获取包括共享库的 C++ 应用程序的调用堆栈
get callstack of c++ application including shared libraries
我用 c++ 编写了一个小函数来创建调用堆栈，使用 bfd 解析地址。它工作正常，我获得了当前应用程序中所有函数的详细信息（源文件和行），但我没有得到关于我的应用程序中包含的共享库的任何信息。
例如：
callstack:
[0x00002b54229ba6d3 .none] <not sectioned address>
[0x00002b5422927907 .none] <not sectioned address>
[0x00002b54229286d0 .none] <not sectioned address>
[0x00000000004f8608 .text] tensorNetwork.hxx:63 (inside operator())
[0x00000000005528da .text] /usr/include/c++/4.8/functional:2058 (inside _M_invoke)
[0x000000000058231c .text] /usr/include/c++/4.8/functional:2469 (inside std::function<bool ()>::operator()() const)
[0x00000000005806c0 .text] test.cpp:26 (inside ___test(std::pair<std::string, std::function<bool ()> > const&))
[0x0000000000581693 .text] test.cpp:119 (inside main)
[0x00002b5423fdebe5 .none] <not sectioned address>
[0x000000000042c129 .text] /home/abuild/rpmbuild/BUILD/glibc-2.18/csu/../sysdeps/x86_64/start.S:125 (inside _start)
如您所见，与应用程序链接的可执行文件和静态对象的符号已正确解析，但高范围内的地址（例如 0x00002b54229ba6d3）未正确解析。这些地址既不是我的应用程序的一部分，也不是我的共享库文件的一部分。因此，addr2line 等其他工具也无法重建该指令的位置。
只要我只打开光盘上的文件来获取符号（我目前所做的是 abfd = bfd_openr("/proc/self/exe", 0);），我就无法使用 bfd 工具解析这些地址，这在某种程度上是预料之中的，所以有没有办法获取当前 运行 进程的 bfd（因此包括共享库的部分）？如果不是：我怎样才能得到加载的共享对象列表及其偏移量，以及如何将这些偏移量与磁盘上的共享对象文件相关联（这样我就可以单独加载 .so 文件的 bfd）？
glibc 向 dl 库中添加了一个名为 dladdr 的函数。使用它可以找到共享对象的文件名及其加载的内存偏移量。使用 bfd_openr 加载这些目标文件允许我转储源文件和行，类似于 addr2line 的处理方式（但仍然转储一些信息以防这些不可用）。例如（注意 libc6.so 在我的系统上不包含调试符号，因此只显示最接近的导出符号）：
callstack:
[0x00002b3d744b4340 .text] /homes/numerik/huber/store/code/tensorDev/algorithm/als.hpp:11 (inside xerus::ALSVariant::lapack_solver(xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&))
[0x0000000000571f0a .text] /usr/include/c++/4.8/functional:2073 (inside std::_Function_handler<void (xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&), void (*)(xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&)>::_M_invoke(std::_Any_data const&, xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&))
[0x00002b3d744ddcba .text] /usr/include/c++/4.8/functional:2469 (inside std::function<void (xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&)>::operator()(xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&) const)
[0x00002b3d744b98bc .text] /homes/numerik/huber/store/code/tensorDev/algorithm/als.hpp:117 (inside xerus::ALSVariant::operator()(xerus::TTNetwork<true> const&, xerus::TTNetwork<false>&, xerus::TTNetwork<false> const&, double, std::vector<double, std::allocator<double> >*) const)
[0x0000000000547ac3 .text] /homes/numerik/huber/store/code/tensorDev/unitTests/als.hxx:4 (inside operator())
[0x0000000000554744 .text] /usr/include/c++/4.8/functional:2058 (inside _M_invoke)
[0x00000000005827c8 .text] /usr/include/c++/4.8/functional:2469 (inside std::function<bool ()>::operator()() const)
[0x0000000000580b6c .text] /homes/numerik/huber/store/code/tensorDev/misc/test.cpp:26 (inside ___test(std::pair<std::string, std::function<bool ()> > const&))
[0x0000000000581b3f .text] /homes/numerik/huber/store/code/tensorDev/misc/test.cpp:119 (inside main)
[0x00002b3d75b5dbe5 .text] ??:? (inside __libc_start_main +0x245)
[0x000000000042c269 .text] /home/abuild/rpmbuild/BUILD/glibc-2.18/csu/../sysdeps/x86_64/start.S:125 (inside _start)
如果有人需要相同的功能（我发现创建一个漂亮的调用堆栈非常困难），这里是源代码（作为我们根据 AGPLv3 许可的库的一部分）：
// Xerus - A General Purpose Tensor Library
// Copyright (C) 2014-2015 Benjamin Huber and Sebastian Wolf.
//
// Xerus is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published
// by the Free Software Foundation, either version 3 of the License,
// or (at your option) any later version.
//
// Xerus is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with Xerus. If not, see <http://www.gnu.org/licenses/>.
//
// For further information on Xerus visit https://libXerus.org
// or contact us at contact@libXerus.org.
std::string demangle_cxa(const std::string &_cxa) {
int status;
std::unique_ptr<char[]> realname;
realname.reset(abi::__cxa_demangle(_cxa.data(), 0, 0, &status));
if (status != 0) {
return _cxa;
}
if (realname) {
return std::string(realname.get());
} else {
return "";
}
}
struct bfdResolver {
struct storedBfd {
bfd* abfd;
asymbol** symbols;
intptr_t offset;
};
static std::map<void *, storedBfd> bfds;
static bool bfd_initialized;
static std::string resolve(void *address) {
if (!bfd_initialized) {
bfd_init();
bfd_initialized = true;
}
std::stringstream res;
res << "[0x" << std::setw((int)sizeof(void*)*2) << std::setfill('0') << std::hex << (uintptr_t)address;
// get path and offset of shared object that contains this address
Dl_info info;
dladdr(address, &info);
if (info.dli_fbase == nullptr) {
return res.str()+" .?] <object to address not found>";
}
// load the corresponding bfd file (from file or map)
if (bfds.count(info.dli_fbase) == 0) {
std::unique_ptr<storedBfd> newBfd(new storedBfd);
newBfd->abfd = bfd_openr(info.dli_fname, 0);
if (!newBfd->abfd) {
return res.str()+" .?] <could not open object file>";
}
bfd_check_format(newBfd->abfd,bfd_object);
size_t storage_needed = bfd_get_symtab_upper_bound(newBfd->abfd);
newBfd->symbols =reinterpret_cast<asymbol**>(new char[storage_needed]);
/*size_t numSymbols = */bfd_canonicalize_symtab(newBfd->abfd, newBfd->symbols );
newBfd->offset = (intptr_t)info.dli_fbase;
bfds.insert(std::pair<void *, storedBfd>(info.dli_fbase, *newBfd.release()));
}
storedBfd &currBfd = bfds.at(info.dli_fbase);
asection *section = currBfd.abfd->sections;
bool relative = section->vma < (uintptr_t)currBfd.offset;
// std::cout << '\n' << "sections:\n";
while (section != nullptr) {
intptr_t offset = ((intptr_t)address) - (relative?currBfd.offset:0) - section->vma;
// std::cout << section->name << " " << section->id << " file: " << section->filepos << " flags: " << section->flags
// << " vma: " << std::hex << section->vma << " - " << std::hex << (section->vma+section->size) << std::endl;
if (offset < 0 || (size_t)offset > section->size) {
section = section->next;
continue;
}
res << ' ' << section->name;
if (!(section->flags | SEC_CODE)) {
return res.str()+"] <non executable address>";
}
// get more info on legal addresses
const char *file;
const char *func;
unsigned line;
if (bfd_find_nearest_line(currBfd.abfd, section, currBfd.symbols, offset, &file, &func, &line)) {
if (file) {
return res.str()+"] "+std::string(file)+":"+to_string(line)+" (inside "+demangle_cxa(func)+")";
} else {
if (info.dli_saddr) {
return res.str()+"] ??:? (inside "+demangle_cxa(func)+" +0x"+std::to_string((intptr_t)address-(intptr_t)info.dli_saddr)+")";
} else {
return res.str()+"] ??:? (inside "+demangle_cxa(func)+")";
}
}
} else {
return res.str()+"] <bfd_error> (inside "+demangle_cxa((info.dli_sname?info.dli_sname:""))+")";
}
}
// std::cout << " ---- sections end ------ " << std::endl;
return res.str()+" .none] <not sectioned address>";
}
};
std::map<void *, bfdResolver::storedBfd> bfdResolver::bfds;
bool bfdResolver::bfd_initialized = false;
std::string get_call_stack() {
const size_t MAX_FRAMES = 100;
std::vector<void *> stack(MAX_FRAMES);
