@@ -171,6 +171,7 @@ struct record {
bool timestamp_filename;
bool timestamp_boundary;
bool off_cpu;
+ bool dummy_event_added;
const char *filter_action;
struct switch_output switch_output;
unsigned long long samples;
@@ -961,7 +962,7 @@ static int record__config_tracking_events(struct record *rec)
*/
if (opts->target.initial_delay || target__has_cpu(&opts->target) ||
perf_pmus__num_core_pmus() > 1) {
-
+ int evlist_entries_before = evlist->core.nr_entries;
/*
* User space tasks can migrate between CPUs, so when tracing
* selected CPUs, sideband for all CPUs is still needed.
@@ -973,6 +974,8 @@ static int record__config_tracking_events(struct record *rec)
if (!evsel)
return -ENOMEM;
+ rec->dummy_event_added = evlist->core.nr_entries > evlist_entries_before;
+
/*
* Enable the tracking event when the process is forked for
* initial_delay, immediately for system wide.
@@ -1366,6 +1369,7 @@ static int record__open(struct record *rec)
struct perf_session *session = rec->session;
struct record_opts *opts = &rec->opts;
int rc = 0;
+ bool skipped = false;
evlist__for_each_entry(evlist, pos) {
try_again:
@@ -1381,15 +1385,33 @@ static int record__open(struct record *rec)
pos = evlist__reset_weak_group(evlist, pos, true);
goto try_again;
}
- rc = -errno;
evsel__open_strerror(pos, &opts->target, errno, msg, sizeof(msg));
- ui__error("%s\n", msg);
- goto out;
+ ui__error("Failure to open event '%s' on PMU '%s' which will be removed.\n%s\n",
+ evsel__name(pos), evsel__pmu_name(pos), msg);
+ pos->skippable = true;
+ skipped = true;
+ } else {
+ pos->supported = true;
}
-
- pos->supported = true;
}
+ if (skipped) {
+ struct evsel *tmp;
+ int idx = 0;
+
+ evlist__for_each_entry_safe(evlist, tmp, pos) {
+ if (pos->skippable)
+ evlist__remove(evlist, pos);
+ }
+ evlist__for_each_entry(evlist, pos) {
+ pos->core.idx = idx++;
+ }
+ if (idx == 0 || (idx == 1 && rec->dummy_event_added)) {
+ ui__error("Failure to open any events for recording.\n");
+ rc = -1;
+ goto out;
+ }
+ }
if (symbol_conf.kptr_restrict && !evlist__exclude_kernel(evlist)) {
pr_warning(
"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
Whilst for many tools it is an expected behavior that failure to open a perf event is a failure, ARM decided to name PMU events the same as legacy events and then failed to rename such events on a server uncore SLC PMU. As perf's default behavior when no PMU is specified is to open the event on all PMUs that advertise/"have" the event, this yielded failures when trying to make the priority of legacy and sysfs/json events uniform - something requested by RISC-V and ARM. A legacy event user on ARM hardware may find their event opened on an uncore PMU which for perf record will fail. Arnaldo suggested skipping such events which this patch implements. Rather than have the skipping conditional on running on ARM, the skipping is done on all architectures as such a fundamental behavioral difference could lead to problems with tools built/depending on perf. An example of perf record failing to open events on x86 is: ``` $ perf record -e data_read,cycles,LLC-prefetch-read -a sleep 0.1 Error: Failure to open event 'data_read' on PMU 'uncore_imc_free_running_0' which will be removed. The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (data_read). "dmesg | grep -i perf" may provide additional information. Error: Failure to open event 'data_read' on PMU 'uncore_imc_free_running_1' which will be removed. The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (data_read). "dmesg | grep -i perf" may provide additional information. Error: Failure to open event 'LLC-prefetch-read' on PMU 'cpu' which will be removed. The LLC-prefetch-read event is not supported. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 2.188 MB perf.data (87 samples) ] $ perf report --stats Aggregated stats: TOTAL events: 17255 MMAP events: 284 ( 1.6%) COMM events: 1961 (11.4%) EXIT events: 1 ( 0.0%) FORK events: 1960 (11.4%) SAMPLE events: 87 ( 0.5%) MMAP2 events: 12836 (74.4%) KSYMBOL events: 83 ( 0.5%) BPF_EVENT events: 36 ( 0.2%) FINISHED_ROUND events: 2 ( 0.0%) ID_INDEX events: 1 ( 0.0%) THREAD_MAP events: 1 ( 0.0%) CPU_MAP events: 1 ( 0.0%) TIME_CONV events: 1 ( 0.0%) FINISHED_INIT events: 1 ( 0.0%) cycles stats: SAMPLE events: 87 ``` If all events fail to open then the perf record will fail: ``` $ perf record -e LLC-prefetch-read true Error: Failure to open event 'LLC-prefetch-read' on PMU 'cpu' which will be removed. The LLC-prefetch-read event is not supported. Error: Failure to open any events for recording ``` This is done by detecting if a dummy event was added by perf and seeing if the evlist is empty without it. This allows the dummy event still to be recorded: ``` $ perf record -e dummy true [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.046 MB perf.data ] ``` but fail when inserted: ``` $ perf record -e LLC-prefetch-read -a true Error: Failure to open event 'LLC-prefetch-read' on PMU 'cpu' which will be removed. The LLC-prefetch-read event is not supported. Error: Failure to open any events for recording ``` The issue with legacy events is that on RISC-V they want the driver to not have mappings from legacy to non-legacy config encodings for each vendor/model due to size, complexity and difficulty to update. It was reported that on ARM Apple-M? CPUs the legacy mapping in the driver was broken and the sysfs/json events should always take precedent, however, it isn't clear this is still the case. It is the case that without working around this issue a legacy event like cycles without a PMU can encode differently than when specified with a PMU - the non-PMU version favoring legacy encodings, the PMU one avoiding legacy encodings. The patch removes events and then adjusts the idx value for each evsel. This is done so that the dense xyarrays used for file descriptors, etc. don't contain broken entries. As event opening happens relatively late in the record process, use of the idx value before the open will have become corrupted, so it is expected there are latent bugs hidden behind this change - the change is best effort. As the only vendor that has broken event names is ARM, this will principally effect ARM users. They will also experience warning messages like those above because of the uncore PMU advertising legacy event names. Suggested-by: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: James Clark <james.clark@linaro.org> Tested-by: Leo Yan <leo.yan@arm.com> Tested-by: Atish Patra <atishp@rivosinc.com> --- tools/perf/builtin-record.c | 34 ++++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-)