public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
To: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
	David Ahern <dsahern@gmail.com>,
	linux-kernel@vger.kernel.org,
	"Steven Rostedt (Red Hat)" <rostedt@goodmis.org>,
	Oleg Nesterov <oleg@redhat.com>, Ingo Molnar <mingo@redhat.com>,
	"David A. Long" <dave.long@linaro.org>,
	yrl.pp-manager.tt@hitachi.com, Namhyung Kim <namhyung@kernel.org>
Subject: Re: [PATCH -tip 0/8] perf-probe: Updates for handling local functions correctly
Date: Mon, 27 Jan 2014 19:26:37 +0900	[thread overview]
Message-ID: <52E6345D.6080902@hitachi.com> (raw)
In-Reply-To: <20140123022945.7206.79944.stgit@kbuild-fedora.yrl.intra.hitachi.co.jp>

Hi Arnaldo,

Could you wait for pulling this series?
I've found that this series has an obvious bug on
kaslr enabled kernel. I'll fix that by using
the relative address from _stext for kprobes.

Thank you,

(2014/01/23 11:29), Masami Hiramatsu wrote:
> Hi,
> 
> Here is a series of patches for handling local functions
> correctly in perf-probe.
> 
> Issue 1)
>  Current perf-probe can't handle probe-points for kprobes,
>  since it uses symbol-based probe definition. The symbol
>  based definition is easy to read and robust for differnt
>  kernel and modules. However, when user gives a local
>  function name which has several different instances,
>  it may put probes on wrong (or unexpected) address.
>  On the other hand, since uprobe events are based on the
>  actual address, it can avoid this issue.
> 
>  E.g.
> In the case to probe t_show local functions (which has
> 4 different instances.
> ----
> # grep " t_show\$" /proc/kallsyms
> ffffffff810d9720 t t_show
> ffffffff810e2e40 t t_show
> ffffffff810ece30 t t_show
> ffffffff810f4ad0 t t_show
> # ./perf probe -f t_show \$vars
> Added new events:
>   probe:t_show         (on t_show with $vars)
>   probe:t_show_1       (on t_show with $vars)
>   probe:t_show_2       (on t_show with $vars)
>   probe:t_show_3       (on t_show with $vars)
> 
> You can now use it in all perf tools, such as:
> 
>         perf record -e probe:t_show_3 -aR sleep 1
> ----
> OK, we have 4 different t_show()s. All functions have
> different arguments as below;
> ----
> # cat /sys/kernel/debug/tracing/kprobe_events
> p:probe/t_show t_show m=%di:u64 v=%si:u64
> p:probe/t_show_1 t_show m=%di:u64 v=%si:u64 t=%si:u64
> p:probe/t_show_2 t_show m=%di:u64 v=%si:u64 fmt=%si:u64
> p:probe/t_show_3 t_show m=%di:u64 v=%si:u64 file=%si:u64
> ----
> However, all of them have been put on the *same* address.
> ----
> # cat /sys/kernel/debug/kprobes/list
> ffffffff810d9720  k  t_show+0x0    [DISABLED]
> ffffffff810d9720  k  t_show+0x0    [DISABLED]
> ffffffff810d9720  k  t_show+0x0    [DISABLED]
> ffffffff810d9720  k  t_show+0x0    [DISABLED]
> ----
>  oops...
> 
> Issue 2)
>  With the debuginfo, issue 1 can be solved by using
>  address-based probe definition instead of symbol-based.
>  However, without debuginfo, perf-probe can only use
>  symbol-map in the binary (or kallsyms). The map provides
>  symbol find methods, but it returns only the first matched
>  symbol. To put probes on all functions which have given
>  symbol, we need a symbol-list iterator for the map.
> 
>  E.g. (built perf with NO_DWARF=1)
> In the case to probe t_show and identity__map_ip in perf.
> ----
> # ./perf probe -a t_show
> Added new event:
>   probe:t_show         (on t_show)
> 
> You can now use it in all perf tools, such as:
> 
>         perf record -e probe:t_show -aR sleep 1
> 
> # ./perf probe -x perf -a identity__map_ip
> no symbols found in /kbuild/ksrc/linux-3/tools/perf/perf, maybe install a debug package?
> Failed to load map.
>   Error: Failed to add events. (-22)
> ----
>  oops.....
> 
> 
> Solutions)
> To solve the issue 1, this series changes perf probe to
> use address-based probe definition. This means that we
> also need to fix the --list options to analyze probe
> addresses instead of symbols (and that has been done
> in this series).
> 
> E.g. with this series;
> ----
> # ./perf probe -f t_show \$vars
> Added new events:
>   probe:t_show         (on t_show with $vars)
>   probe:t_show_1       (on t_show with $vars)
>   probe:t_show_2       (on t_show with $vars)
>   probe:t_show_3       (on t_show with $vars)
> 
> You can now use it in all perf tools, such as:
> 
>         perf record -e probe:t_show_3 -aR sleep 1
> 
> # cat /sys/kernel/debug/tracing/kprobe_events
> p:probe/t_show 0xffffffff810d9720 m=%di:u64 v=%si:u64
> p:probe/t_show_1 0xffffffff810e2e40 m=%di:u64 v=%si:u64 t=%si:u64
> p:probe/t_show_2 0xffffffff810ece30 m=%di:u64 v=%si:u64 fmt=%si:u64
> p:probe/t_show_3 0xffffffff810f4ad0 m=%di:u64 v=%si:u64 file=%si:u64
> 
> # cat /sys/kernel/debug/kprobes/list
> ffffffff810e2e40  k  t_show+0x0    [DISABLED]
> ffffffff810ece30  k  t_show+0x0    [DISABLED]
> ffffffff810f4ad0  k  t_show+0x0    [DISABLED]
> ffffffff810d9720  k  t_show+0x0    [DISABLED]
> ----
> This time we can see the events are set in different
> addresses.
> 
> And for the issue 2, the last patch introduces symbol
> iterators for map, dso and symbols (since the symbol
> list is the symbols and it is included dso, and perf
> probe accesses dso via map).
> 
> E.g. with this series (built perf with NO_DWARF=1);
> ----
> # ./perf probe -a t_show
> Added new events:
>   probe:t_show         (on t_show)
>   probe:t_show_1       (on t_show)
>   probe:t_show_2       (on t_show)
>   probe:t_show_3       (on t_show)
> 
> You can now use it in all perf tools, such as:
> 
>         perf record -e probe:t_show_3 -aR sleep 1
> 
> # ./perf probe -x perf -a identity__map_ip
> Added new events:
>   probe_perf:identity__map_ip (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf)
>   probe_perf:identity__map_ip_1 (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf)
>   probe_perf:identity__map_ip_2 (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf)
>   probe_perf:identity__map_ip_3 (on identity__map_ip in /kbuild/ksrc/linux-3/tools/perf/perf)
> 
> You can now use it in all perf tools, such as:
> 
>         perf record -e probe_perf:identity__map_ip_3 -aR sleep 1
> ----
> Now, even without the debuginfo, both the kprobe and
> uprobe are set 4 different places correctly.
> 
> BTW, while testing above, I've found some bugs and
> another minor issue; perf-probe doesn't show the
> modules and binaries in which probes are set.
> I've also fixed it in this series as below.
> 
> Without the fix;
> 
> # ./perf probe -m drm drm_av_sync_delay
> # ./perf probe -x perf dso__load_vmlinux
> 
> # ./perf probe -l
>   probe:drm_av_sync_delay (on drm_av_sync_delay)
>   probe_perf:dso__load_vmlinux (on 0x000000000006d110)
> 
> With this fix;
> 
> # ./perf probe -l
>   probe:drm_av_sync_delay (on drm_av_sync_delay in drm)
>   probe_perf:dso__load_vmlinux (on 0x000000000006d110 in /kbuild/ksrc/linux-3/tools/perf/perf)
> 
> 
> TODO:
>  - Support local functions in modules. This requires kernel
>  side enhancement to allow setting probes by the relative
>  addresses in modules too.
>  - Uprobe-event MUST traces the change of given binary even
>  when the event is disabled. I've found that user can replace
>  the target binary after setting events and the events can be
>  enabled on the different instructions...
> 
> ---
> 
> Masami Hiramatsu (8):
>       [BUGFIX] perf-probe: Fix to do exit call for symbol maps
>       [BUGFIX] perf-tools: Load map before using map->map_ip
>       perf-probe: Show in what binaries/modules probes are set
>       perf-probe: Use the actual address instead of the symbol name
>       perf-probe: Show source level information for address only kprobes
>       perf-probe: Show symbol+offset for address only kprobes
>       perf-probe: Show source-level or symbol-level info for uprobes
>       perf-probe: Allow to add events on the local functions
> 
> 
>  tools/perf/util/dso.h         |   10 +
>  tools/perf/util/map.c         |    3 
>  tools/perf/util/map.h         |   10 +
>  tools/perf/util/probe-event.c |  661 ++++++++++++++++++++++-------------------
>  tools/perf/util/symbol.h      |   11 +
>  5 files changed, 387 insertions(+), 308 deletions(-)
> 