int num = backtrace(&stack[0], MAX_FRAMES);
if (num <= 0) {
return "Callstack could not be built.";
}
stack.resize((size_t) num);
std::string res;
//NOTE i=0 corresponds to get_call_stack and is omitted
for (size_t i=1; i<(size_t)num; ++i) {
res += bfdResolver::resolve(stack[i]) + '\n';
}
return res;
}
我用 c++ 编写了一个小函数来创建调用堆栈，使用 bfd 解析地址。它工作正常，我获得了当前应用程序中所有函数的详细信息（源文件和行），但我没有得到关于我的应用程序中包含的共享库的任何信息。
例如：
callstack:
[0x00002b54229ba6d3 .none] <not sectioned address>
[0x00002b5422927907 .none] <not sectioned address>
[0x00002b54229286d0 .none] <not sectioned address>
[0x00000000004f8608 .text] tensorNetwork.hxx:63 (inside operator())
[0x00000000005528da .text] /usr/include/c++/4.8/functional:2058 (inside _M_invoke)
[0x000000000058231c .text] /usr/include/c++/4.8/functional:2469 (inside std::function<bool ()>::operator()() const)
[0x00000000005806c0 .text] test.cpp:26 (inside ___test(std::pair<std::string, std::function<bool ()> > const&))
[0x0000000000581693 .text] test.cpp:119 (inside main)
[0x00002b5423fdebe5 .none] <not sectioned address>
[0x000000000042c129 .text] /home/abuild/rpmbuild/BUILD/glibc-2.18/csu/../sysdeps/x86_64/start.S:125 (inside _start)
如您所见，与应用程序链接的可执行文件和静态对象的符号已正确解析，但高范围内的地址（例如 0x00002b54229ba6d3）未正确解析。这些地址既不是我的应用程序的一部分，也不是我的共享库文件的一部分。因此，addr2line 等其他工具也无法重建该指令的位置。
只要我只打开光盘上的文件来获取符号（我目前所做的是 abfd = bfd_openr("/proc/self/exe", 0);），我就无法使用 bfd 工具解析这些地址，这在某种程度上是预料之中的，所以有没有办法获取当前 运行 进程的 bfd（因此包括共享库的部分）？如果不是：我怎样才能得到加载的共享对象列表及其偏移量，以及如何将这些偏移量与磁盘上的共享对象文件相关联（这样我就可以单独加载 .so 文件的 bfd）？
glibc 向 dl 库中添加了一个名为 dladdr 的函数。使用它可以找到共享对象的文件名及其加载的内存偏移量。使用 bfd_openr 加载这些目标文件允许我转储源文件和行，类似于 addr2line 的处理方式（但仍然转储一些信息以防这些不可用）。例如（注意 libc6.so 在我的系统上不包含调试符号，因此只显示最接近的导出符号）：
callstack:
[0x00002b3d744b4340 .text] /homes/numerik/huber/store/code/tensorDev/algorithm/als.hpp:11 (inside xerus::ALSVariant::lapack_solver(xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&))
[0x0000000000571f0a .text] /usr/include/c++/4.8/functional:2073 (inside std::_Function_handler<void (xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&), void (*)(xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&)>::_M_invoke(std::_Any_data const&, xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&))
[0x00002b3d744ddcba .text] /usr/include/c++/4.8/functional:2469 (inside std::function<void (xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&)>::operator()(xerus::TensorNetwork const&, xerus::Tensor&, xerus::Tensor const&) const)
[0x00002b3d744b98bc .text] /homes/numerik/huber/store/code/tensorDev/algorithm/als.hpp:117 (inside xerus::ALSVariant::operator()(xerus::TTNetwork<true> const&, xerus::TTNetwork<false>&, xerus::TTNetwork<false> const&, double, std::vector<double, std::allocator<double> >*) const)
[0x0000000000547ac3 .text] /homes/numerik/huber/store/code/tensorDev/unitTests/als.hxx:4 (inside operator())
[0x0000000000554744 .text] /usr/include/c++/4.8/functional:2058 (inside _M_invoke)
[0x00000000005827c8 .text] /usr/include/c++/4.8/functional:2469 (inside std::function<bool ()>::operator()() const)
[0x0000000000580b6c .text] /homes/numerik/huber/store/code/tensorDev/misc/test.cpp:26 (inside ___test(std::pair<std::string, std::function<bool ()> > const&))
[0x0000000000581b3f .text] /homes/numerik/huber/store/code/tensorDev/misc/test.cpp:119 (inside main)
[0x00002b3d75b5dbe5 .text] ??:? (inside __libc_start_main +0x245)
[0x000000000042c269 .text] /home/abuild/rpmbuild/BUILD/glibc-2.18/csu/../sysdeps/x86_64/start.S:125 (inside _start)
如果有人需要相同的功能（我发现创建一个漂亮的调用堆栈非常困难），这里是源代码（作为我们根据 AGPLv3 许可的库的一部分）：
// Xerus - A General Purpose Tensor Library
// Copyright (C) 2014-2015 Benjamin Huber and Sebastian Wolf.
