[PATCH v5 4/6] perf tools: enable dwarf_callchain_users on arm64

[German Gomez]

From: Alexandre Truong <alexandre.truong at arm.com>

On arm64, enable dwarf_callchain_users which will be needed
to do a dwarf unwind in order to get the caller of the leaf frame.

Signed-off-by: Alexandre Truong <alexandre.truong at arm.com>
Signed-off-by: German Gomez <german.gomez at arm.com>
---
 tools/perf/builtin-report.c |  4 ++--
 tools/perf/builtin-script.c |  4 ++--
 tools/perf/util/callchain.c | 14 +++++++++++++-
 tools/perf/util/callchain.h |  2 +-
 4 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8167ebfe776a..a31ad60ba66e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -410,7 +410,7 @@ static int report__setup_sample_type(struct report *rep)
 		}
 	}
 
-	callchain_param_setup(sample_type);
+	callchain_param_setup(sample_type, perf_env__arch(&rep->session->header.env));
 
 	if (rep->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
 		ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
@@ -1124,7 +1124,7 @@ static int process_attr(struct perf_tool *tool __maybe_unused,
 	 * on events sample_type.
 	 */
 	sample_type = evlist__combined_sample_type(*pevlist);
-	callchain_param_setup(sample_type);
+	callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env));
 	return 0;
 }
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ab7d575f97f2..d308adfd1176 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2318,7 +2318,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	 * on events sample_type.
 	 */
 	sample_type = evlist__combined_sample_type(evlist);
-	callchain_param_setup(sample_type);
+	callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env));
 
 	/* Enable fields for callchain entries */
 	if (symbol_conf.use_callchain &&
@@ -3468,7 +3468,7 @@ static void script__setup_sample_type(struct perf_script *script)
 	struct perf_session *session = script->session;
 	u64 sample_type = evlist__combined_sample_type(session->evlist);
 
-	callchain_param_setup(sample_type);
+	callchain_param_setup(sample_type, perf_env__arch(session->machines.host.env));
 
 	if (script->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
 		pr_warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8e2777133bd9..131207b91d15 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1600,7 +1600,7 @@ void callchain_cursor_reset(struct callchain_cursor *cursor)
 		map__zput(node->ms.map);
 }
 
-void callchain_param_setup(u64 sample_type)
+void callchain_param_setup(u64 sample_type, const char *arch)
 {
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
 		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
@@ -1612,6 +1612,18 @@ void callchain_param_setup(u64 sample_type)
 		else
 			callchain_param.record_mode = CALLCHAIN_FP;
 	}
+
+	/*
+	 * It's necessary to use libunwind to reliably determine the caller of
+	 * a leaf function on aarch64, as otherwise we cannot know whether to
+	 * start from the LR or FP.
+	 *
+	 * Always starting from the LR can result in duplicate or entirely
+	 * erroneous entries. Always skipping the LR and starting from the FP
+	 * can result in missing entries.
+	 */
+	if (callchain_param.record_mode == CALLCHAIN_FP && !strcmp(arch, "arm64"))
+		dwarf_callchain_users = true;
 }
 
 static bool chain_match(struct callchain_list *base_chain,
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 77fba053c677..d95615daed73 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -300,7 +300,7 @@ int callchain_branch_counts(struct callchain_root *root,
 			    u64 *branch_count, u64 *predicted_count,
 			    u64 *abort_count, u64 *cycles_count);
 
-void callchain_param_setup(u64 sample_type);
+void callchain_param_setup(u64 sample_type, const char *arch);
 
 bool callchain_cnode_matched(struct callchain_node *base_cnode,
 			     struct callchain_node *pair_cnode);
-- 
2.25.1