Merge tag 'perf-tools-fixes-for-v5.14-2021-07-18' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Skip invalid hybrid PMU on hybrid systems when the atom (little) CPUs
   are offlined.

 - Fix 'perf test' problems related to the recently added hybrid
   (BIG/little) code.

 - Split ARM's coresight (hw tracing) decode by aux records to avoid
   fatal decoding errors.

 - Fix add event failure in 'perf probe' when running 32-bit perf in a
   64-bit kernel.

 - Fix 'perf sched record' failure when CONFIG_SCHEDSTATS is not set.

 - Fix memory and refcount leaks detected by ASAn when running 'perf
   test', should be clean of warnings now.

 - Remove broken definition of __LITTLE_ENDIAN from tools'
   linux/kconfig.h, which was breaking the build in some systems.

 - Cast PTHREAD_STACK_MIN to int as it may turn into 'long
   sysconf(__SC_THREAD_STACK_MIN_VALUE), breaking the build in some
   systems.

 - Fix libperf build error with LIBPFM4=1.

 - Sync UAPI files changed by the memfd_secret new syscall.

* tag 'perf-tools-fixes-for-v5.14-2021-07-18' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (35 commits)
  perf sched: Fix record failure when CONFIG_SCHEDSTATS is not set
  perf probe: Fix add event failure when running 32-bit perf in a 64-bit kernel
  perf data: Close all files in close_dir()
  perf probe-file: Delete namelist in del_events() on the error path
  perf test bpf: Free obj_buf
  perf trace: Free strings in trace__parse_events_option()
  perf trace: Free syscall tp fields in evsel->priv
  perf trace: Free syscall->arg_fmt
  perf trace: Free malloc'd trace fields on exit
  perf lzma: Close lzma stream on exit
  perf script: Fix memory 'threads' and 'cpus' leaks on exit
  perf script: Release zstd data
  perf session: Cleanup trace_event
  perf inject: Close inject.output on exit
  perf report: Free generated help strings for sort option
  perf env: Fix memory leak of cpu_pmu_caps
  perf test maps__merge_in: Fix memory leak of maps
  perf dso: Fix memory leak in dso__new_map()
  perf test event_update: Fix memory leak of unit
  perf test event_update: Fix memory leak of evlist
  ...

1 files changed, 167 insertions, 1 deletions

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 32ad92d3e454..22f8326547eb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -2683,6 +2683,172 @@ static u64 *cs_etm__create_meta_blk(u64 *buff_in, int *buff_in_offset,
 	return metadata;
 }
 
