perf callchain: Use pthread keys for tls callchain_cursor

Pthread keys are more portable than __thread and allow the association
of a destructor with the key. Use the destructor to clean up TLS
callchain cursors to aid understanding memory leaks.

Committer notes:

Had to fixup a series of unconverted places and also check for the
return of get_tls_callchain_cursor() as it may fail and return NULL.

In that unlikely case we now either print something to a file, if the
caller was expecting to print a callchain, or return an error code to
state that resolving the callchain isn't possible.

In some cases this was made easier because thread__resolve_callchain()
already can fail for other reasons, so this new one (cursor == NULL) can
be added and the callers don't have to explicitely check for this new
condition.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ali Saidi <alisaidi@amazon.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Brian Robbins <brianrob@linux.microsoft.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Fangrui Song <maskray@google.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ivan Babrou <ivan@cloudflare.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Wenyu Liu <liuwenyu7@huawei.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Ye Xingchen <ye.xingchen@zte.com.cn>
Cc: Yuan Can <yuancan@huawei.com>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230608232823.4027869-25-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/callchain.c

@@ -58,7 +58,8 @@ struct callchain_param callchain_param_default = {
 	CALLCHAIN_PARAM_DEFAULT
 };
 
-__thread struct callchain_cursor callchain_cursor;
+/* Used for thread-local struct callchain_cursor. */
+static pthread_key_t callchain_cursor;
 
 int parse_callchain_record_opt(const char *arg, struct callchain_param *param)
 {
@@ -986,6 +987,9 @@ int callchain_append(struct callchain_root *root,
 		     struct callchain_cursor *cursor,
 		     u64 period)
 {
+	if (cursor == NULL)
+		return -1;
+
 	if (!cursor->nr)
 		return 0;
 
@@ -1116,7 +1120,7 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp
 	if ((!symbol_conf.use_callchain || sample->callchain == NULL) &&
 		!symbol_conf.show_branchflag_count)
 		return 0;
-	return callchain_append(he->callchain, &callchain_cursor, sample->period);
+	return callchain_append(he->callchain, get_tls_callchain_cursor(), sample->period);
 }
 
 int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
@@ -1570,6 +1574,43 @@ out:
 	return -ENOMEM;
 }
 
+static void callchain_cursor__delete(void *vcursor)
+{
+	struct callchain_cursor *cursor = vcursor;
+	struct callchain_cursor_node *node, *next;
+
+	callchain_cursor_reset(cursor);
+	for (node = cursor->first; node != NULL; node = next) {
+		next = node->next;
+		free(node);
+	}
+	free(cursor);
+}
+
+static void init_callchain_cursor_key(void)
+{
+	if (pthread_key_create(&callchain_cursor, callchain_cursor__delete)) {
+		pr_err("callchain cursor creation failed");
+		abort();
+	}
+}
+
+struct callchain_cursor *get_tls_callchain_cursor(void)
+{
+	static pthread_once_t once_control = PTHREAD_ONCE_INIT;
+	struct callchain_cursor *cursor;
+
+	pthread_once(&once_control, init_callchain_cursor_key);
+	cursor = pthread_getspecific(callchain_cursor);
+	if (!cursor) {
+		cursor = zalloc(sizeof(*cursor));
+		if (!cursor)
+			pr_debug3("%s: not enough memory\n", __func__);
+		pthread_setspecific(callchain_cursor, cursor);
+	}
+	return cursor;
+}
+
 int callchain_cursor__copy(struct callchain_cursor *dst,
 			   struct callchain_cursor *src)
 {