[PATCH AUTOSEL 5.15 36/39] perf inject: Fix ARM SPE handling

From: Sasha Levin
Date: Thu Nov 25 2021 - 21:37:03 EST


From: German Gomez <german.gomez@xxxxxxx>

[ Upstream commit 9e1a8d9f683260d50e0a14176d3f7c46a93b2700 ]

'perf inject' is currently not working for Arm SPE. When you try to run
'perf inject' and 'perf report' with a perf.data file that contains SPE
traces, the tool reports a "Bad address" error:

# ./perf record -e arm_spe_0/ts_enable=1,store_filter=1,branch_filter=1,load_filter=1/ -a -- sleep 1
# ./perf inject -i perf.data -o perf.inject.data --itrace
# ./perf report -i perf.inject.data --stdio

0x42c00 [0x8]: failed to process type: 9 [Bad address]
Error:
failed to process sample

As far as I know, the issue was first spotted in [1], but 'perf inject'
was not yet injecting the samples. This patch does something similar to
what cs_etm does for injecting the samples [2], but for SPE.

[1] https://patchwork.kernel.org/project/linux-arm-kernel/cover/20210412091006.468557-1-leo.yan@xxxxxxxxxx/#24117339
[2] https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/tree/tools/perf/util/cs-etm.c?h=perf/core&id=133fe2e617e48ca0948983329f43877064ffda3e#n1196

Reviewed-by: James Clark <james.clark@xxxxxxx>
Signed-off-by: German Gomez <german.gomez@xxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: John Garry <john.garry@xxxxxxxxxx>
Cc: Leo Yan <leo.yan@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Link: https://lore.kernel.org/r/20211105104130.28186-2-german.gomez@xxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
tools/perf/util/arm-spe.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 58b7069c5a5f8..7054f23150e1b 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -51,6 +51,7 @@ struct arm_spe {
u8 timeless_decoding;
u8 data_queued;

+ u64 sample_type;
u8 sample_flc;
u8 sample_llc;
u8 sample_tlb;
@@ -248,6 +249,12 @@ static void arm_spe_prep_sample(struct arm_spe *spe,
event->sample.header.size = sizeof(struct perf_event_header);
}

+static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type)
+{
+ event->header.size = perf_event__sample_event_size(sample, type, 0);
+ return perf_event__synthesize_sample(event, type, 0, sample);
+}
+
static inline int
arm_spe_deliver_synth_event(struct arm_spe *spe,
struct arm_spe_queue *speq __maybe_unused,
@@ -256,6 +263,12 @@ arm_spe_deliver_synth_event(struct arm_spe *spe,
{
int ret;

+ if (spe->synth_opts.inject) {
+ ret = arm_spe__inject_event(event, sample, spe->sample_type);
+ if (ret)
+ return ret;
+ }
+
ret = perf_session__deliver_synth_event(spe->session, event, sample);
if (ret)
pr_err("ARM SPE: failed to deliver event, error %d\n", ret);
@@ -920,6 +933,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
else
attr.sample_type |= PERF_SAMPLE_TIME;

+ spe->sample_type = attr.sample_type;
+
attr.exclude_user = evsel->core.attr.exclude_user;
attr.exclude_kernel = evsel->core.attr.exclude_kernel;
attr.exclude_hv = evsel->core.attr.exclude_hv;
--
2.33.0