backtrace problems; this output needs a little refining but it's a good first step. eh_frame information is currently read unconditionally - the code is structured to allow this to be delayed until it's actually needed. There is a performance hit when you have to parse the eh_frame information for any largeish executable/library so it's necessary to avoid if possible. It's confusing having both the UnwindPlan::RegisterLocation struct and the RegisterConextLLDB::RegisterLocation struct, I need to rename one of them. The writing of registers isn't done in the RegisterConextLLDB subclass yet; neither is the running of complex DWARF expressions from eh_frame (e.g. used for _sigtramp on Mac OS X). llvm-svn: 117256
2010-10-25 19:12:07 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_same_value: // 0x8
The first part of an lldb native stack unwinder. The Unwind and RegisterContext subclasses still need to be finished; none of this code is used by lldb at this point (unless you call into it by hand). The ObjectFile class now has an UnwindTable object. The UnwindTable object has a series of FuncUnwinders objects (Function Unwinders) -- one for each function in that ObjectFile we've backtraced through during this debug session. The FuncUnwinders object has a few different UnwindPlans. UnwindPlans are a generic way of describing how to find the canonical address of a given function's stack frame (the CFA idea from DWARF/eh_frame) and how to restore the caller frame's register values, if they have been saved by this function. UnwindPlans are created from different sources. One source is the eh_frame exception handling information generated by the compiler for unwinding an exception throw. Another source is an assembly language inspection class (UnwindAssemblyProfiler, uses the Plugin architecture) which looks at the instructions in the funciton prologue and describes the stack movements/register saves that are done. Two additional types of UnwindPlans that are worth noting are the "fast" stack UnwindPlan which is useful for making a first pass over a thread's stack, determining how many stack frames there are and retrieving the pc and CFA values for each frame (enough to create StackFrameIDs). Only a minimal set of registers is recovered during a fast stack walk. The final UnwindPlan is an architectural default unwind plan. These are provided by the ArchDefaultUnwindPlan class (which uses the plugin architecture). When no symbol/function address range can be found for a given pc value -- when we have no eh_frame information and when we don't have a start address so we can't examine the assembly language instrucitons -- we have to make a best guess about how to unwind. That's when we use the architectural default UnwindPlan. On x86_64, this would be to assume that rbp is used as a stack pointer and we can use that to find the caller's frame pointer and pc value. It's a last-ditch best guess about how to unwind out of a frame. There are heuristics about when to use one UnwindPlan versues the other -- this will all happen in the still-begin-written UnwindLLDB subclass of Unwind which runs the UnwindPlans. llvm-svn: 113581
2010-09-10 15:49:16 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// takes a single unsigned LEB128 argument that represents a register
// number. The required action is to set the rule for the specified
// register to same value.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
UnwindPlan::Row::RegisterLocation reg_location;
reg_location.SetSame();
row.SetRegisterInfo(reg_num, reg_location);
return true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Read the LSDA and Personality Routine function address out of the eh_frame data. These two pieces of information are used in the process of exception handler unwinding on SysV ABI systems. This patch reads the data from the eh_frame section (DWARFCallFrameInfo.cpp), allows for it to be saved & read out of a given UnwindPlan (UnwindPlan.h, UnwindPlan.cpp) - as well as printing the information in the UnwindPlan::Dump method - and adds methods to the FuncUnwinders object so that higher levels can query if a given function has an LSDA / personality routine defined. It's only lightly tested, but seems to be working correctly as long as your have this information in eh_frame. Does not address getting this information from compact unwind yet on Darwin systems. <rdar://problem/18742797> llvm-svn: 222214
2014-11-18 10:27:42 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_register: // 0x9
Read the LSDA and Personality Routine function address out of the eh_frame data. These two pieces of information are used in the process of exception handler unwinding on SysV ABI systems. This patch reads the data from the eh_frame section (DWARFCallFrameInfo.cpp), allows for it to be saved & read out of a given UnwindPlan (UnwindPlan.h, UnwindPlan.cpp) - as well as printing the information in the UnwindPlan::Dump method - and adds methods to the FuncUnwinders object so that higher levels can query if a given function has an LSDA / personality routine defined. It's only lightly tested, but seems to be working correctly as long as your have this information in eh_frame. Does not address getting this information from compact unwind yet on Darwin systems. <rdar://problem/18742797> llvm-svn: 222214
2014-11-18 10:27:42 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// takes two unsigned LEB128 arguments representing register numbers.
