perf callchain: Enable dwarf_callchain_users on arm64

Enable dwarf_callchain_users on arm64 which will be needed to do a
DWARF unwind in order to get the caller of the leaf frame.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Alexandre Truong <alexandre.truong@arm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20211217154521.80603-5-german.gomez@arm.com
Signed-off-by: German Gomez <german.gomez@arm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8ae400429870a8fc5a191b420d5711c39c86842c..1dd92d8c92799c2cb7065f10348171dd16f8cef0 100644 (file)
--- 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"
@@ -1127,7 +1127,7 @@ 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 ab7d575f97f286d2b28a2fa2831af46a131ac1c3..d308adfd1176e149ea731e5a0d39c7866e6ec378 100644 (file)
--- 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 8e2777133bd907e1903e8d0afab583f5f88fc74d..131207b91d15039ceb23797c1ced396fad70ac34 100644 (file)
--- 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 77fba053c67747d46b2f57510957926c2d2ae3c1..d95615daed73256433302ca5754b03abf31f83ec 100644 (file)
--- 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);