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>

15 files changed, 170 insertions, 61 deletions

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 530a44a59f41..a4cf9de7a7b5 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -284,6 +284,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	struct hist_entry *he;
 	struct addr_location al;
 	struct mem_info *mi, *mi_dup;
+	struct callchain_cursor *cursor;
 	int ret;
 
 	addr_location__init(&al);
@@ -297,7 +298,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (c2c.stitch_lbr)
 		thread__set_lbr_stitch_enable(al.thread, true);
 
-	ret = sample__resolve_callchain(sample, &callchain_cursor, NULL,
+	cursor = get_tls_callchain_cursor();
+	ret = sample__resolve_callchain(sample, cursor, NULL,
 					evsel, &al, sysctl_perf_event_max_stack);
 	if (ret)
 		goto out;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 96a6611e4e53..9714327fd0ea 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -399,6 +399,7 @@ static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample)
 	struct addr_location al;
 	struct machine *machine = &kmem_session->machines.host;
 	struct callchain_cursor_node *node;
+	struct callchain_cursor *cursor;
 	u64 result = sample->ip;
 
 	addr_location__init(&al);
@@ -408,14 +409,19 @@ static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample)
 	}
 
 	al.thread = machine__findnew_thread(machine, sample->pid, sample->tid);
-	sample__resolve_callchain(sample, &callchain_cursor, NULL, evsel, &al, 16);
 
-	callchain_cursor_commit(&callchain_cursor);
+	cursor = get_tls_callchain_cursor();
+	if (cursor == NULL)
+		goto out;
+
+	sample__resolve_callchain(sample, cursor, NULL, evsel, &al, 16);
+
+	callchain_cursor_commit(cursor);
 	while (true) {
 		struct alloc_func key, *caller;
 		u64 addr;
 
-		node = callchain_cursor_current(&callchain_cursor);
+		node = callchain_cursor_current(cursor);
 		if (node == NULL)
 			break;
 
@@ -434,7 +440,7 @@ static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample)
 		} else
 			pr_debug3("skipping alloc function: %s\n", caller->name);
 
-		callchain_cursor_advance(&callchain_cursor);
+		callchain_cursor_advance(cursor);
 	}
 
 	pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip);
diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c
index 2d80aef4eccc..14bf7a8429e7 100644
--- a/tools/perf/builtin-kwork.c
+++ b/tools/perf/builtin-kwork.c
@@ -589,7 +589,7 @@ static void timehist_save_callchain(struct perf_kwork *kwork,
 	struct symbol *sym;
 	struct thread *thread;
 	struct callchain_cursor_node *node;
-	struct callchain_cursor *cursor = &callchain_cursor;
+	struct callchain_cursor *cursor;
 
 	if (!kwork->show_callchain || sample->callchain == NULL)
 		return;
@@ -601,6 +601,8 @@ static void timehist_save_callchain(struct perf_kwork *kwork,
 		return;
 	}
 
+	cursor = get_tls_callchain_cursor();
+
 	if (thread__resolve_callchain(thread, cursor, evsel, sample,
 				      NULL, NULL, kwork->max_stack + 2) != 0) {
 		pr_debug("Failed to resolve callchain, skipping\n");
@@ -686,12 +688,18 @@ static void timehist_print_event(struct perf_kwork *kwork,
 	 * callchain
 	 */
 	if (kwork->show_callchain) {
+		struct callchain_cursor *cursor = get_tls_callchain_cursor();
+
+		if (cursor == NULL)
+			return;
+
 		printf(" ");
+
 		sample__fprintf_sym(sample, al, 0,
 				    EVSEL__PRINT_SYM | EVSEL__PRINT_ONELINE |
 				    EVSEL__PRINT_CALLCHAIN_ARROW |
 				    EVSEL__PRINT_SKIP_IGNORED,
-				    &callchain_cursor, symbol_conf.bt_stop_list,
+				    cursor, symbol_conf.bt_stop_list,
 				    stdout);
 	}
 
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index fc8356bd6e3a..8b505e1e5002 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -911,7 +911,7 @@ static int lock_contention_caller(struct evsel *evsel, struct perf_sample *sampl
 				  char *buf, int size)
 {
 	struct thread *thread;
-	struct callchain_cursor *cursor = &callchain_cursor;
+	struct callchain_cursor *cursor;
 	struct machine *machine = &session->machines.host;
 	struct symbol *sym;
 	int skip = 0;
@@ -925,6 +925,8 @@ static int lock_contention_caller(struct evsel *evsel, struct perf_sample *sampl
 	if (thread == NULL)
 		return -1;
 