// The required action is to set the rule for the first register to be
// the second register.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
uint32_t other_reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
UnwindPlan::Row::RegisterLocation reg_location;
reg_location.SetInRegister(other_reg_num);
row.SetRegisterInfo(reg_num, reg_location);
return true;
Read the LSDA and Personality Routine function address out of the eh_frame data. These two pieces of information are used in the process of exception handler unwinding on SysV ABI systems. This patch reads the data from the eh_frame section (DWARFCallFrameInfo.cpp), allows for it to be saved & read out of a given UnwindPlan (UnwindPlan.h, UnwindPlan.cpp) - as well as printing the information in the UnwindPlan::Dump method - and adds methods to the FuncUnwinders object so that higher levels can query if a given function has an LSDA / personality routine defined. It's only lightly tested, but seems to be working correctly as long as your have this information in eh_frame. Does not address getting this information from compact unwind yet on Darwin systems. <rdar://problem/18742797> llvm-svn: 222214
2014-11-18 10:27:42 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_def_cfa: // 0xC (CFA Definition Instruction)
Read the LSDA and Personality Routine function address out of the eh_frame data. These two pieces of information are used in the process of exception handler unwinding on SysV ABI systems. This patch reads the data from the eh_frame section (DWARFCallFrameInfo.cpp), allows for it to be saved & read out of a given UnwindPlan (UnwindPlan.h, UnwindPlan.cpp) - as well as printing the information in the UnwindPlan::Dump method - and adds methods to the FuncUnwinders object so that higher levels can query if a given function has an LSDA / personality routine defined. It's only lightly tested, but seems to be working correctly as long as your have this information in eh_frame. Does not address getting this information from compact unwind yet on Darwin systems. <rdar://problem/18742797> llvm-svn: 222214
2014-11-18 10:27:42 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// Takes two unsigned LEB128 operands representing a register
// number and a (non-factored) offset. The required action
// is to define the current CFA rule to use the provided
// register and offset.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
int32_t op_offset = (int32_t)m_cfi_data.GetULEB128(&offset);
row.GetCFAValue().SetIsRegisterPlusOffset(reg_num, op_offset);
return true;
Read the LSDA and Personality Routine function address out of the eh_frame data. These two pieces of information are used in the process of exception handler unwinding on SysV ABI systems. This patch reads the data from the eh_frame section (DWARFCallFrameInfo.cpp), allows for it to be saved & read out of a given UnwindPlan (UnwindPlan.h, UnwindPlan.cpp) - as well as printing the information in the UnwindPlan::Dump method - and adds methods to the FuncUnwinders object so that higher levels can query if a given function has an LSDA / personality routine defined. It's only lightly tested, but seems to be working correctly as long as your have this information in eh_frame. Does not address getting this information from compact unwind yet on Darwin systems. <rdar://problem/18742797> llvm-svn: 222214
2014-11-18 10:27:42 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_def_cfa_register: // 0xD (CFA Definition Instruction)
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// takes a single unsigned LEB128 argument representing a register
// number. The required action is to define the current CFA rule to
// use the provided register (but to keep the old offset).
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
row.GetCFAValue().SetIsRegisterPlusOffset(reg_num,
row.GetCFAValue().GetOffset());
return true;
Improve DWARF CFI CIE parsing and remove duplicated code Previously we handled only a few opcode DWARF CFI opcode when we were parsing the CIE. With this change we use mostly the same code what we use for parsing the PDE which cover more opcode. Differential revision: http://reviews.llvm.org/D10866 llvm-svn: 241332
2015-07-03 17:30:17 +08:00
}
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_def_cfa_offset: // 0xE (CFA Definition Instruction)
Improve DWARF CFI CIE parsing and remove duplicated code Previously we handled only a few opcode DWARF CFI opcode when we were parsing the CIE. With this change we use mostly the same code what we use for parsing the PDE which cover more opcode. Differential revision: http://reviews.llvm.org/D10866 llvm-svn: 241332
2015-07-03 17:30:17 +08:00
{
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
// Takes a single unsigned LEB128 operand representing a
// (non-factored) offset. The required action is to define
// the current CFA rule to use the provided offset (but
// to keep the old register).
int32_t op_offset = (int32_t)m_cfi_data.GetULEB128(&offset);
row.GetCFAValue().SetIsRegisterPlusOffset(
row.GetCFAValue().GetRegisterNumber(), op_offset);
return true;
Improve DWARF CFI CIE parsing and remove duplicated code Previously we handled only a few opcode DWARF CFI opcode when we were parsing the CIE. With this change we use mostly the same code what we use for parsing the PDE which cover more opcode. Differential revision: http://reviews.llvm.org/D10866 llvm-svn: 241332
2015-07-03 17:30:17 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_def_cfa_expression: // 0xF (CFA Definition Instruction)
{
size_t block_len = (size_t)m_cfi_data.GetULEB128(&offset);
const uint8_t *block_data =
static_cast<const uint8_t *>(m_cfi_data.GetData(&offset, block_len));
row.GetCFAValue().SetIsDWARFExpression(block_data, block_len);
return true;
}
Improve DWARF CFI CIE parsing and remove duplicated code Previously we handled only a few opcode DWARF CFI opcode when we were parsing the CIE. With this change we use mostly the same code what we use for parsing the PDE which cover more opcode. Differential revision: http://reviews.llvm.org/D10866 llvm-svn: 241332
2015-07-03 17:30:17 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_expression: // 0x10
{
// Takes two operands: an unsigned LEB128 value representing
// a register number, and a DW_FORM_block value representing a DWARF
// expression. The required action is to change the rule for the
// register indicated by the register number to be an expression(E)
// rule where E is the DWARF expression. That is, the DWARF
// expression computes the address. The value of the CFA is
// pushed on the DWARF evaluation stack prior to execution of
// the DWARF expression.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
uint32_t block_len = (uint32_t)m_cfi_data.GetULEB128(&offset);
const uint8_t *block_data =
static_cast<const uint8_t *>(m_cfi_data.GetData(&offset, block_len));
UnwindPlan::Row::RegisterLocation reg_location;
reg_location.SetAtDWARFExpression(block_data, block_len);
row.SetRegisterInfo(reg_num, reg_location);
return true;
}
Improve DWARF CFI CIE parsing and remove duplicated code Previously we handled only a few opcode DWARF CFI opcode when we were parsing the CIE. With this change we use mostly the same code what we use for parsing the PDE which cover more opcode. Differential revision: http://reviews.llvm.org/D10866 llvm-svn: 241332
2015-07-03 17:30:17 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_offset_extended_sf: // 0x11
{
// takes two operands: an unsigned LEB128 value representing a
// register number and a signed LEB128 factored offset. This
// instruction is identical to DW_CFA_offset_extended except
// that the second operand is signed and factored.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
int32_t op_offset = (int32_t)m_cfi_data.GetSLEB128(&offset) * data_align;
UnwindPlan::Row::RegisterLocation reg_location;
reg_location.SetAtCFAPlusOffset(op_offset);
row.SetRegisterInfo(reg_num, reg_location);
return true;
}
Improve DWARF CFI CIE parsing and remove duplicated code Previously we handled only a few opcode DWARF CFI opcode when we were parsing the CIE. With this change we use mostly the same code what we use for parsing the PDE which cover more opcode. Differential revision: http://reviews.llvm.org/D10866 llvm-svn: 241332
2015-07-03 17:30:17 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_def_cfa_sf: // 0x12 (CFA Definition Instruction)
{
// Takes two operands: an unsigned LEB128 value representing
// a register number and a signed LEB128 factored offset.
