[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240905105043.160225-4-james.clark@linaro.org>
Date: Thu, 5 Sep 2024 11:50:34 +0100
From: James Clark <james.clark@...aro.org>
To: linux-perf-users@...r.kernel.org,
gankulkarni@...amperecomputing.com,
coresight@...ts.linaro.org,
leo.yan@....com,
scclevenger@...amperecomputing.com
Cc: James Clark <james.clark@...aro.org>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Ian Rogers <irogers@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>,
"Liang, Kan" <kan.liang@...ux.intel.com>,
Suzuki K Poulose <suzuki.poulose@....com>,
Mike Leach <mike.leach@...aro.org>,
John Garry <john.g.garry@...cle.com>,
Will Deacon <will@...nel.org>,
Leo Yan <leo.yan@...ux.dev>,
Ben Gainey <ben.gainey@....com>,
Ruidong Tian <tianruidong@...ux.alibaba.com>,
Benjamin Gray <bgray@...ux.ibm.com>,
Mathieu Poirier <mathieu.poirier@...aro.org>,
linux-kernel@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org
Subject: [PATCH 3/8] perf cs-etm: Remove cs_etm__flush()
This is only called on a discontinuity, and it generates a normal
sample and then clears the branch buffer. I'm not convinced that any
of the subtle differences between cs_etm__flush() and cs_etm__sample()
weren't actual bugs or potential sources of them.
Replace it with a call to the existing sample function and then a clear
of the branch buffer.
One obvious difference is that it now generates a range of instructions
based on instructions_sample_period, rather than only a single
instruction sample. I think this is actually the correct thing to do.
Signed-off-by: James Clark <james.clark@...aro.org>
---
tools/perf/util/cs-etm.c | 62 ++++------------------------------------
1 file changed, 5 insertions(+), 57 deletions(-)
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 602e791ff5ba..cdda8403af2b 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1908,60 +1908,6 @@ static int cs_etm__exception(struct cs_etm_traceid_queue *tidq)
return 0;
}
-static int cs_etm__flush(struct cs_etm_queue *etmq,
- struct cs_etm_traceid_queue *tidq)
-{
- int err = 0;
- struct cs_etm_auxtrace *etm = etmq->etm;
-
- /* Handle start tracing packet */
- if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
- goto swap_packet;
-
- if (etmq->etm->synth_opts.last_branch &&
- etmq->etm->synth_opts.instructions &&
- tidq->prev_packet->sample_type == CS_ETM_RANGE) {
- u64 addr;
-
- /* Prepare last branches for instruction sample */
- cs_etm__copy_last_branch_rb(etmq, tidq);
-
- /*
- * Generate a last branch event for the branches left in the
- * circular buffer at the end of the trace.
- *
- * Use the address of the end of the last reported execution
- * range
- */
- addr = cs_etm__last_executed_instr(tidq->prev_packet);
-
- err = cs_etm__synth_instruction_sample(
- etmq, tidq, addr,
- tidq->period_instructions);
- if (err)
- return err;
-
- tidq->period_instructions = 0;
-
- }
-
- if (etm->synth_opts.branches &&
- tidq->prev_packet->sample_type == CS_ETM_RANGE) {
- err = cs_etm__synth_branch_sample(etmq, tidq);
- if (err)
- return err;
- }
-
-swap_packet:
- cs_etm__packet_swap(etm, tidq);
-
- /* Reset last branches after flush the trace */
- if (etm->synth_opts.last_branch)
- cs_etm__reset_last_branch_rb(tidq);
-
- return err;
-}
-
static int cs_etm__end_block(struct cs_etm_queue *etmq,
struct cs_etm_traceid_queue *tidq)
{
@@ -2457,10 +2403,12 @@ static int cs_etm__process_traceid_queue(struct cs_etm_queue *etmq,
break;
case CS_ETM_DISCONTINUITY:
/*
- * Discontinuity in trace, flush
- * previous branch stack
+ * Discontinuity in trace, generate a sample then
+ * clear the branch stack.
*/
- cs_etm__flush(etmq, tidq);
+ cs_etm__sample(etmq, tidq);
+ if (etmq->etm->synth_opts.last_branch)
+ cs_etm__reset_last_branch_rb(tidq);
break;
case CS_ETM_EMPTY:
/*
--
2.34.1
Powered by blists - more mailing lists