+	cursor = get_tls_callchain_cursor();
+
 	/* use caller function name from the callchain */
 	ret = thread__resolve_callchain(thread, cursor, evsel, sample,
 					NULL, NULL, max_stack_depth);
@@ -962,7 +964,7 @@ next:
 
 static u64 callchain_id(struct evsel *evsel, struct perf_sample *sample)
 {
-	struct callchain_cursor *cursor = &callchain_cursor;
+	struct callchain_cursor *cursor;
 	struct machine *machine = &session->machines.host;
 	struct thread *thread;
 	u64 hash = 0;
@@ -973,6 +975,7 @@ static u64 callchain_id(struct evsel *evsel, struct perf_sample *sample)
 	if (thread == NULL)
 		return -1;
 
+	cursor = get_tls_callchain_cursor();
 	/* use caller function name from the callchain */
 	ret = thread__resolve_callchain(thread, cursor, evsel, sample,
 					NULL, NULL, max_stack_depth);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index cd79068200e5..c9ddf73689cd 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2111,7 +2111,7 @@ static void timehist_print_sample(struct perf_sched *sched,
 			    EVSEL__PRINT_SYM | EVSEL__PRINT_ONELINE |
 			    EVSEL__PRINT_CALLCHAIN_ARROW |
 			    EVSEL__PRINT_SKIP_IGNORED,
-			    &callchain_cursor, symbol_conf.bt_stop_list,  stdout);
+			    get_tls_callchain_cursor(), symbol_conf.bt_stop_list,  stdout);
 
 out:
 	printf("\n");
@@ -2196,7 +2196,7 @@ static void save_task_callchain(struct perf_sched *sched,
 				struct evsel *evsel,
 				struct machine *machine)
 {
-	struct callchain_cursor *cursor = &callchain_cursor;
+	struct callchain_cursor *cursor;
 	struct thread *thread;
 
 	/* want main thread for process - has maps */
@@ -2209,6 +2209,8 @@ static void save_task_callchain(struct perf_sched *sched,
 	if (!sched->show_callchain || sample->callchain == NULL)
 		return;
 
+	cursor = get_tls_callchain_cursor();
+
 	if (thread__resolve_callchain(thread, cursor, evsel, sample,
 				      NULL, NULL, sched->max_stack + 2) != 0) {
 		if (verbose > 0)
@@ -2338,10 +2340,16 @@ static void save_idle_callchain(struct perf_sched *sched,
 				struct idle_thread_runtime *itr,
 				struct perf_sample *sample)
 {
+	struct callchain_cursor *cursor;
+
 	if (!sched->show_callchain || sample->callchain == NULL)
 		return;
 
-	callchain_cursor__copy(&itr->cursor, &callchain_cursor);
+	cursor = get_tls_callchain_cursor();
+	if (cursor == NULL)
+		return;
+
+	callchain_cursor__copy(&itr->cursor, cursor);
 }
 
 static struct thread *timehist_get_thread(struct perf_sched *sched,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 784d478c2e05..e3f435e6a7d0 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1557,11 +1557,13 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,
 		unsigned int print_opts = output[type].print_ip_opts;
 		struct callchain_cursor *cursor = NULL;
 
-		if (symbol_conf.use_callchain && sample->callchain &&
-		    thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
-					      sample, NULL, NULL, scripting_max_stack) == 0)
-			cursor = &callchain_cursor;
-
+		if (symbol_conf.use_callchain && sample->callchain) {
+			cursor = get_tls_callchain_cursor();
+			if (thread__resolve_callchain(al->thread, cursor, evsel,
+						      sample, NULL, NULL,
+						      scripting_max_stack))
+				cursor = NULL;
+		}
 		if (cursor == NULL) {
 			printed += fprintf(fp, " ");
 			if (print_opts & EVSEL__PRINT_SRCLINE) {
@@ -2203,11 +2205,13 @@ static void process_event(struct perf_script *script,
 		if (script->stitch_lbr)
 			thread__set_lbr_stitch_enable(al->thread, true);
 
