mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2025-01-14 15:56:08 +07:00
1fe627da30
libdwfl parses an ELF file itself and creates mappings for the
individual sections. perf on the other hand sees raw mmap events which
represent individual sections. When we encounter an address pointing
into a mapping with pgoff != 0, we must take that into account and
report the file at the non-offset base address.
This fixes unwinding with libdwfl in some cases. E.g. for a file like:
```
using namespace std;
mutex g_mutex;
double worker()
{
lock_guard<mutex> guard(g_mutex);
uniform_real_distribution<double> uniform(-1E5, 1E5);
default_random_engine engine;
double s = 0;
for (int i = 0; i < 1000; ++i) {
s += norm(complex<double>(uniform(engine), uniform(engine)));
}
cout << s << endl;
return s;
}
int main()
{
vector<std::future<double>> results;
for (int i = 0; i < 10000; ++i) {
results.push_back(async(launch::async, worker));
}
return 0;
}
```
Compile it with `g++ -g -O2 -lpthread cpp-locking.cpp -o cpp-locking`,
then record it with `perf record --call-graph dwarf -e
sched:sched_switch`.
When you analyze it with `perf script` and libunwind, you should see:
```
cpp-locking 20038 [005] 54830.236589: sched:sched_switch: prev_comm=cpp-locking prev_pid=20038 prev_prio=120 prev_state=T ==> next_comm=swapper/5 next_pid=0 next_prio=120
ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb1670208 schedule+0x28 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb16737cc rwsem_down_read_failed+0xec (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb1665e04 call_rwsem_down_read_failed+0x14 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb1672a03 down_read+0x13 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb106bd85 __do_page_fault+0x445 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb18015f5 page_fault+0x45 (/lib/modules/4.14.78-1-lts/build/vmlinux)
7f38e4252591 new_heap+0x101 (/usr/lib/libc-2.28.so)
7f38e4252d0b arena_get2.part.4+0x2fb (/usr/lib/libc-2.28.so)
7f38e4255b1c tcache_init.part.6+0xec (/usr/lib/libc-2.28.so)
7f38e42569e5 __GI___libc_malloc+0x115 (inlined)
7f38e4241790 __GI__IO_file_doallocate+0x90 (inlined)
7f38e424fbbf __GI__IO_doallocbuf+0x4f (inlined)
7f38e424ee47 __GI__IO_file_overflow+0x197 (inlined)
7f38e424df36 _IO_new_file_xsputn+0x116 (inlined)
7f38e4242bfb __GI__IO_fwrite+0xdb (inlined)
7f38e463fa6d std::basic_streambuf<char, std::char_traits<char> >::sputn(char const*, long)+0x1cd (inlined)
7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> >::_M_put(char const*, long)+0x1cd (inlined)
7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::__write<char>(std::ostreambuf_iterator<char, std::char_traits<char> >, char const*, int)+0x1cd (inlined)
7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::_M_insert_float<double>(std::ostreambuf_iterator<c>
7f38e464bd70 std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::put(std::ostreambuf_iterator<char, std::char_traits<char> >, std::ios_base&, char, double) const+0x90 (inl>
7f38e464bd70 std::ostream& std::ostream::_M_insert<double>(double)+0x90 (/usr/lib/libstdc++.so.6.0.25)
563b9cb502f7 std::ostream::operator<<(double)+0xb7 (inlined)
563b9cb502f7 worker()+0xb7 (/ssd/milian/projects/kdab/rnd/hotspot/build/tests/test-clients/cpp-locking/cpp-locking)
563b9cb506fb double std::__invoke_impl<double, double (*)()>(std::__invoke_other, double (*&&)())+0x2b (inlined)
563b9cb506fb std::__invoke_result<double (*)()>::type std::__invoke<double (*)()>(double (*&&)())+0x2b (inlined)
