linux-kernel - Re: [PATCH v3 6/8] perf cs-etm: Treat NO

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]
Date:   Thu, 13 Dec 2018 09:41:54 -0300
From:   Arnaldo Carvalho de Melo <acme@...nel.org>
To:     Leo Yan <leo.yan@...aro.org>
Cc:     Mathieu Poirier <mathieu.poirier@...aro.org>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...hat.com>,
        Namhyung Kim <namhyung@...nel.org>,
        linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
        Coresight ML <coresight@...ts.linaro.org>,
        Mike Leach <mike.leach@...aro.org>,
        Robert Walker <robert.walker@....com>
Subject: Re: [PATCH v3 6/8] perf cs-etm: Treat NO_SYNC element as trace
 discontinuity

Em Thu, Dec 13, 2018 at 09:38:54AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Tue, Dec 11, 2018 at 03:38:26PM +0800, Leo Yan escreveu:
> > CoreSight tracer driver might insert barrier packet between different
> > buffers, thus the decoder can spot the boundaries based on the barrier
> > packet; the decoder is possible to hit a barrier packet and emit a
> > NO_SYNC element, then the decoder will find a periodic synchronisation
> > point inside that next trace block that starts trace again but does not
> > have the TRACE_ON element as indicator - usually because this block of
> > trace has wrapped the buffer so we have lost the original point that
> > trace was enabled.
> > 
> > In upper case, it results in the trace stream only inserts the
> > OCSD_GEN_TRC_ELEM_NO_SYNC element in the middle of tracing stream, but
> > we don't handle NO_SYNC element properly and at the end users miss to
> > see the info for trace discontinuity.
> 
> 
> "In upper case"? Maybe:
> 
> In the former case it causes the insertion of a OCSD_GEN_TRC_ELEM_NO_SYNC
> in the middle of the the tracing stream, but as we were npt handling the
> NO_SYNC element properly which ends up making users miss the
> discontinuity indication"?

> > Though OCSD_GEN_TRC_ELEM_NO_SYNC is different from CS_ETM_TRACE_ON when
> > output from the decoder, but both of them indicate the trace data is
> 
> can we remove the "but" and "of them" (redundant) above?
> 
> > discontinuous; this patch treats OCSD_GEN_TRC_ELEM_NO_SYNC as trace
>                                                                a
> > discontinuity and generates CS_ETM_DISCONTINUITY packet for it, so
> > cs-etm can handle discontinuity for this case, finally it saves the last
>                        it (way too many "discontinuity")
> > trace data for previous trace block and restart samples for new block.

I've tentatively done those changes (and a few more) in my local branch,
resulting in the wording below, plese let me know if you are ok with it:


commit 148068b45fe2e93b19c06cfc1140ea12ca72eb59
Author: Leo Yan <leo.yan@...aro.org>
Date:   Tue Dec 11 15:38:26 2018 +0800

    perf cs-etm: Treat NO_SYNC element as trace discontinuity
    
    The CoreSight tracer driver might insert a barrier packets between
    different buffers, thus the decoder can spot the boundaries based on the
    barrier packet; it is possible for the decoder to hit a barrier packet
    and emit a NO_SYNC element, then the decoder will find a periodic
    synchronisation point inside that next trace block that starts the trace
    again but does not have the TRACE_ON element as indicator - usually
    because this trace block has wrapped the buffer so we have lost the
    original point when the trace was enabled.
    
    In the first case it causes the insertion of a OCSD_GEN_TRC_ELEM_NO_SYNC
    in the middle of the the tracing stream, but as we were npt handling the
    NO_SYNC element properly which ends up making users miss the
    discontinuity indication"?
    
    Though OCSD_GEN_TRC_ELEM_NO_SYNC is different from CS_ETM_TRACE_ON when
    output from the decoder, both indicate that the trace data is
    discontinuous; this patch treats OCSD_GEN_TRC_ELEM_NO_SYNC as a trace
    discontinuity and generates a CS_ETM_DISCONTINUITY packet for it, so
    cs-etm can handle the discontinuity for this case, finally it saves the
    last trace data for the previous trace block and restart samples for the
    new block.
    
    Signed-off-by: Leo Yan <leo.yan@...aro.org>
    Reviewed-by: Mathieu Poirier <mathieu.poirier@...aro.org>
    Cc: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
    Cc: Jiri Olsa <jolsa@...hat.com>
    Cc: Mike Leach <mike.leach@...aro.org>
    Cc: Namhyung Kim <namhyung@...nel.org>
    Cc: Robert Walker <robert.walker@....com>
    Cc: coresight ml <coresight@...ts.linaro.org>
    Cc: linux-arm-kernel@...ts.infradead.org
    Link: http://lkml.kernel.org/r/1544513908-16805-7-git-send-email-leo.yan@linaro.org
    Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 1039f364f4cc..bee026e76a4c 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -410,7 +410,6 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 	case OCSD_GEN_TRC_ELEM_UNKNOWN:
 		break;
 	case OCSD_GEN_TRC_ELEM_NO_SYNC:
-		break;
 	case OCSD_GEN_TRC_ELEM_TRACE_ON:
 		resp = cs_etm_decoder__buffer_discontinuity(decoder,
 							    trace_chan_id);