-		if (symbol_conf.use_callchain && sample->callchain &&
-		    thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
-					      sample, NULL, NULL, scripting_max_stack) == 0)
-			cursor = &callchain_cursor;
-
+		if (symbol_conf.use_callchain && sample->callchain) {
+			cursor = get_tls_callchain_cursor();
+			if (thread__resolve_callchain(al->thread, cursor, evsel,
+						      sample, NULL, NULL,
+						      scripting_max_stack))
+				cursor = NULL;
+		}
 		fputc(cursor ? '\n' : ' ', fp);
 		sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor,
 				    symbol_conf.bt_stop_list, fp);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6a1e75f06832..6e73d0e95715 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2437,7 +2437,7 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam
 				        EVSEL__PRINT_DSO |
 				        EVSEL__PRINT_UNKNOWN_AS_ADDR;
 
-	return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, symbol_conf.bt_stop_list, trace->output);
+	return sample__fprintf_callchain(sample, 38, print_opts, get_tls_callchain_cursor(), symbol_conf.bt_stop_list, trace->output);
 }
 
 static const char *errno_to_name(struct evsel *evsel, int err)
@@ -2491,9 +2491,11 @@ static int trace__sys_exit(struct trace *trace, struct evsel *evsel,
 		goto out;
 
 	if (sample->callchain) {
-		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
+		struct callchain_cursor *cursor = get_tls_callchain_cursor();
+
+		callchain_ret = trace__resolve_callchain(trace, evsel, sample, cursor);
 		if (callchain_ret == 0) {
-			if (callchain_cursor.nr < trace->min_stack)
+			if (cursor->nr < trace->min_stack)
 				goto out;
 			callchain_ret = 1;
 		}
@@ -2795,9 +2797,11 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel,
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 
 	if (sample->callchain) {
-		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
+		struct callchain_cursor *cursor = get_tls_callchain_cursor();
+
+		callchain_ret = trace__resolve_callchain(trace, evsel, sample, cursor);
 		if (callchain_ret == 0) {
-			if (callchain_cursor.nr < trace->min_stack)
+			if (cursor->nr < trace->min_stack)
 				goto out;
 			callchain_ret = 1;
 		}
@@ -2899,9 +2903,11 @@ static int trace__pgfault(struct trace *trace,
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 
 	if (sample->callchain) {
-		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
+		struct callchain_cursor *cursor = get_tls_callchain_cursor();
+
+		callchain_ret = trace__resolve_callchain(trace, evsel, sample, cursor);
 		if (callchain_ret == 0) {
-			if (callchain_cursor.nr < trace->min_stack)
+			if (cursor->nr < trace->min_stack)
 				goto out_put;
 			callchain_ret = 1;
 		}
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 909f62b3b266..aee937d14fbb 100644
--- a/tools/perf/util/callchain.c
+++ b/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)
 {
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index d95615daed73..d2618a47deca 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -168,8 +168,6 @@ struct callchain_cursor {
 	struct callchain_cursor_node	*curr;
 };
 
-extern __thread struct callchain_cursor callchain_cursor;
-
 static inline void callchain_init(struct callchain_root *root)
 {
 	INIT_LIST_HEAD(&root->node.val);
@@ -211,6 +209,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
 /* Close a cursor writing session. Initialize for the reader */
 static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
 {
+	if (cursor == NULL)
+		return;
 	cursor->curr = cursor->first;
 	cursor->pos = 0;
 }
@@ -219,7 +219,7 @@ static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
 static inline struct callchain_cursor_node *
 callchain_cursor_current(struct callchain_cursor *cursor)
 {
-	if (cursor->pos == cursor->nr)
+	if (cursor == NULL || cursor->pos == cursor->nr)
 		return NULL;
 
 	return cursor->curr;
@@ -231,6 +231,8 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 	cursor->pos++;
 }
 
+struct callchain_cursor *get_tls_callchain_cursor(void);
+
 int callchain_cursor__copy(struct callchain_cursor *dst,
 			   struct callchain_cursor *src);
 