+/**
+ * Puts a fragment of an auxtrace buffer into the auxtrace queues based
+ * on the bounds of aux_event, if it matches with the buffer that's at
+ * file_offset.
+ *
+ * Normally, whole auxtrace buffers would be added to the queue. But we
+ * want to reset the decoder for every PERF_RECORD_AUX event, and the decoder
+ * is reset across each buffer, so splitting the buffers up in advance has
+ * the same effect.
+ */
+static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_offset, size_t sz,
+				      struct perf_record_aux *aux_event, struct perf_sample *sample)
+{
+	int err;
+	char buf[PERF_SAMPLE_MAX_SIZE];
+	union perf_event *auxtrace_event_union;
+	struct perf_record_auxtrace *auxtrace_event;
+	union perf_event auxtrace_fragment;
+	__u64 aux_offset, aux_size;
+
+	struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+
+	/*
+	 * There should be a PERF_RECORD_AUXTRACE event at the file_offset that we got
+	 * from looping through the auxtrace index.
+	 */
+	err = perf_session__peek_event(session, file_offset, buf,
+				       PERF_SAMPLE_MAX_SIZE, &auxtrace_event_union, NULL);
+	if (err)
+		return err;
+	auxtrace_event = &auxtrace_event_union->auxtrace;
+	if (auxtrace_event->header.type != PERF_RECORD_AUXTRACE)
+		return -EINVAL;
+
+	if (auxtrace_event->header.size < sizeof(struct perf_record_auxtrace) ||
+		auxtrace_event->header.size != sz) {
+		return -EINVAL;
+	}
+
+	/*
+	 * In per-thread mode, CPU is set to -1, but TID will be set instead. See
+	 * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match.
+	 */
+	if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) ||
+			auxtrace_event->cpu != sample->cpu)
+		return 1;
+
+	if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) {
+		/*
+		 * Clamp size in snapshot mode. The buffer size is clamped in
+		 * __auxtrace_mmap__read() for snapshots, so the aux record size doesn't reflect
+		 * the buffer size.
+		 */
+		aux_size = min(aux_event->aux_size, auxtrace_event->size);
+
+		/*
+		 * In this mode, the head also points to the end of the buffer so aux_offset
+		 * needs to have the size subtracted so it points to the beginning as in normal mode
+		 */
+		aux_offset = aux_event->aux_offset - aux_size;
+	} else {
+		aux_size = aux_event->aux_size;
+		aux_offset = aux_event->aux_offset;
+	}
+
+	if (aux_offset >= auxtrace_event->offset &&
+	    aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) {
+		/*
+		 * If this AUX event was inside this buffer somewhere, create a new auxtrace event
+		 * based on the sizes of the aux event, and queue that fragment.
+		 */
+		auxtrace_fragment.auxtrace = *auxtrace_event;
+		auxtrace_fragment.auxtrace.size = aux_size;
+		auxtrace_fragment.auxtrace.offset = aux_offset;
+		file_offset += aux_offset - auxtrace_event->offset + auxtrace_event->header.size;
+
+		pr_debug3("CS ETM: Queue buffer size: %#"PRI_lx64" offset: %#"PRI_lx64
+			  " tid: %d cpu: %d\n", aux_size, aux_offset, sample->tid, sample->cpu);
+		return auxtrace_queues__add_event(&etm->queues, session, &auxtrace_fragment,
+						  file_offset, NULL);
+	}
+
+	/* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */
+	return 1;
+}
+
+static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event,
+					u64 offset __maybe_unused, void *data __maybe_unused)
+{
+	struct perf_sample sample;
+	int ret;
+	struct auxtrace_index_entry *ent;
+	struct auxtrace_index *auxtrace_index;
+	struct evsel *evsel;
+	size_t i;
+
+	/* Don't care about any other events, we're only queuing buffers for AUX events */
+	if (event->header.type != PERF_RECORD_AUX)
+		return 0;
+
+	if (event->header.size < sizeof(struct perf_record_aux))
+		return -EINVAL;
+
+	/* Truncated Aux records can have 0 size and shouldn't result in anything being queued. */
+	if (!event->aux.aux_size)
+		return 0;
+
+	/*
+	 * Parse the sample, we need the sample_id_all data that comes after the event so that the
+	 * CPU or PID can be matched to an AUXTRACE buffer's CPU or PID.
+	 */
+	evsel = evlist__event2evsel(session->evlist, event);
+	if (!evsel)
+		return -EINVAL;
+	ret = evsel__parse_sample(evsel, event, &sample);
+	if (ret)
+		return ret;
+
+	/*
+	 * Loop through the auxtrace index to find the buffer that matches up with this aux event.
+	 */
+	list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+		for (i = 0; i < auxtrace_index->nr; i++) {
+			ent = &auxtrace_index->entries[i];
+			ret = cs_etm__queue_aux_fragment(session, ent->file_offset,
+							 ent->sz, &event->aux, &sample);
+			/*
+			 * Stop search on error or successful values. Continue search on
+			 * 1 ('not found')
+			 */
+			if (ret != 1)
+				return ret;
+		}
+	}
+
+	/*
+	 * Couldn't find the buffer corresponding to this aux record, something went wrong. Warn but
+	 * don't exit with an error because it will still be possible to decode other aux records.
+	 */
+	pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64
+	       " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu);
+	return 0;
+}
+
+static int cs_etm__queue_aux_records(struct perf_session *session)
+{
+	struct auxtrace_index *index = list_first_entry_or_null(&session->auxtrace_index,
+								struct auxtrace_index, list);
+	if (index && index->nr > 0)
+		return perf_session__peek_events(session, session->header.data_offset,
+						 session->header.data_size,
+						 cs_etm__queue_aux_records_cb, NULL);
+
+	/*
+	 * We would get here if there are no entries in the index (either no auxtrace
+	 * buffers or no index at all). Fail silently as there is the possibility of
+	 * queueing them in cs_etm__process_auxtrace_event() if etm->data_queued is still
+	 * false.
+	 *
+	 * In that scenario, buffers will not be split by AUX records.
+	 */
+	return 0;
+}
+
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session)
 {
@@ -2883,7 +3049,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	if (err)
 		goto err_delete_thread;
 
-	err = auxtrace_queues__process_index(&etm->queues, session);
+	err = cs_etm__queue_aux_records(session);
 	if (err)
 		goto err_delete_thread;