563b9cb506fb decltype (__invoke((_S_declval<0ul>)())) std:🧵:_Invoker<std::tuple<double (*)()> >::_M_invoke<0ul>(std::_Index_tuple<0ul>)+0x2b (inlined)
563b9cb506fb std:🧵:_Invoker<std::tuple<double (*)()> >::operator()()+0x2b (inlined)
563b9cb506fb std::__future_base::_Task_setter<std::unique_ptr<std::__future_base::_Result<double>, std::__future_base::_Result_base::_Deleter>, std:🧵:_Invoker<std::tuple<double (*)()> >, dou>
563b9cb506fb std::_Function_handler<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> (), std::__future_base::_Task_setter<std::unique_ptr<std::__future_>
563b9cb507e8 std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>::operator()() const+0x28 (inlined)
563b9cb507e8 std::__future_base::_State_baseV2::_M_do_set(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>*, bool*)+0x28 (/ssd/milian/>
7f38e46d24fe __pthread_once_slow+0xbe (/usr/lib/libpthread-2.28.so)
563b9cb51149 __gthread_once+0xe9 (inlined)
563b9cb51149 void std::call_once<void (std::__future_base::_State_baseV2::*)(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>*, bool*)>
563b9cb51149 std::__future_base::_State_baseV2::_M_set_result(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>, bool)+0xe9 (inlined)
563b9cb51149 std::__future_base::_Async_state_impl<std:🧵:_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std:🧵:_Invoker<std::tuple<double (*)()> >&&)::{lambda()#1}::op>
563b9cb51149 void std::__invoke_impl<void, std::__future_base::_Async_state_impl<std:🧵:_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std:🧵:_Invoker<std::tuple<double>
563b9cb51149 std::__invoke_result<std::__future_base::_Async_state_impl<std:🧵:_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std:🧵:_Invoker<std::tuple<double (*)()> >>
563b9cb51149 decltype (__invoke((_S_declval<0ul>)())) std:🧵:_Invoker<std::tuple<std::__future_base::_Async_state_impl<std:🧵:_Invoker<std::tuple<double (*)()> >, double>::_Async_state_>
563b9cb51149 std:🧵:_Invoker<std::tuple<std::__future_base::_Async_state_impl<std:🧵:_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std:🧵:_Invoker<std::tuple<dou>
563b9cb51149 std:🧵:_State_impl<std:🧵:_Invoker<std::tuple<std::__future_base::_Async_state_impl<std:🧵:_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread>
7f38e45f0062 execute_native_thread_routine+0x12 (/usr/lib/libstdc++.so.6.0.25)
7f38e46caa9c start_thread+0xfc (/usr/lib/libpthread-2.28.so)
7f38e42ccb22 __GI___clone+0x42 (inlined)
```
Before this patch, using libdwfl, you would see:
```
cpp-locking 20038 [005] 54830.236589: sched:sched_switch: prev_comm=cpp-locking prev_pid=20038 prev_prio=120 prev_state=T ==> next_comm=swapper/5 next_pid=0 next_prio=120
ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb1670208 schedule+0x28 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb16737cc rwsem_down_read_failed+0xec (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb1665e04 call_rwsem_down_read_failed+0x14 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb1672a03 down_read+0x13 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb106bd85 __do_page_fault+0x445 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb18015f5 page_fault+0x45 (/lib/modules/4.14.78-1-lts/build/vmlinux)
7f38e4252591 new_heap+0x101 (/usr/lib/libc-2.28.so)
a041161e77950c5c [unknown] ([unknown])
```
With this patch applied, we get a bit further in unwinding:
```
cpp-locking 20038 [005] 54830.236589: sched:sched_switch: prev_comm=cpp-locking prev_pid=20038 prev_prio=120 prev_state=T ==> next_comm=swapper/5 next_pid=0 next_prio=120
ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb1670208 schedule+0x28 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb16737cc rwsem_down_read_failed+0xec (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb1665e04 call_rwsem_down_read_failed+0x14 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb1672a03 down_read+0x13 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb106bd85 __do_page_fault+0x445 (/lib/modules/4.14.78-1-lts/build/vmlinux)
ffffffffb18015f5 page_fault+0x45 (/lib/modules/4.14.78-1-lts/build/vmlinux)
7f38e4252591 new_heap+0x101 (/usr/lib/libc-2.28.so)
7f38e4252d0b arena_get2.part.4+0x2fb (/usr/lib/libc-2.28.so)
7f38e4255b1c tcache_init.part.6+0xec (/usr/lib/libc-2.28.so)
7f38e42569e5 __GI___libc_malloc+0x115 (inlined)
7f38e4241790 __GI__IO_file_doallocate+0x90 (inlined)
7f38e424fbbf __GI__IO_doallocbuf+0x4f (inlined)
7f38e424ee47 __GI__IO_file_overflow+0x197 (inlined)
7f38e424df36 _IO_new_file_xsputn+0x116 (inlined)
7f38e4242bfb __GI__IO_fwrite+0xdb (inlined)
7f38e463fa6d std::basic_streambuf<char, std::char_traits<char> >::sputn(char const*, long)+0x1cd (inlined)
7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> >::_M_put(char const*, long)+0x1cd (inlined)
7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::__write<char>(std::ostreambuf_iterator<char, std::char_traits<char> >, char const*, int)+0x1cd (inlined)
7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::_M_insert_float<double>(std::ostreambuf_iterator<c>
7f38e464bd70 std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::put(std::ostreambuf_iterator<char, std::char_traits<char> >, std::ios_base&, char, double) const+0x90 (inl>
7f38e464bd70 std::ostream& std::ostream::_M_insert<double>(double)+0x90 (/usr/lib/libstdc++.so.6.0.25)
563b9cb502f7 std::ostream::operator<<(double)+0xb7 (inlined)
563b9cb502f7 worker()+0xb7 (/ssd/milian/projects/kdab/rnd/hotspot/build/tests/test-clients/cpp-locking/cpp-locking)
6eab825c1ee3e4ff [unknown] ([unknown])
```
Note that the backtrace is still stopping too early, when compared to
the nice results obtained via libunwind. It's unclear so far what the
reason for that is.
Committer note:
Further comment by Milian on the thread started on the Link: tag below:
---
The remaining issue is due to a bug in elfutils:
https://sourceware.org/ml/elfutils-devel/2018-q4/msg00089.html
With both patches applied, libunwind and elfutils produce the same output for
the above scenario.
---
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181029141644.3907-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|---|---|---|
| .. | ||
| c++ | ||
| cs-etm-decoder | ||
| include | ||
| intel-pt-decoder | ||
| libunwind | ||
| scripting-engines | ||
| annotate.c | ||
| annotate.h | ||
| arm-spe-pkt-decoder.c | ||
| arm-spe-pkt-decoder.h | ||
| arm-spe.c | ||
| arm-spe.h | ||
| auxtrace.c | ||
| auxtrace.h | ||
| block-range.c | ||
| block-range.h | ||
| bpf-loader.c | ||
| bpf-loader.h | ||
| bpf-prologue.c | ||
| bpf-prologue.h | ||
| branch.c | ||
| branch.h | ||
| Build | ||
| build-id.c | ||
| build-id.h | ||
| cache.h | ||
| call-path.c | ||
| call-path.h | ||
| callchain.c | ||
| callchain.h | ||
| cgroup.c | ||
| cgroup.h | ||
| cloexec.c | ||
| cloexec.h | ||
| color.c | ||
| color.h | ||
| comm.c | ||
| comm.h | ||
| compress.h | ||
| config.c | ||
| config.h | ||
| counts.c | ||
| counts.h | ||
| cpumap.c | ||
| cpumap.h | ||
| cs-etm.c | ||
| cs-etm.h | ||
| ctype.c | ||
| data-convert-bt.c | ||
| data-convert-bt.h | ||