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 6184696dc266..b9fb71ab7a73 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -215,6 +215,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 	u64 kernel_start = machine__kernel_start(machine);
 	struct call_path *current = &dbe->cpr->call_path;
 	enum chain_order saved_order = callchain_param.order;
+	struct callchain_cursor *cursor;
 	int err;
 
 	if (!symbol_conf.use_callchain || !sample->callchain)
@@ -226,13 +227,14 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 	 * the callchain starting with the root node and ending with the leaf.
 	 */
 	callchain_param.order = ORDER_CALLER;
-	err = thread__resolve_callchain(thread, &callchain_cursor, evsel,
+	cursor = get_tls_callchain_cursor();
+	err = thread__resolve_callchain(thread, cursor, evsel,
 					sample, NULL, NULL, PERF_MAX_STACK_DEPTH);
 	if (err) {
 		callchain_param.order = saved_order;
 		return NULL;
 	}
-	callchain_cursor_commit(&callchain_cursor);
+	callchain_cursor_commit(cursor);
 
 	while (1) {
 		struct callchain_cursor_node *node;
@@ -240,7 +242,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 		u64 dso_db_id = 0, sym_db_id = 0, offset = 0;
 
 
-		node = callchain_cursor_current(&callchain_cursor);
+		node = callchain_cursor_current(cursor);
 		if (!node)
 			break;
 
@@ -265,7 +267,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 					     al.sym, node->ip,
 					     kernel_start);
 
-		callchain_cursor_advance(&callchain_cursor);
+		callchain_cursor_advance(cursor);
 		addr_location__exit(&al);
 	}
 
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index cf45ca0e768f..8719b3cb5646 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -127,6 +127,9 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 	char s = print_oneline ? ' ' : '\t';
 	bool first = true;
 
+	if (cursor == NULL)
+		return fprintf(fp, "<not enough memory for the callchain cursor>%s", print_oneline ? "" : "\n");
+
 	if (sample->callchain) {
 		callchain_cursor_commit(cursor);
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index fb218b3e8a7c..efaf7ac784fc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1029,15 +1029,19 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter,
 			      struct addr_location *al __maybe_unused)
 {
 	struct hist_entry **he_cache;
+	struct callchain_cursor *cursor = get_tls_callchain_cursor();
 
-	callchain_cursor_commit(&callchain_cursor);
+	if (cursor == NULL)
+		return -ENOMEM;
+
+	callchain_cursor_commit(cursor);
 
 	/*
 	 * This is for detecting cycles or recursions so that they're
 	 * cumulated only one time to prevent entries more than 100%
 	 * overhead.
 	 */
-	he_cache = malloc(sizeof(*he_cache) * (callchain_cursor.nr + 1));
+	he_cache = malloc(sizeof(*he_cache) * (cursor->nr + 1));
 	if (he_cache == NULL)
 		return -ENOMEM;
 
@@ -1072,7 +1076,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	 * We need to re-initialize the cursor since callchain_append()
 	 * advanced the cursor to the end.
 	 */
-	callchain_cursor_commit(&callchain_cursor);
+	callchain_cursor_commit(get_tls_callchain_cursor());
 
 	hists__inc_nr_samples(hists, he->filtered);
 
@@ -1085,7 +1089,7 @@ iter_next_cumulative_entry(struct hist_entry_iter *iter,
 {
 	struct callchain_cursor_node *node;
 
-	node = callchain_cursor_current(&callchain_cursor);
+	node = callchain_cursor_current(get_tls_callchain_cursor());
 	if (node == NULL)
 		return 0;
 
@@ -1131,12 +1135,15 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 		.raw_size = sample->raw_size,
 	};
 	int i;
-	struct callchain_cursor cursor;
+	struct callchain_cursor cursor, *tls_cursor = get_tls_callchain_cursor();
 	bool fast = hists__has(he_tmp.hists, sym);
 
-	callchain_cursor_snapshot(&cursor, &callchain_cursor);
+	if (tls_cursor == NULL)
+		return -ENOMEM;
+
+	callchain_cursor_snapshot(&cursor, tls_cursor);
 
-	callchain_cursor_advance(&callchain_cursor);
+	callchain_cursor_advance(tls_cursor);
 
 	/*
 	 * Check if there's duplicate entries in the callchain.
@@ -1222,7 +1229,7 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 	if (al)
 		alm = map__get(al->map);
 
