[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200220120655.GA586895@krava>
Date: Thu, 20 Feb 2020 13:06:55 +0100
From: Jiri Olsa <jolsa@...hat.com>
To: "Jin, Yao" <yao.jin@...ux.intel.com>
Cc: acme@...nel.org, jolsa@...nel.org, peterz@...radead.org,
mingo@...hat.com, alexander.shishkin@...ux.intel.com,
Linux-kernel@...r.kernel.org, ak@...ux.intel.com,
kan.liang@...el.com, yao.jin@...el.com
Subject: Re: [PATCH v1 0/2] perf report: Support annotation of code without
symbols
On Thu, Feb 20, 2020 at 08:03:18PM +0800, Jin, Yao wrote:
>
>
> On 2/20/2020 7:56 PM, Jiri Olsa wrote:
> > On Thu, Feb 20, 2020 at 08:59:00AM +0800, Jin Yao wrote:
> > > For perf report on stripped binaries it is currently impossible to do
> > > annotation. The annotation state is all tied to symbols, but there are
> > > either no symbols, or symbols are not covering all the code.
> > >
> > > We should support the annotation functionality even without symbols.
> > >
> > > The first patch uses al_addr to print because it's easy to dump
> > > the instructions from this address in binary for branch mode.
> > >
> > > The second patch supports the annotation on stripped binary.
> > >
> > > Jin Yao (2):
> > > perf util: Print al_addr when symbol is not found
> > > perf annotate: Support interactive annotation of code without symbols
> >
> > looks good, but I'm getting crash when annotating unresolved kernel address:
> >
> > jirka
> >
> >
>
> Thanks for reporting the issue.
>
> I guess you are trying the "0xffffffff81c00ae7", let me try to reproduce
> this issue.
yes, I also checked and it did not happen before
jirka
>
> Thanks
> Jin Yao
>
> > Samples: 14 of event 'cycles:u', Event count (approx.): 1822321
> > Overhead Command Shared Object Symbol
> > 26.86% ls libc-2.30.so [.] __strcoll_l ▒
> > 17.03% ls ls [.] 0x0000000000008968 ▒
> > 13.10% ls [unknown] [k] 0xffffffff81c00ae7 ▒
> > 13.02% ls ld-2.30.so [.] _dl_cache_libcmp ▒
> > 12.84% ls libc-2.30.so [.] _int_malloc ▒
> > 11.94% ls libc-2.30.so [.] __memcpy_chk ▒
> > 5.21% ls ld-2.30.so [.] __GI___tunables_init ▒
> > ▒
> > Program received signal SIGSEGV, Segmentation fault. ▒
> > add_annotate_opt (browser=0xec34a0, act=0x7fffffffabf0, optstr=0x7fffffffab70, ms=0xdbdb60, addr=18446744071591430887) at ui/browsers/hists.c:2500 ▒
> > 2500 if (ms->map->dso->annotate_warned) ▒
> > Missing separate debuginfos, use: dnf debuginfo-install brotli-1.0.7-6.fc31.x86_64 bzip2-libs-1.0.8-1.fc31.x86_64 cyrus-sasl-lib-2.1.27-2.fc31.x86_64 elfutils-debuginfod-client-0.178-7.fc31.x86_64 elfutils-libelf-0.178-7.fc31.x86_64 elfutils-libs-0.178-7.fc31.x86_64 glib2-2.62.5-1.fc31.x86_64 keyutils-libs-1.6-3.fc31.x86_64 krb5-libs-1.17-46.fc31.x86_64 libbabeltrace-1.5.7-2.fc31.x86_64 libcap-2.26-6.fc31.x86_64 libcom_err-1.45.5-1.fc31.x86_64 libcurl-7.66.0-1.fc31.x86_64 libgcc-9.2.1-1.fc31.x86_64 libidn2-2.3.0-1.fc31.x86_64 libnghttp2-1.40.0-1.fc31.x86_64 libpsl-0.21.0-2.fc31.x86_64 libselinux-2.9-5.fc31.x86_64 libssh-0.9.3-1.fc31.x86_64 libunwind-1.3.1-5.fc31.x86_64 libuuid-2.34-4.fc31.x86_64 libxcrypt-4.4.14-1.fc31.x86_64 libzstd-1.4.4-1.fc31.x86_64 openldap-2.4.47-3.fc31.x86_64 openssl-libs-1.1.1d-2.fc31.x86_64 pcre-8.43-3.fc31.x86_64 pcre2-10.34-6.fc31.x86_64 perl-libs-5.30.1-449.fc31.x86_64 popt-1.16-18.fc31.x86_64 python2-libs-2.7.17-1.fc31.x86_64 slang-2.3.2-6.fc31.x86_64 xz-libs-5.2.4-6.fc31.x86_64 zlib-1.2.11-20.fc31.x86_64 ▒
> > (gdb) bt ▒
> > #0 add_annotate_opt (browser=0xec34a0, act=0x7fffffffabf0, optstr=0x7fffffffab70, ms=0xdbdb60, addr=18446744071591430887) at ui/browsers/hists.c:2500 ▒
> > #1 0x000000000061caf9 in perf_evsel__hists_browse (evsel=0xc58860, nr_events=1, helpline=0xef69f0 "Tip: Show current config key-value pairs: perf config --list", left_exits=false, hbt=0x0, min_pcnt=0, ▒
> > env=0xc5c7b0, warn_lost_event=true, annotation_opts=0x7fffffffb518) at ui/browsers/hists.c:3265 ▒
> > #2 0x000000000061dbc2 in perf_evlist__tui_browse_hists (evlist=0xc55ed0, help=0xef69f0 "Tip: Show current config key-value pairs: perf config --list", hbt=0x0, min_pcnt=0, env=0xc5c7b0, warn_lost_event=true, ▒
> > annotation_opts=0x7fffffffb518) at ui/browsers/hists.c:3569 ▒
> > #3 0x00000000004511e4 in report__browse_hists (rep=0x7fffffffb380) at builtin-report.c:630 ▒
> > #4 0x00000000004521db in __cmd_report (rep=0x7fffffffb380) at builtin-report.c:975 ▒
> > #5 0x000000000045444a in cmd_report (argc=0, argv=0x7fffffffd820) at builtin-report.c:1540 ▒
> > #6 0x00000000004e384a in run_builtin (p=0xa5b370 <commands+240>, argc=1, argv=0x7fffffffd820) at perf.c:312 ▒
> > #7 0x00000000004e3ab7 in handle_internal_command (argc=1, argv=0x7fffffffd820) at perf.c:364 ▒
> > #8 0x00000000004e3bfe in run_argv (argcp=0x7fffffffd67c, argv=0x7fffffffd670) at perf.c:408 ▒
> > #9 0x00000000004e3fca in main (argc=1, argv=0x7fffffffd820) at perf.c:538 ▒
> > (gdb) ▒
> >
> >
> >
> >
Powered by blists - more mailing lists