[PATCH v1 18/58] perf python: Add callchain support

[Ian Rogers]

Implement pyrf_callchain_node and pyrf_callchain types for lazy
iteration over callchain frames. Add callchain property to
sample_event.

Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/util/python.c | 202 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 202 insertions(+)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 09b566707563..6baf38a08690 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -609,6 +609,193 @@ static PyObject *pyrf_sample_event__insn(PyObject *self, PyObject *args __maybe_
 					 pevent->sample.insn_len);
 }
 
+struct pyrf_callchain_node {
+	PyObject_HEAD
+	u64 ip;
+	struct map *map;
+	struct symbol *sym;
+};
+
+static void pyrf_callchain_node__delete(struct pyrf_callchain_node *pnode)
+{
+	map__put(pnode->map);
+	Py_TYPE(pnode)->tp_free((PyObject*)pnode);
+}
+
+static PyObject *pyrf_callchain_node__get_ip(struct pyrf_callchain_node *pnode,
+					     void *closure __maybe_unused)
+{
+	return PyLong_FromUnsignedLongLong(pnode->ip);
+}
+
+static PyObject *pyrf_callchain_node__get_symbol(struct pyrf_callchain_node *pnode,
+						 void *closure __maybe_unused)
+{
+	if (pnode->sym)
+		return PyUnicode_FromString(pnode->sym->name);
+	return PyUnicode_FromString("[unknown]");
+}
+
+static PyObject *pyrf_callchain_node__get_dso(struct pyrf_callchain_node *pnode,
+					      void *closure __maybe_unused)
+{
+	const char *dsoname = "[unknown]";
+
+	if (pnode->map) {
+		struct dso *dso = map__dso(pnode->map);
+		if (dso) {
+			if (symbol_conf.show_kernel_path && dso__long_name(dso))
+				dsoname = dso__long_name(dso);
+			else
+				dsoname = dso__name(dso);
+		}
+	}
+	return PyUnicode_FromString(dsoname);
+}
+
+static PyGetSetDef pyrf_callchain_node__getset[] = {
+	{ .name = "ip",     .get = (getter)pyrf_callchain_node__get_ip, },
+	{ .name = "symbol", .get = (getter)pyrf_callchain_node__get_symbol, },
+	{ .name = "dso",    .get = (getter)pyrf_callchain_node__get_dso, },
+	{ .name = NULL, },
+};
+
+static PyTypeObject pyrf_callchain_node__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.callchain_node",
+	.tp_basicsize	= sizeof(struct pyrf_callchain_node),
+	.tp_dealloc	= (destructor)pyrf_callchain_node__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= "perf callchain node object.",
+	.tp_getset	= pyrf_callchain_node__getset,
+};
+
+struct pyrf_callchain_frame {
+	u64 ip;
+	struct map *map;
+	struct symbol *sym;
+};
+
+struct pyrf_callchain {
+	PyObject_HEAD
+	struct pyrf_event *pevent;
+	struct pyrf_callchain_frame *frames;
+	u64 nr_frames;
+	u64 pos;
+	bool resolved;
+};
+
+static void pyrf_callchain__delete(struct pyrf_callchain *pchain)
+{
+	Py_XDECREF(pchain->pevent);
+	if (pchain->frames) {
+		for (u64 i = 0; i < pchain->nr_frames; i++)
+			map__put(pchain->frames[i].map);
+		free(pchain->frames);
+	}
+	Py_TYPE(pchain)->tp_free((PyObject*)pchain);
+}
+
+static PyObject *pyrf_callchain__next(struct pyrf_callchain *pchain)
+{
+	struct pyrf_callchain_node *pnode;
+
+	if (!pchain->resolved) {
+		struct evsel *evsel = pchain->pevent->sample.evsel;
+		struct evlist *evlist = evsel->evlist;
+		struct perf_session *session = evlist ? evlist->session : NULL;
+		struct addr_location al;
+		struct callchain_cursor *cursor;
+		struct callchain_cursor_node *node;
+		u64 i;
+
+		if (!session || !pchain->pevent->sample.callchain)
+			return NULL;
+