// This instruction is identical to DW_CFA_def_cfa except
// that the second operand is signed and factored.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
int32_t op_offset = (int32_t)m_cfi_data.GetSLEB128(&offset) * data_align;
row.GetCFAValue().SetIsRegisterPlusOffset(reg_num, op_offset);
return true;
}
Improve DWARF CFI CIE parsing and remove duplicated code Previously we handled only a few opcode DWARF CFI opcode when we were parsing the CIE. With this change we use mostly the same code what we use for parsing the PDE which cover more opcode. Differential revision: http://reviews.llvm.org/D10866 llvm-svn: 241332
2015-07-03 17:30:17 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_def_cfa_offset_sf: // 0x13 (CFA Definition Instruction)
{
// takes a signed LEB128 operand representing a factored
// offset. This instruction is identical to DW_CFA_def_cfa_offset
// except that the operand is signed and factored.
int32_t op_offset = (int32_t)m_cfi_data.GetSLEB128(&offset) * data_align;
uint32_t cfa_regnum = row.GetCFAValue().GetRegisterNumber();
row.GetCFAValue().SetIsRegisterPlusOffset(cfa_regnum, op_offset);
return true;
}
Improve DWARF CFI CIE parsing and remove duplicated code Previously we handled only a few opcode DWARF CFI opcode when we were parsing the CIE. With this change we use mostly the same code what we use for parsing the PDE which cover more opcode. Differential revision: http://reviews.llvm.org/D10866 llvm-svn: 241332
2015-07-03 17:30:17 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
case DW_CFA_val_expression: // 0x16
{
// takes two operands: an unsigned LEB128 value representing a register
// number, and a DW_FORM_block value representing a DWARF expression.
// The required action is to change the rule for the register indicated
// by the register number to be a val_expression(E) rule where E is the
// DWARF expression. That is, the DWARF expression computes the value of
// the given register. The value of the CFA is pushed on the DWARF
// evaluation stack prior to execution of the DWARF expression.
uint32_t reg_num = (uint32_t)m_cfi_data.GetULEB128(&offset);
uint32_t block_len = (uint32_t)m_cfi_data.GetULEB128(&offset);
const uint8_t *block_data =
(const uint8_t *)m_cfi_data.GetData(&offset, block_len);
//#if defined(__i386__) || defined(__x86_64__)
// // The EH frame info for EIP and RIP contains code that
// looks for traps to
// // be a specific type and increments the PC.
// // For i386:
// // DW_CFA_val_expression where:
// // eip = DW_OP_breg6(+28), DW_OP_deref, DW_OP_dup,
// DW_OP_plus_uconst(0x34),
// // DW_OP_deref, DW_OP_swap, DW_OP_plus_uconst(0),
// DW_OP_deref,
// // DW_OP_dup, DW_OP_lit3, DW_OP_ne, DW_OP_swap,
// DW_OP_lit4, DW_OP_ne,
// // DW_OP_and, DW_OP_plus
// // This basically does a:
// // eip = ucontenxt.mcontext32->gpr.eip;
// // if (ucontenxt.mcontext32->exc.trapno != 3 &&
// ucontenxt.mcontext32->exc.trapno != 4)
// // eip++;
// //
// // For x86_64:
// // DW_CFA_val_expression where:
// // rip = DW_OP_breg3(+48), DW_OP_deref, DW_OP_dup,
// DW_OP_plus_uconst(0x90), DW_OP_deref,
// // DW_OP_swap, DW_OP_plus_uconst(0),
// DW_OP_deref_size(4), DW_OP_dup, DW_OP_lit3,
// // DW_OP_ne, DW_OP_swap, DW_OP_lit4, DW_OP_ne,
// DW_OP_and, DW_OP_plus
// // This basically does a:
// // rip = ucontenxt.mcontext64->gpr.rip;
// // if (ucontenxt.mcontext64->exc.trapno != 3 &&
// ucontenxt.mcontext64->exc.trapno != 4)
// // rip++;
// // The trap comparisons and increments are not needed as
// it hoses up the unwound PC which
// // is expected to point at least past the instruction that
// causes the fault/trap. So we
// // take it out by trimming the expression right at the
// first "DW_OP_swap" opcodes
// if (block_data != NULL && thread->GetPCRegNum(Thread::GCC)
// == reg_num)
// {
// if (thread->Is64Bit())
// {
// if (block_len > 9 && block_data[8] == DW_OP_swap
// && block_data[9] == DW_OP_plus_uconst)
// block_len = 8;
// }
// else
// {
// if (block_len > 8 && block_data[7] == DW_OP_swap
// && block_data[8] == DW_OP_plus_uconst)
// block_len = 7;
// }
// }
//#endif
reg_location.SetIsDWARFExpression(block_data, block_len);
row.SetRegisterInfo(reg_num, reg_location);
return true;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
}
}
return false;
Initial checkin of lldb code from internal Apple repo. llvm-svn: 105619
2010-06-09 00:52:24 +08:00
}
Improve the handling of missing elf symtab and missing symbol sizes * Generate artificial symbol names from eh_fame during symbol parsing so these symbols are already present when we calcualte the size of the symbols where 0 is specified. * Fix symbol size calculation for the last symbol in the file where it have to last until the end of the parent section. This is the re-commit of the original change after fixing some test failures on OSX. Differential revision: http://reviews.llvm.org/D16996 llvm-svn: 261205
2016-02-18 19:12:18 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
void DWARFCallFrameInfo::ForEachFDEEntries(
const std::function<bool(lldb::addr_t, uint32_t, dw_offset_t)> &callback) {
GetFDEIndex();
Improve the handling of missing elf symtab and missing symbol sizes * Generate artificial symbol names from eh_fame during symbol parsing so these symbols are already present when we calcualte the size of the symbols where 0 is specified. * Fix symbol size calculation for the last symbol in the file where it have to last until the end of the parent section. This is the re-commit of the original change after fixing some test failures on OSX. Differential revision: http://reviews.llvm.org/D16996 llvm-svn: 261205
2016-02-18 19:12:18 +08:00
*** This commit represents a complete reformatting of the LLDB source code *** to conform to clang-format’s LLVM style. This kind of mass change has *** two obvious implications: Firstly, merging this particular commit into a downstream fork may be a huge effort. Alternatively, it may be worth merging all changes up to this commit, performing the same reformatting operation locally, and then discarding the merge for this particular commit. The commands used to accomplish this reformatting were as follows (with current working directory as the root of the repository): find . \( -iname "*.c" -or -iname "*.cpp" -or -iname "*.h" -or -iname "*.mm" \) -exec clang-format -i {} + find . -iname "*.py" -exec autopep8 --in-place --aggressive --aggressive {} + ; The version of clang-format used was 3.9.0, and autopep8 was 1.2.4. Secondly, “blame” style tools will generally point to this commit instead of a meaningful prior commit. There are alternatives available that will attempt to look through this change and find the appropriate prior commit. YMMV. llvm-svn: 280751
2016-09-07 04:57:50 +08:00
for (size_t i = 0, c = m_fde_index.GetSize(); i < c; ++i) {
const FDEEntryMap::Entry &entry = m_fde_index.GetEntryRef(i);
if (!callback(entry.base, entry.size, entry.data))
break;
}
Improve the handling of missing elf symtab and missing symbol sizes * Generate artificial symbol names from eh_fame during symbol parsing so these symbols are already present when we calcualte the size of the symbols where 0 is specified. * Fix symbol size calculation for the last symbol in the file where it have to last until the end of the parent section. This is the re-commit of the original change after fixing some test failures on OSX. Differential revision: http://reviews.llvm.org/D16996 llvm-svn: 261205
2016-02-18 19:12:18 +08:00
}