[PATCH v4 21/58] perf python: Expose brstack in sample event

[Ian Rogers <irogers@google.com>]

Implement pyrf_branch_entry and pyrf_branch_stack for lazy
iteration over branch stack entries.

Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
v2:

1. Avoided Keyword Collision: Renamed the properties "from" and "to"
   to "from_ip" and "to_ip" in pyrf_branch_entry__getset[] to prevent
   syntax errors in Python.

2. Eager Branch Stack Resolution: Updated pyrf_session_tool__sample()
   to allocate and copy the branch stack entries eagerly when the
   event is processed, instead of deferring it to iteration time. This
   avoids reading from potentially overwritten or unmapped mmap
   buffers.

3. Updated Iterators: Updated pyrf_branch_stack and
   pyrf_branch_stack__next() to use the copied entries rather than
   pointing directly to the sample's buffer.

4. Avoided Reference Leak on Init Failure: Added proper error checking
   for PyModule_AddObject() in the module initialization function,
   decrementing references on failure.
---
 tools/perf/util/python.c | 189 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 189 insertions(+)

diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index c4f0e01b64f3..b446b1e9cfb6 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -19,6 +19,7 @@
 #include "dso.h"
 #include "dwarf-regs.h"
 #include "event.h"
+#include "branch.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "expr.h"
@@ -69,6 +70,8 @@ struct pyrf_event {
 	bool al_resolved;
 	/** @callchain: Resolved callchain, eagerly computed if requested. */
 	PyObject *callchain;
+	/** @brstack: Resolved branch stack, eagerly computed if requested. */
+	PyObject *brstack;
 	/** @event: The underlying perf_event that may be in a file or ring buffer. */
 	union perf_event event;
 };
@@ -107,6 +110,7 @@ static void pyrf_event__delete(struct pyrf_event *pevent)
 	if (pevent->al_resolved)
 		addr_location__exit(&pevent->al);
 	Py_XDECREF(pevent->callchain);
+	Py_XDECREF(pevent->brstack);
 	perf_sample__exit(&pevent->sample);
 	Py_TYPE(pevent)->tp_free((PyObject*)pevent);
 }
@@ -870,6 +874,144 @@ static PyObject *pyrf_sample_event__get_callchain(PyObject *self, void *closure
 	return pevent->callchain;
 }
 
+struct pyrf_branch_entry {
+	PyObject_HEAD
+	u64 from;
+	u64 to;
+	struct branch_flags flags;
+};
+
+static void pyrf_branch_entry__delete(struct pyrf_branch_entry *pentry)
+{
+	Py_TYPE(pentry)->tp_free((PyObject *)pentry);
+}
+
+static PyObject *pyrf_branch_entry__get_from(struct pyrf_branch_entry *pentry,
+					     void *closure __maybe_unused)
+{
+	return PyLong_FromUnsignedLongLong(pentry->from);
+}
+
+static PyObject *pyrf_branch_entry__get_to(struct pyrf_branch_entry *pentry,
+					   void *closure __maybe_unused)
+{
+	return PyLong_FromUnsignedLongLong(pentry->to);
+}
+
+static PyObject *pyrf_branch_entry__get_mispred(struct pyrf_branch_entry *pentry,
+						void *closure __maybe_unused)
+{
+	return PyBool_FromLong(pentry->flags.mispred);
+}
+
+static PyObject *pyrf_branch_entry__get_predicted(struct pyrf_branch_entry *pentry,
+						  void *closure __maybe_unused)
+{
+	return PyBool_FromLong(pentry->flags.predicted);
+}
+
+static PyObject *pyrf_branch_entry__get_in_tx(struct pyrf_branch_entry *pentry,
+					      void *closure __maybe_unused)
+{
+	return PyBool_FromLong(pentry->flags.in_tx);
+}
+
+static PyObject *pyrf_branch_entry__get_abort(struct pyrf_branch_entry *pentry,
+					      void *closure __maybe_unused)
+{
+	return PyBool_FromLong(pentry->flags.abort);
+}
+
+static PyObject *pyrf_branch_entry__get_cycles(struct pyrf_branch_entry *pentry,
+					       void *closure __maybe_unused)
+{
+	return PyLong_FromUnsignedLongLong(pentry->flags.cycles);
+}
+
+static PyObject *pyrf_branch_entry__get_type(struct pyrf_branch_entry *pentry,
+					     void *closure __maybe_unused)
+{
+	return PyLong_FromLong(pentry->flags.type);
+}
+
+static PyGetSetDef pyrf_branch_entry__getset[] = {
+	{ .name = "from_ip",      .get = (getter)pyrf_branch_entry__get_from, },
+	{ .name = "to_ip",        .get = (getter)pyrf_branch_entry__get_to, },
+	{ .name = "mispred",   .get = (getter)pyrf_branch_entry__get_mispred, },
+	{ .name = "predicted", .get = (getter)pyrf_branch_entry__get_predicted, },
+	{ .name = "in_tx",     .get = (getter)pyrf_branch_entry__get_in_tx, },
+	{ .name = "abort",     .get = (getter)pyrf_branch_entry__get_abort, },
+	{ .name = "cycles",    .get = (getter)pyrf_branch_entry__get_cycles, },
+	{ .name = "type",      .get = (getter)pyrf_branch_entry__get_type, },
+	{ .name = NULL, },
+};
+
+static PyTypeObject pyrf_branch_entry__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.branch_entry",
+	.tp_basicsize	= sizeof(struct pyrf_branch_entry),
+	.tp_dealloc	= (destructor)pyrf_branch_entry__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= "perf branch entry object.",
+	.tp_getset	= pyrf_branch_entry__getset,
+};
+
+struct pyrf_branch_stack {
+	PyObject_HEAD
+	struct pyrf_event *pevent;
+	struct branch_entry *entries;
+	u64 nr;
+	u64 pos;
+};
+
+static void pyrf_branch_stack__delete(struct pyrf_branch_stack *pstack)
+{
+	Py_XDECREF(pstack->pevent);
+	free(pstack->entries);
+	Py_TYPE(pstack)->tp_free((PyObject *)pstack);
+}
+
+static PyObject *pyrf_branch_stack__next(struct pyrf_branch_stack *pstack)
+{
+	struct pyrf_branch_entry *pentry;
+
+	if (pstack->pos >= pstack->nr)
+		return NULL;
+
+	pentry = PyObject_New(struct pyrf_branch_entry, &pyrf_branch_entry__type);
+	if (!pentry)
+		return NULL;
+
+	pentry->from = pstack->entries[pstack->pos].from;
+	pentry->to = pstack->entries[pstack->pos].to;
+	pentry->flags = pstack->entries[pstack->pos].flags;
+
+	pstack->pos++;
+	return (PyObject *)pentry;
+}
+
+static PyTypeObject pyrf_branch_stack__type = {
+	PyVarObject_HEAD_INIT(NULL, 0)
+	.tp_name	= "perf.branch_stack",
+	.tp_basicsize	= sizeof(struct pyrf_branch_stack),
+	.tp_dealloc	= (destructor)pyrf_branch_stack__delete,
+	.tp_flags	= Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+	.tp_doc		= "perf branch stack object.",
+	.tp_iter	= PyObject_SelfIter,
+	.tp_iternext	= (iternextfunc)pyrf_branch_stack__next,
+};
+
+static PyObject *pyrf_sample_event__get_brstack(PyObject *self, void *closure __maybe_unused)
+{
+	struct pyrf_event *pevent = (void *)self;
+
+	if (!pevent->brstack)
+		Py_RETURN_NONE;
+
+	Py_INCREF(pevent->brstack);
+	return pevent->brstack;
+}
+
 static PyObject*
 pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name)
 {
@@ -890,6 +1032,12 @@ static PyGetSetDef pyrf_sample_event__getset[] = {
 		.set = NULL,
 		.doc = "event callchain.",
 	},
+	{
+		.name = "brstack",
+		.get = pyrf_sample_event__get_brstack,
+		.set = NULL,
+		.doc = "event branch stack.",
+	},
 	{
 		.name = "raw_buf",
 		.get = (getter)pyrf_sample_event__get_raw_buf,
@@ -1070,6 +1218,12 @@ static int pyrf_event__setup_types(void)
 	err = PyType_Ready(&pyrf_callchain__type);
 	if (err < 0)
 		goto out;
+	err = PyType_Ready(&pyrf_branch_entry__type);
+	if (err < 0)
+		goto out;
+	err = PyType_Ready(&pyrf_branch_stack__type);
+	if (err < 0)
+		goto out;
 out:
 	return err;
 }
@@ -1120,6 +1274,7 @@ static PyObject *pyrf_event__new(const union perf_event *event)
 		memcpy(&pevent->event, event, event->header.size);
 		pevent->sample.evsel = NULL;
 		pevent->callchain = NULL;
+		pevent->brstack = NULL;
 		pevent->al_resolved = false;
 		addr_location__init(&pevent->al);
 	}
@@ -3160,6 +3315,28 @@ static int pyrf_session_tool__sample(const struct perf_tool *tool,
 		}
 	}
 
+	if (sample->branch_stack) {
+		struct branch_stack *bs = sample->branch_stack;
+		struct branch_entry *entries = perf_sample__branch_entries(sample);
+		struct pyrf_branch_stack *pstack;
+
+		pstack = PyObject_New(struct pyrf_branch_stack, &pyrf_branch_stack__type);
+		if (pstack) {
+			Py_INCREF(pevent);
+			pstack->pevent = pevent;
+			pstack->pos = 0;
+			pstack->nr = bs->nr;
+			pstack->entries = calloc(bs->nr, sizeof(struct branch_entry));
+			if (pstack->entries) {
+				memcpy(pstack->entries, entries,
+				       bs->nr * sizeof(struct branch_entry));
+				pevent->brstack = (PyObject *)pstack;
+			} else {
+				Py_DECREF(pstack);
+			}
+		}
+	}
+
 	ret = PyObject_CallFunction(psession->sample, "O", pyevent);
 	if (!ret) {
 		PyErr_Print();
@@ -3543,6 +3720,18 @@ PyMODINIT_FUNC PyInit_perf(void)
 	Py_INCREF(&pyrf_session__type);
 	PyModule_AddObject(module, "session", (PyObject *)&pyrf_session__type);
 
+	Py_INCREF(&pyrf_branch_entry__type);
+	if (PyModule_AddObject(module, "branch_entry", (PyObject *)&pyrf_branch_entry__type) < 0) {
+		Py_DECREF(&pyrf_branch_entry__type);
+		goto error;
+	}
+
+	Py_INCREF(&pyrf_branch_stack__type);
+	if (PyModule_AddObject(module, "branch_stack", (PyObject *)&pyrf_branch_stack__type) < 0) {
+		Py_DECREF(&pyrf_branch_stack__type);
+		goto error;
+	}
+
 	dict = PyModule_GetDict(module);
 	if (dict == NULL)
 		goto error;
-- 
2.54.0.rc2.533.g4f5dca5207-goog