-- 
Masami HIRAMATSU
IT Management Research Dept. Linux Technology Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt@hitachi.com



  parent reply	other threads:[~2014-01-27 10:26 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-01-23  2:29 [PATCH -tip 0/8] perf-probe: Updates for handling local functions correctly Masami Hiramatsu
2014-01-23  2:29 ` [PATCH -tip 1/8] [BUGFIX] perf-probe: Fix to do exit call for symbol maps Masami Hiramatsu
2014-01-23  2:29 ` [PATCH -tip 2/8] [BUGFIX] perf-tools: Load map before using map->map_ip Masami Hiramatsu
2014-01-23 14:43   ` Arnaldo Carvalho de Melo
2014-01-25 14:23   ` [tip:perf/urgent] perf symbols: Load map before using map->map_ip () tip-bot for Masami Hiramatsu
2014-01-23  2:29 ` [PATCH -tip 3/8] perf-probe: Show in what binaries/modules probes are set Masami Hiramatsu
2014-01-23 14:49   ` Arnaldo Carvalho de Melo
2014-01-23  2:29 ` [PATCH -tip 4/8] perf-probe: Use the actual address instead of the symbol name Masami Hiramatsu
2014-01-23 14:52   ` Arnaldo Carvalho de Melo
2014-01-23 16:12     ` Steven Rostedt
2014-01-24  1:49       ` Masami Hiramatsu
2014-01-24 12:13         ` Arnaldo Carvalho de Melo
2014-01-25  3:04           ` Masami Hiramatsu
2014-01-23  2:29 ` [PATCH -tip 5/8] perf-probe: Show source level information for address only kprobes Masami Hiramatsu
2014-01-23  2:29 ` [PATCH -tip 6/8] perf-probe: Show symbol+offset " Masami Hiramatsu
2014-01-23  2:30 ` [PATCH -tip 7/8] perf-probe: Show source-level or symbol-level info for uprobes Masami Hiramatsu
2014-01-23  2:30 ` [PATCH -tip 8/8] perf-probe: Allow to add events on the local functions Masami Hiramatsu
2014-01-27 10:26 ` Masami Hiramatsu [this message]
2014-01-27 14:46   ` [PATCH -tip 0/8] perf-probe: Updates for handling local functions correctly Arnaldo Carvalho de Melo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=52E6345D.6080902@hitachi.com \
    --to=masami.hiramatsu.pt@hitachi.com \
    --cc=acme@ghostprotocols.net \
    --cc=dave.long@linaro.org \
    --cc=dsahern@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=oleg@redhat.com \
    --cc=rostedt@goodmis.org \
    --cc=srikar@linux.vnet.ibm.com \
    --cc=yrl.pp-manager.tt@hitachi.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox