lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <7de7aa09-d59b-3e98-6289-d497aa0496d4@amd.com>
Date:   Mon, 10 Feb 2020 10:47:11 -0600
From:   Kim Phillips <kim.phillips@....com>
To:     Jiri Olsa <jolsa@...nel.org>,
        Arnaldo Carvalho de Melo <acme@...nel.org>
Cc:     lkml <linux-kernel@...r.kernel.org>,
        Ingo Molnar <mingo@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Peter Zijlstra <a.p.zijlstra@...llo.nl>,
        Michael Petlan <mpetlan@...hat.com>,
        Ravi Bangoria <ravi.bangoria@...ux.ibm.com>
Subject: Re: [PATCH 0/4] perf tools: Fix kmap handling

On 2/10/20 8:32 AM, Jiri Olsa wrote:
> hi,
> Ravi Bangoria reported crash in perf top due to wrong kmap
> objects management, this patchset should fix that.
> 
> thanks,
> jirka
> 
> 
> ---
> Jiri Olsa (4):
>       perf tools: Mark modules dsos with kernel type
>       perf tools: Mark ksymbol dsos with kernel type
>       perf tools: Fix map__clone for struct kmap
>       perf tools: Move kmap::kmaps setup to maps__insert
> 
>  tools/perf/util/machine.c | 24 ++++++++++--------------
>  tools/perf/util/map.c     | 17 ++++++++++++++++-
>  2 files changed, 26 insertions(+), 15 deletions(-)
> 

This series fixes a segmentation fault I was seeing on a
couple of AMD systems, so:

Tested-by: Kim Phillips <kim.phillips@....com>

Thanks,

Kim

Thread 259 "perf" received signal SIGSEGV, Segmentation fault.
                                                              [Switching to Thread 0x7fff3b7b6700 (LWP 13241)]
__map__is_kernel (map=0x7fffd80098d0) at util/map.c:244
244		return machine__kernel_map(map__kmaps((struct map *)map)->machine) == map;
(gdb) bt
#0  __map__is_kernel (map=0x7fffd80098d0) at util/map.c:244
#1  0x000055555575d756 in perf_event__process_sample (machine=<optimized out>, sample=0x7fff3b7b5710, 
    evsel=0x555555ef9dd0, event=<optimized out>, tool=0x7fffffff8660) at builtin-top.c:799
#2  deliver_event (qe=<optimized out>, qevent=<optimized out>) at builtin-top.c:1192
#3  0x0000555555831f81 in do_flush (show_progress=false, oe=0x7fffffff8960) at util/ordered-events.c:244
#4  __ordered_events__flush (oe=oe@...ry=0x7fffffff8960, how=how@...ry=OE_FLUSH__TOP, timestamp=timestamp@...ry=0)
    at util/ordered-events.c:323
#5  0x00005555558328df in __ordered_events__flush (timestamp=<optimized out>, how=<optimized out>, oe=<optimized out>)
    at util/ordered-events.c:342
#6  ordered_events__flush (oe=oe@...ry=0x7fffffff8960, how=how@...ry=OE_FLUSH__TOP) at util/ordered-events.c:341
#7  0x000055555575d0f1 in process_thread (arg=0x7fffffff8660) at builtin-top.c:1104
#8  0x00007ffff7bbd6db in start_thread (arg=0x7fff3b7b6700) at pthread_create.c:463
#9  0x00007ffff5d9788f in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:95
(gdb) p map
$1 = (const struct map *) 0x7fffd80098d0

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