| data-convert.h | ||
| data.c | ||
| data.h | ||
| db-export.c | ||
| db-export.h | ||
| debug.c | ||
| debug.h | ||
| demangle-java.c | ||
| demangle-java.h | ||
| demangle-rust.c | ||
| demangle-rust.h | ||
| drv_configs.c | ||
| drv_configs.h | ||
| dso.c | ||
| dso.h | ||
| dump-insn.c | ||
| dump-insn.h | ||
| dwarf-aux.c | ||
| dwarf-aux.h | ||
| dwarf-regs.c | ||
| env.c | ||
| env.h | ||
| event.c | ||
| event.h | ||
| evlist.c | ||
| evlist.h | ||
| evsel_fprintf.c | ||
| evsel.c | ||
| evsel.h | ||
| expr.h | ||
| expr.y | ||
| find-vdso-map.c | ||
| genelf_debug.c | ||
| genelf.c | ||
| genelf.h | ||
| generate-cmdlist.sh | ||
| group.h | ||
| header.c | ||
| header.h | ||
| help-unknown-cmd.c | ||
| help-unknown-cmd.h | ||
| hist.c | ||
| hist.h | ||
| intel-bts.c | ||
| intel-bts.h | ||
| intel-pt.c | ||
| intel-pt.h | ||
| intlist.c | ||
| intlist.h | ||
| jit.h | ||
| jitdump.c | ||
| jitdump.h | ||
| kvm-stat.h | ||
| levenshtein.c | ||
| levenshtein.h | ||
| llvm-utils.c | ||
| llvm-utils.h | ||
| lzma.c | ||
| machine.c | ||
| machine.h | ||
| map.c | ||
| map.h | ||
| mem2node.c | ||
| mem2node.h | ||
| mem-events.c | ||
| mem-events.h | ||
| memswap.c | ||
| memswap.h | ||
| metricgroup.c | ||
| metricgroup.h | ||
| mmap.c | ||
| mmap.h | ||
| namespaces.c | ||
| namespaces.h | ||
| ordered-events.c | ||
| ordered-events.h | ||
| parse-branch-options.c | ||
| parse-branch-options.h | ||
| parse-events.c | ||
| parse-events.h | ||
| parse-events.l | ||
| parse-events.y | ||
| parse-regs-options.c | ||
| parse-regs-options.h | ||
| path.c | ||
| path.h | ||
| perf_regs.c | ||
| perf_regs.h | ||
| perf-hooks-list.h | ||
| perf-hooks.c | ||
| perf-hooks.h | ||
| PERF-VERSION-GEN | ||
| pmu.c | ||
| pmu.h | ||
| pmu.l | ||
| pmu.y | ||
| print_binary.c | ||
| print_binary.h | ||
| probe-event.c | ||
| probe-event.h | ||
| probe-file.c | ||
| probe-file.h | ||
| probe-finder.c | ||
| probe-finder.h | ||
| pstack.c | ||
| pstack.h | ||
| python-ext-sources | ||
| python.c | ||
| rb_resort.h | ||
| rblist.c | ||
| rblist.h | ||
| record.c | ||
| rwsem.c | ||
| rwsem.h | ||
| s390-cpumsf-kernel.h | ||
| s390-cpumsf.c | ||
| s390-cpumsf.h | ||
| sane_ctype.h | ||
| session.c | ||
| session.h | ||
| setns.c | ||
| setup.py | ||
| smt.c | ||
| smt.h | ||
| sort.c | ||
| sort.h | ||
| srcline.c | ||
| srcline.h | ||
| stat-display.c | ||
| stat-shadow.c | ||
| stat.c | ||
| stat.h | ||
| strbuf.c | ||
| strbuf.h | ||
| strfilter.c | ||
| strfilter.h | ||
| string2.h | ||
| string.c | ||
| strlist.c | ||
| strlist.h | ||
| svghelper.c | ||
| svghelper.h | ||
| symbol_fprintf.c | ||
| symbol-elf.c | ||
| symbol-minimal.c | ||
| symbol.c | ||
| symbol.h | ||
| syscalltbl.c | ||
| syscalltbl.h | ||
| target.c | ||
| target.h | ||
| term.c | ||
| term.h | ||
| thread_map.c | ||
| thread_map.h | ||
| thread-stack.c | ||
| thread-stack.h | ||
| thread.c | ||
| thread.h | ||
| time-utils.c | ||
| time-utils.h | ||
| tool.h | ||
| top.c | ||
| top.h | ||
| trace-event-info.c | ||
| trace-event-parse.c | ||
| trace-event-read.c | ||
| trace-event-scripting.c | ||
| trace-event.c | ||
| trace-event.h | ||
| trigger.h | ||
| tsc.c | ||
| tsc.h | ||
| units.c | ||
| units.h | ||
| unwind-libdw.c | ||
| unwind-libdw.h | ||
| unwind-libunwind-local.c | ||
| unwind-libunwind.c | ||
| unwind.h | ||
| usage.c | ||
| util-cxx.h | ||
| util.c | ||
| util.h | ||
| values.c | ||
| values.h | ||
| vdso.c | ||
| vdso.h | ||
| xyarray.c | ||
| xyarray.h | ||
| zlib.c | ||