linux-toradex.git/tools/perf/util/cs-etm-decoder, branch v6.3

perf cs-etm: Update decoder code for OpenCSD version 1.4

2023-01-30T17:54:13+00:00

OpenCSD version 1.4 is released with support for FEAT_ITE.

This adds a new packet type, with associated output element ID in the
packet type enum - OCSD_GEN_TRC_ELEM_INSTRUMENTATION.

As we just ignore this packet in perf, add to the switch statement to
avoid the "enum not handled in switch error", but conditionally so as
not to break the perf build for older OpenCSD installations.

Reviewed-by: James Clark 
Signed-off-by: Mike Leach 
Acked-by: Ian Rogers 
Cc: Alexander Shishkin 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Suzuki Poulouse 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230120153706.20388-1-mike.leach@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo

perf cs-etm: Ensure that Coresight timestamps don't go backwards

2023-01-22T21:17:46+00:00

There are some edge cases around estimated timestamps that can result
in them going backwards.

One is that after a discontinuity, the last used timestamp is set to 0.
The duration of the next range is then subtracted which could result in
an earlier timestamp than the last instruction. Fix this by not
resetting the last timestamp used on a discontinuity, and make sure that
new estimated timestamps are clamped to be later than that.

Another case is that estimated timestamps could compound over time to
end up being more than the next real timestamp in the trace. Fix this by
clamping the estimates in cs_etm_decoder__do_soft_timestamp() to be no
later than it.

cs_etm_decoder__do_soft_timestamp() also updated next_cs_timestamp,
which meant that the next real timestamp was lost and not stored
anywhere. Fix that by only updating cs_timestamp for estimates and keep
next_cs_timestamp untouched.

Finally, use next_cs_timestamp to signify if a timestamp has been
received previously. Because cs_timestamp has the first range
subtracted, it could technically go to 0 which would break the logic.

Testing
=======

It can be verified that timestamps don't go backwards when tracing on a
single core with the following commands. Across multiple cores it's
expected that timestamps are interleaved:

  $ perf record -e cs_etm/@tmc_etr0/k -C 4 taskset -c 4 sleep 1
  $ perf script --itrace=i1ns --ns -Fcomm,tid,pid,time,cpu,event,ip,sym,addr,symoff,flags,callindent > itrace
  $ sed 's/://g' itrace | awk -F ' ' ' { print $4 } ' | awk '{ if ($1 < prev) { print "line:" NR " " $0 } {prev=$1}}'

Reported-by: Tanmay Jagdale 
Signed-off-by: James Clark 
Acked-by: Suzuki Poulouse 
Tested-by: Tanmay Jagdale 
Cc: Alexander Shishkin 
Cc: Bharat Bhushan 
Cc: George Cherian 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Leo Yan 
Cc: Linu Cherian 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Sunil Kovvuri Goutham 
Cc: Will Deacon 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230120143702.4035046-9-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo

perf cs_etm: Set the time field in the synthetic samples

2023-01-22T21:17:45+00:00

If virtual timestamps are detected, set sample time field accordingly,
otherwise warn the user that the samples will not include accurate
time data.

  | Test notes (FEAT_TRF platform)
  |
  | $ ./perf record -e cs_etm//u -a -- sleep 4
  | $ ./perf script --fields +time
  | 	    perf   422 [000]   163.375100:          1 branches:uH:                 0 [unknown] ([unknown])
  | 	    perf   422 [000]   163.375100:          1 branches:uH:      ffffb8009544 ioctl+0x14 (/lib/aarch64-linux-gnu/libc-2.27.so)
  | 	    perf   422 [000]   163.375100:          1 branches:uH:      aaaaab6bebf4 perf_evsel__run_ioctl+0x90 (/home/german/linux/tools/perf/perf)
  | [...]
  | 	    perf   422 [000]   167.393100:          1 branches:uH:      aaaaab6bda00 __xyarray__entry+0x74 (/home/german/linux/tools/perf/perf)
  | 	    perf   422 [000]   167.393099:          1 branches:uH:      aaaaab6bda0c __xyarray__entry+0x80 (/home/german/linux/tools/perf/perf)
  | 	    perf   422 [000]   167.393099:          1 branches:uH:      ffffb8009538 ioctl+0x8 (/lib/aarch64-linux-gnu/libc-2.27.so)
  |
  | The time from the first sample to the last sample is 4 seconds

Now that times are converted to nanoseconds, also try to estimate the
timestamps more accurately be dividing by some fixed value for
instructions per ns. This prevents long ranges from being estimated
too far in the past than would be realistic.