-	err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
+	err = sample__resolve_callchain(iter->sample, get_tls_callchain_cursor(), &iter->parent,
 					iter->evsel, al, max_stack_depth);
 	if (err) {
 		map__put(alm);
@@ -1568,8 +1575,13 @@ static int hists__hierarchy_insert_entry(struct hists *hists,
 
 		if (hist_entry__has_callchains(new_he) &&
 		    symbol_conf.use_callchain) {
-			callchain_cursor_reset(&callchain_cursor);
-			if (callchain_merge(&callchain_cursor,
+			struct callchain_cursor *cursor = get_tls_callchain_cursor();
+
+			if (cursor == NULL)
+				return -1;
+
+			callchain_cursor_reset(cursor);
+			if (callchain_merge(cursor,
 					    new_he->callchain,
 					    he->callchain) < 0)
 				ret = -1;
@@ -1610,11 +1622,15 @@ static int hists__collapse_insert_entry(struct hists *hists,
 				he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
 			if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) {
-				callchain_cursor_reset(&callchain_cursor);
-				if (callchain_merge(&callchain_cursor,
-						    iter->callchain,
-						    he->callchain) < 0)
-					ret = -1;
+				struct callchain_cursor *cursor = get_tls_callchain_cursor();
+
+				if (cursor != NULL) {
+					callchain_cursor_reset(cursor);
+					if (callchain_merge(cursor, iter->callchain, he->callchain) < 0)
+						ret = -1;
+				} else {
+					ret = 0;
+				}
 			}
 			hist_entry__delete(he);
 			return ret;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index bdad4b8bf77d..4e62843d51b7 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -3180,6 +3180,9 @@ int thread__resolve_callchain(struct thread *thread,
 {
 	int ret = 0;
 
+	if (cursor == NULL)
+		return -ENOMEM;
+
 	callchain_cursor_reset(cursor);
 
 	if (callchain_param.order == ORDER_CALLEE) {
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 65b761d83a1f..603091317bed 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -260,6 +260,7 @@ static SV *perl_process_callchain(struct perf_sample *sample,
 				  struct evsel *evsel,
 				  struct addr_location *al)
 {
+	struct callchain_cursor *cursor;
 	AV *list;
 
 	list = newAV();
@@ -269,18 +270,20 @@ static SV *perl_process_callchain(struct perf_sample *sample,
 	if (!symbol_conf.use_callchain || !sample->callchain)
 		goto exit;
 
-	if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
+	cursor = get_tls_callchain_cursor();
+
+	if (thread__resolve_callchain(al->thread, cursor, evsel,
 				      sample, NULL, NULL, scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}
-	callchain_cursor_commit(&callchain_cursor);
+	callchain_cursor_commit(cursor);
 
 
 	while (1) {
 		HV *elem;
 		struct callchain_cursor_node *node;
-		node = callchain_cursor_current(&callchain_cursor);
+		node = callchain_cursor_current(cursor);
 		if (!node)
 			break;
 
@@ -328,7 +331,7 @@ static SV *perl_process_callchain(struct perf_sample *sample,
 			}
 		}
 
-		callchain_cursor_advance(&callchain_cursor);
+		callchain_cursor_advance(cursor);
 		av_push(list, newRV_noinc((SV*)elem));
 	}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d96e5c0fef45..59063ec98619 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -417,6 +417,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 					 struct addr_location *al)
 {
 	PyObject *pylist;
+	struct callchain_cursor *cursor;
 
 	pylist = PyList_New(0);
 	if (!pylist)
@@ -425,19 +426,20 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 	if (!symbol_conf.use_callchain || !sample->callchain)
 		goto exit;
 
-	if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
+	cursor = get_tls_callchain_cursor();
+	if (thread__resolve_callchain(al->thread, cursor, evsel,
 				      sample, NULL, NULL,
 				      scripting_max_stack) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}
-	callchain_cursor_commit(&callchain_cursor);
+	callchain_cursor_commit(cursor);
 
 
 	while (1) {
 		PyObject *pyelem;
 		struct callchain_cursor_node *node;
-		node = callchain_cursor_current(&callchain_cursor);
+		node = callchain_cursor_current(cursor);
 		if (!node)
 			break;
 
@@ -493,7 +495,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 					_PyUnicode_FromString(dsoname));
 		}
 
-		callchain_cursor_advance(&callchain_cursor);
+		callchain_cursor_advance(cursor);
 		PyList_Append(pylist, pyelem);
 		Py_DECREF(pyelem);
 	}