//
// Xerus is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published
// by the Free Software Foundation, either version 3 of the License,
// or (at your option) any later version.
//
// Xerus is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with Xerus. If not, see <http://www.gnu.org/licenses/>.
//
// For further information on Xerus visit https://libXerus.org
// or contact us at contact@libXerus.org.
std::string demangle_cxa(const std::string &_cxa) {
int status;
std::unique_ptr<char[]> realname;
realname.reset(abi::__cxa_demangle(_cxa.data(), 0, 0, &status));
if (status != 0) {
return _cxa;
}
if (realname) {
return std::string(realname.get());
} else {
return "";
}
}
struct bfdResolver {
struct storedBfd {
bfd* abfd;
asymbol** symbols;
intptr_t offset;
};
static std::map<void *, storedBfd> bfds;
static bool bfd_initialized;
static std::string resolve(void *address) {
if (!bfd_initialized) {
bfd_init();
bfd_initialized = true;
}
std::stringstream res;
res << "[0x" << std::setw((int)sizeof(void*)*2) << std::setfill('0') << std::hex << (uintptr_t)address;
// get path and offset of shared object that contains this address
Dl_info info;
dladdr(address, &info);
if (info.dli_fbase == nullptr) {
return res.str()+" .?] <object to address not found>";
}
// load the corresponding bfd file (from file or map)
if (bfds.count(info.dli_fbase) == 0) {
std::unique_ptr<storedBfd> newBfd(new storedBfd);
newBfd->abfd = bfd_openr(info.dli_fname, 0);
if (!newBfd->abfd) {
return res.str()+" .?] <could not open object file>";
}
bfd_check_format(newBfd->abfd,bfd_object);
size_t storage_needed = bfd_get_symtab_upper_bound(newBfd->abfd);
newBfd->symbols =reinterpret_cast<asymbol**>(new char[storage_needed]);
/*size_t numSymbols = */bfd_canonicalize_symtab(newBfd->abfd, newBfd->symbols );
newBfd->offset = (intptr_t)info.dli_fbase;
bfds.insert(std::pair<void *, storedBfd>(info.dli_fbase, *newBfd.release()));
}
storedBfd &currBfd = bfds.at(info.dli_fbase);
asection *section = currBfd.abfd->sections;
bool relative = section->vma < (uintptr_t)currBfd.offset;
// std::cout << '\n' << "sections:\n";
while (section != nullptr) {
intptr_t offset = ((intptr_t)address) - (relative?currBfd.offset:0) - section->vma;
// std::cout << section->name << " " << section->id << " file: " << section->filepos << " flags: " << section->flags
// << " vma: " << std::hex << section->vma << " - " << std::hex << (section->vma+section->size) << std::endl;
if (offset < 0 || (size_t)offset > section->size) {
section = section->next;
continue;
}
res << ' ' << section->name;
if (!(section->flags | SEC_CODE)) {
return res.str()+"] <non executable address>";
}
// get more info on legal addresses
const char *file;
const char *func;
unsigned line;
if (bfd_find_nearest_line(currBfd.abfd, section, currBfd.symbols, offset, &file, &func, &line)) {
if (file) {
return res.str()+"] "+std::string(file)+":"+to_string(line)+" (inside "+demangle_cxa(func)+")";
} else {
if (info.dli_saddr) {
return res.str()+"] ??:? (inside "+demangle_cxa(func)+" +0x"+std::to_string((intptr_t)address-(intptr_t)info.dli_saddr)+")";
} else {
return res.str()+"] ??:? (inside "+demangle_cxa(func)+")";
}
}
} else {
return res.str()+"] <bfd_error> (inside "+demangle_cxa((info.dli_sname?info.dli_sname:""))+")";
}
}
// std::cout << " ---- sections end ------ " << std::endl;
return res.str()+" .none] <not sectioned address>";
}
};
std::map<void *, bfdResolver::storedBfd> bfdResolver::bfds;
bool bfdResolver::bfd_initialized = false;
std::string get_call_stack() {
const size_t MAX_FRAMES = 100;
std::vector<void *> stack(MAX_FRAMES);
int num = backtrace(&stack[0], MAX_FRAMES);
if (num <= 0) {
return "Callstack could not be built.";
}
stack.resize((size_t) num);
std::string res;
//NOTE i=0 corresponds to get_call_stack and is omitted
for (size_t i=1; i<(size_t)num; ++i) {
res += bfdResolver::resolve(stack[i]) + '\n';
}
return res;
}