+		addr_location__init(&al);
+		if (machine__resolve(&session->machines.host, &al, &pchain->pevent->sample) < 0) {
+			addr_location__exit(&al);
+			return NULL;
+		}
+
+		cursor = get_tls_callchain_cursor();
+		if (thread__resolve_callchain(al.thread, cursor, evsel,
+					      &pchain->pevent->sample, NULL, NULL,
+					      PERF_MAX_STACK_DEPTH) != 0) {
+			addr_location__exit(&al);
+			return NULL;
+		}
+		callchain_cursor_commit(cursor);
+
+		pchain->nr_frames = cursor->nr;
+		if (pchain->nr_frames > 0) {
+			pchain->frames = calloc(pchain->nr_frames, sizeof(*pchain->frames));
+			if (!pchain->frames) {
+				addr_location__exit(&al);
+				return PyErr_NoMemory();
+			}
+
+			for (i = 0; i < pchain->nr_frames; i++) {
+				node = callchain_cursor_current(cursor);
+				pchain->frames[i].ip = node->ip;
+				pchain->frames[i].map = map__get(node->ms.map);
+				pchain->frames[i].sym = node->ms.sym;
+				callchain_cursor_advance(cursor);
+			}
+		}
+		pchain->resolved = true;
+		addr_location__exit(&al);
+	}
+
+	if (pchain->pos >= pchain->nr_frames)
+		return NULL;
+
+	pnode = PyObject_New(struct pyrf_callchain_node, &pyrf_callchain_node__type);
+	if (!pnode)
+		return NULL;
+
+	pnode->ip = pchain->frames[pchain->pos].ip;
+	pnode->map = map__get(pchain->frames[pchain->pos].map);
+	pnode->sym = pchain->frames[pchain->pos].sym;
+
+	pchain->pos++;
+	return (PyObject *)pnode;
+}
+
+static PyTypeObject pyrf_callchain__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.callchain",
+	.tp_basicsize	= sizeof(struct pyrf_callchain),
+	.tp_dealloc	= (destructor)pyrf_callchain__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= "perf callchain object.",
+	.tp_iter	= PyObject_SelfIter,
+	.tp_iternext	= (iternextfunc)pyrf_callchain__next,
+};
+
+static PyObject *pyrf_sample_event__get_callchain(PyObject *self, void */*closure*/)
+{
+	struct pyrf_event *pevent = (void *)self;
+	struct pyrf_callchain *pchain;
+
+	if (!pevent->sample.callchain) {
+		Py_INCREF(Py_None);
+		return Py_None;
+	}
+
+	pchain = PyObject_New(struct pyrf_callchain, &pyrf_callchain__type);
+	if (!pchain)
+		return NULL;
+
+	Py_INCREF(pevent);
+	pchain->pevent = pevent;
+	pchain->frames = NULL;
+	pchain->nr_frames = 0;
+	pchain->pos = 0;
+	pchain->resolved = false;
+	return (PyObject *)pchain;
+}
+
 static PyObject*
 pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name)
 {
@@ -623,6 +810,12 @@ pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name)
 }
 
 static PyGetSetDef pyrf_sample_event__getset[] = {
+	{
+		.name = "callchain",
+		.get = pyrf_sample_event__get_callchain,
+		.set = NULL,
+		.doc = "event callchain.",
+	},
 	{
 		.name = "raw_buf",
 		.get = (getter)pyrf_sample_event__get_raw_buf,
@@ -791,6 +984,12 @@ static int pyrf_event__setup_types(void)
 	err = PyType_Ready(&pyrf_context_switch_event__type);
 	if (err < 0)
 		goto out;
+	err = PyType_Ready(&pyrf_callchain_node__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_callchain__type);
+	if (err < 0)
+		goto out;
 out:
 	return err;
 }
@@ -2836,6 +3035,9 @@ static int pyrf_session__init(struct pyrf_session *psession, PyObject *args, PyO
 		return -1;
 	}
 
+	symbol_conf.use_callchain = true;
+	symbol_conf.show_kernel_path = true;
+	symbol_conf.inline_name = false;
 	if (symbol__init(perf_session__env(psession->session)) < 0) {
 		perf_session__delete(psession->session);
 		Py_DECREF(pdata);
-- 
2.54.0.rc1.513.gad8abe7a5a-goog