Signed-off-by: German Gomez 
Acked-by: Suzuki Poulouse 
Tested-by: Tanmay Jagdale 
Cc: Alexander Shishkin 
Cc: Bharat Bhushan 
Cc: George Cherian 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Leo Yan 
Cc: Linu Cherian 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Sunil Kovvuri Goutham 
Cc: Will Deacon 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230120143702.4035046-8-james.clark@arm.com
Signed-off-by: James Clark 
Signed-off-by: Arnaldo Carvalho de Melo

perf cs-etm: Print the decoder name

2021-09-03T11:17:25+00:00

Use the real name of the decoder instead of hard-coding "ETM" to avoid
confusion when the trace is ETE. This also now distinguishes between
ETMv3 and ETMv4.

Reviewed-by: Leo Yan 
Reviewed-by: Suzuki Poulouse 
Signed-off-by: James Clark 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Will Deacon 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https //lore.kernel.org/r/20210806134109.1182235-9-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo

perf cs-etm: Create ETE decoder

2021-09-03T11:16:36+00:00

If the magic number indicates ETE instantiate a OCSD_BUILTIN_DCD_ETE
decoder instead of OCSD_BUILTIN_DCD_ETMV4I. ETE is the new trace feature
for Armv9.

Testing performed
=================

* Old files with v0 and v1 headers for ETMv4 still open correctly
* New files with new magic number open on new versions of perf
* New files with new magic number fail to open on old versions of perf
* Decoding with the ETE decoder results in the same output as the ETMv4
  decoder as long as there are no new ETE packet types

Reviewed-by: Leo Yan 
Signed-off-by: James Clark 
Acked-by: Suzuki Poulouse 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Will Deacon 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https //lore.kernel.org/r/20210806134109.1182235-8-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo

perf cs-etm: Update OpenCSD decoder for ETE

2021-09-03T11:16:00+00:00

OpenCSD v1.1.1 has a bug fix for the installation of the ETE decoder
headers. This also means that including headers separately for each
decoder is unnecessary so remove these.

Reviewed-by: Leo Yan 
Signed-off-by: James Clark 
Acked-by: Suzuki Poulouse 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Will Deacon 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https //lore.kernel.org/r/20210806134109.1182235-7-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo

perf cs-etm: Initialise architecture based on TRCIDR1

2021-09-03T11:07:38+00:00

Currently the architecture is hard coded as ARCH_V8, but from ETMv4.4
onwards this should be ARCH_AA64.

Reviewed-by: Leo Yan 
Signed-off-by: James Clark 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Suzuki Poulouse 
Cc: Will Deacon 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https //lore.kernel.org/r/20210806134109.1182235-3-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo

perf cs-etm: Refactor initialisation of decoder params.

2021-09-03T11:04:38+00:00

The initialisation of the decoder params is duplicated between
creation of the packet printer and packet decoder. Put them both
into one function so that future changes only need to be made in one
place.

Reviewed-by: Leo Yan 
Signed-off-by: James Clark 
Acked-by: Suzuki Poulouse 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Will Deacon 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https //lore.kernel.org/r/20210806134109.1182235-2-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo

perf cs-etm: Improve Coresight zero timestamp warning

2021-08-03T20:04:19+00:00

Only show the warning if the user hasn't already set timeless mode and
improve the text because there was ambiguity around the meaning of '...'

Change the warning to a UI warning instead of printing straight to
stderr because this corrupts the UI when perf report TUI is used. The UI
warning function also handles printing to stderr when in perf script
mode.

Suggested-by: Leo Yan 
Signed-off-by: James Clark 
Reviewed-by: Leo Yan 
Cc: Alexander Shishkin 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Mathieu Poirier 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Suzuki Poulouse 
Cc: Will Deacon 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lore.kernel.org/lkml/20210729155805.2830-6-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo

perf cs-etm: Pass unformatted flag to decoder

2021-08-02T12:56:17+00:00

The TRBE (Trace Buffer Extension) feature allows a separate trace buffer
for each trace source, therefore the trace wouldn't need to be
formatted. The driver was introduced in commit 3fbf7f011f24
("coresight: sink: Add TRBE driver").

The formatted/unformatted mode is encoded in one of the flags of the
AUX record. The first AUX record encountered for each event is used to
determine the mode, and this will persist for the remaining trace that
is either decoded or dumped.

Reviewed-by: Mathieu Poirier 
Signed-off-by: James Clark 
Cc: Al Grant 
Cc: Alexander Shishkin 
Cc: Anshuman Khandual 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
Cc: John Garry 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Mike Leach 
Cc: Namhyung Kim 
Cc: Suzuki Poulouse 
Cc: Will Deacon 
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https //lore.kernel.org/r/20210721150202.32065-7-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo