* [PATCH v8 18/58] perf python: Extend API for stat events in python.c
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Add stat information to the session. Add call backs for stat events.
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
v5:
1. Fix Memory Corruption: Corrected the memory offset for `stat_round_type`
in `pyrf_stat_round_event__members` by adding the base offset of
`struct pyrf_event`.
2. Fix Memory Leak: Added `Py_XDECREF()` to free the unused return value
of the Python callback in `pyrf_session_tool__stat_round()`.
---
v7:
- Added comprehensive size checks in pyrf_event__new for all event
types.
- Fixed line length warning.
---
tools/perf/util/python.c | 177 +++++++++++++++++++++++++++++++++++++--
1 file changed, 170 insertions(+), 7 deletions(-)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 2ff588517c29..144fbc85fcb3 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -341,6 +341,77 @@ static PyTypeObject pyrf_lost_event__type = {
.tp_repr = (reprfunc)pyrf_lost_event__repr,
};
+static const char pyrf_stat_event__doc[] = PyDoc_STR("perf stat event object.");
+
+static PyMemberDef pyrf_stat_event__members[] = {
+ sample_members
+ member_def(perf_event_header, type, T_UINT, "event type"),
+ member_def(perf_record_stat, id, T_ULONGLONG, "event id"),
+ member_def(perf_record_stat, cpu, T_UINT, "event cpu"),
+ member_def(perf_record_stat, thread, T_UINT, "event thread"),
+ member_def(perf_record_stat, val, T_ULONGLONG, "counter value"),
+ member_def(perf_record_stat, ena, T_ULONGLONG, "enabled time"),
+ member_def(perf_record_stat, run, T_ULONGLONG, "running time"),
+ { .name = NULL, },
+};
+
+static PyObject *pyrf_stat_event__repr(const struct pyrf_event *pevent)
+{
+ return PyUnicode_FromFormat(
+ "{ type: stat, id: %llu, cpu: %u, thread: %u, val: %llu, ena: %llu, run: %llu }",
+ pevent->event.stat.id,
+ pevent->event.stat.cpu,
+ pevent->event.stat.thread,
+ pevent->event.stat.val,
+ pevent->event.stat.ena,
+ pevent->event.stat.run);
+}
+
+static PyTypeObject pyrf_stat_event__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.stat_event",
+ .tp_basicsize = sizeof(struct pyrf_event),
+ .tp_new = PyType_GenericNew,
+ .tp_dealloc = (destructor)pyrf_event__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_stat_event__doc,
+ .tp_members = pyrf_stat_event__members,
+ .tp_getset = pyrf_event__getset,
+ .tp_repr = (reprfunc)pyrf_stat_event__repr,
+};
+
+static const char pyrf_stat_round_event__doc[] = PyDoc_STR("perf stat round event object.");
+
+static PyMemberDef pyrf_stat_round_event__members[] = {
+ sample_members
+ member_def(perf_event_header, type, T_UINT, "event type"),
+ { .name = "stat_round_type", .type = T_ULONGLONG,
+ .offset = offsetof(struct pyrf_event, event) + offsetof(struct perf_record_stat_round, type),
+ .doc = "round type" },
+ member_def(perf_record_stat_round, time, T_ULONGLONG, "round time"),
+ { .name = NULL, },
+};
+
+static PyObject *pyrf_stat_round_event__repr(const struct pyrf_event *pevent)
+{
+ return PyUnicode_FromFormat("{ type: stat_round, type: %llu, time: %llu }",
+ pevent->event.stat_round.type,
+ pevent->event.stat_round.time);
+}
+
+static PyTypeObject pyrf_stat_round_event__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.stat_round_event",
+ .tp_basicsize = sizeof(struct pyrf_event),
+ .tp_new = PyType_GenericNew,
+ .tp_dealloc = (destructor)pyrf_event__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_stat_round_event__doc,
+ .tp_members = pyrf_stat_round_event__members,
+ .tp_getset = pyrf_event__getset,
+ .tp_repr = (reprfunc)pyrf_stat_round_event__repr,
+};
+
static const char pyrf_read_event__doc[] = PyDoc_STR("perf read event object.");
static PyMemberDef pyrf_read_event__members[] = {
@@ -1032,6 +1103,12 @@ static int pyrf_event__setup_types(void)
if (err < 0)
goto out;
err = PyType_Ready(&pyrf_context_switch_event__type);
+ if (err < 0)
+ goto out;
+ err = PyType_Ready(&pyrf_stat_event__type);
+ if (err < 0)
+ goto out;
+ err = PyType_Ready(&pyrf_stat_round_event__type);
if (err < 0)
goto out;
err = PyType_Ready(&pyrf_callchain_node__type);
@@ -1057,6 +1134,8 @@ static PyTypeObject *pyrf_event__type[] = {
[PERF_RECORD_SAMPLE] = &pyrf_sample_event__type,
[PERF_RECORD_SWITCH] = &pyrf_context_switch_event__type,
[PERF_RECORD_SWITCH_CPU_WIDE] = &pyrf_context_switch_event__type,
+ [PERF_RECORD_STAT] = &pyrf_stat_event__type,
+ [PERF_RECORD_STAT_ROUND] = &pyrf_stat_round_event__type,
};
static PyObject *pyrf_event__new(const union perf_event *event, struct evsel *evsel,
@@ -1089,13 +1168,13 @@ static PyObject *pyrf_event__new(const union perf_event *event, struct evsel *ev
case PERF_RECORD_EXIT:
min_size = sizeof(struct perf_record_fork);
break;
+ case PERF_RECORD_LOST:
+ min_size = sizeof(struct perf_record_lost);
+ break;
case PERF_RECORD_THROTTLE:
case PERF_RECORD_UNTHROTTLE:
min_size = sizeof(struct perf_record_throttle);
break;
- case PERF_RECORD_LOST:
- min_size = sizeof(struct perf_record_lost);
- break;
case PERF_RECORD_READ:
min_size = sizeof(struct perf_record_read);
break;
@@ -2117,7 +2196,40 @@ static PyObject *pyrf_evsel__get_attr_wakeup_events(PyObject *self, void */*clos
return PyLong_FromUnsignedLong(pevsel->evsel->core.attr.wakeup_events);
}
+static PyObject *pyrf_evsel__get_ids(struct pyrf_evsel *pevsel, void *closure __maybe_unused)
+{
+ struct evsel *evsel = pevsel->evsel;
+ PyObject *list = PyList_New(0);
+
+ if (!list)
+ return NULL;
+
+ for (u32 i = 0; i < evsel->core.ids; i++) {
+ PyObject *id = PyLong_FromUnsignedLongLong(evsel->core.id[i]);
+ int ret;
+
+ if (!id) {
+ Py_DECREF(list);
+ return NULL;
+ }
+ ret = PyList_Append(list, id);
+ Py_DECREF(id);
+ if (ret < 0) {
+ Py_DECREF(list);
+ return NULL;
+ }
+ }
+
+ return list;
+}
+
static PyGetSetDef pyrf_evsel__getset[] = {
+ {
+ .name = "ids",
+ .get = (getter)pyrf_evsel__get_ids,
+ .set = NULL,
+ .doc = "event IDs.",
+ },
{
.name = "tracking",
.get = pyrf_evsel__get_tracking,
@@ -2890,6 +3002,8 @@ static const struct perf_constant perf__constants[] = {
PERF_CONST(RECORD_LOST_SAMPLES),
PERF_CONST(RECORD_SWITCH),
PERF_CONST(RECORD_SWITCH_CPU_WIDE),
+ PERF_CONST(RECORD_STAT),
+ PERF_CONST(RECORD_STAT_ROUND),
PERF_CONST(RECORD_MISC_SWITCH_OUT),
{ .name = NULL, },
@@ -3266,6 +3380,7 @@ struct pyrf_session {
struct perf_tool tool;
struct pyrf_data *pdata;
PyObject *sample;
+ PyObject *stat;
};
static int pyrf_session_tool__sample(const struct perf_tool *tool,
@@ -3291,6 +3406,47 @@ static int pyrf_session_tool__sample(const struct perf_tool *tool,
return 0;
}
+static int pyrf_session_tool__stat(const struct perf_tool *tool,
+ struct perf_session *session,
+ union perf_event *event)
+{
+ struct pyrf_session *psession = container_of(tool, struct pyrf_session, tool);
+ struct evsel *evsel = evlist__id2evsel(session->evlist, event->stat.id);
+ PyObject *pyevent = pyrf_event__new(event, evsel, psession->session);
+ const char *name = evsel ? evsel__name(evsel) : "unknown";
+ PyObject *ret;
+
+ if (pyevent == NULL)
+ return -ENOMEM;
+
+ ret = PyObject_CallFunction(psession->stat, "Os", pyevent, name);
+ if (!ret) {
+ PyErr_Print();
+ Py_DECREF(pyevent);
+ return -1;
+ }
+ Py_DECREF(ret);
+ Py_DECREF(pyevent);
+ return 0;
+}
+
+static int pyrf_session_tool__stat_round(const struct perf_tool *tool,
+ struct perf_session *session __maybe_unused,
+ union perf_event *event)
+{
+ struct pyrf_session *psession = container_of(tool, struct pyrf_session, tool);
+ PyObject *pyevent = pyrf_event__new(event, /*evsel=*/NULL, psession->session);
+ PyObject *ret;
+
+ if (pyevent == NULL)
+ return -ENOMEM;
+
+ ret = PyObject_CallFunction(psession->stat, "O", pyevent);
+ Py_XDECREF(ret);
+ Py_DECREF(pyevent);
+ return 0;
+}
+
static PyObject *pyrf_session__find_thread(struct pyrf_session *psession, PyObject *args)
{
struct machine *machine;
@@ -3322,13 +3478,13 @@ static PyObject *pyrf_session__find_thread(struct pyrf_session *psession, PyObje
static PyObject *pyrf_session__new(PyTypeObject *type, PyObject *args, PyObject *kwargs)
{
struct pyrf_data *pdata;
- PyObject *sample = NULL;
- static char *kwlist[] = { "data", "sample", NULL };
+ PyObject *sample = NULL, *stat = NULL;
+ static char *kwlist[] = { "data", "sample", "stat", NULL };
struct pyrf_session *psession;
struct perf_session *session;
- if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O!|O", kwlist, &pyrf_data__type, &pdata,
- &sample))
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O!|OO", kwlist, &pyrf_data__type, &pdata,
+ &sample, &stat))
return NULL;
psession = PyObject_New(struct pyrf_session, type);
@@ -3337,6 +3493,7 @@ static PyObject *pyrf_session__new(PyTypeObject *type, PyObject *args, PyObject
psession->session = NULL;
psession->sample = NULL;
+ psession->stat = NULL;
Py_INCREF(pdata);
psession->pdata = pdata;
@@ -3358,8 +3515,13 @@ static PyObject *pyrf_session__new(PyTypeObject *type, PyObject *args, PyObject
} while (0)
ADD_TOOL(sample);
+ ADD_TOOL(stat);
#undef ADD_TOOL
+ if (stat)
+ psession->tool.stat_round = pyrf_session_tool__stat_round;
+
+
psession->tool.comm = perf_event__process_comm;
psession->tool.mmap = perf_event__process_mmap;
psession->tool.mmap2 = perf_event__process_mmap2;
@@ -3399,6 +3561,7 @@ static void pyrf_session__delete(struct pyrf_session *psession)
perf_session__delete(psession->session);
Py_XDECREF(psession->pdata);
Py_XDECREF(psession->sample);
+ Py_XDECREF(psession->stat);
Py_TYPE(psession)->tp_free((PyObject *)psession);
}
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 20/58] perf python: Add syscall name/id to convert syscall number and name
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Use perf's syscalltbl support to convert syscall number to name
assuming the number is for the host machine. This avoids python
libaudit support as tools/perf/scripts/python/syscall-counts.py
requires.
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
v2:
1. Guarded with HAVE_LIBTRACEEVENT : Wrapped the syscall functions and
their entries in perf__methods with #ifdef HAVE_LIBTRACEEVENT to
avoid potential linker errors if CONFIG_TRACE is disabled.
2. Changed Exception Type: Updated pyrf__syscall_id to raise a
ValueError instead of a TypeError when a syscall is not found.
3. Fixed Typo: Corrected "name number" to "name" in the docstring for
syscall_id.
v6:
- Added optional keyword-only `elf_machine` argument to `syscall_name`
and `syscall_id`.
v7:
- Made syscalltbl.o unconditional in Build to fix undefined symbol
when building without libtraceevent.
---
tools/perf/util/Build | 2 +-
tools/perf/util/python.c | 48 ++++++++++++++++++++++++++++++++++++++++
2 files changed, 49 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 70cc91d00804..fd55d02dd433 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -75,7 +75,7 @@ perf-util-y += sample.o
perf-util-y += sample-raw.o
perf-util-y += s390-sample-raw.o
perf-util-y += amd-sample-raw.o
-perf-util-$(CONFIG_TRACE) += syscalltbl.o
+perf-util-y += syscalltbl.o
perf-util-y += ordered-events.o
perf-util-y += namespaces.o
perf-util-y += comm.o
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index c947abf8affe..69d443c504d3 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -16,6 +16,7 @@
#include "data.h"
#include "debug.h"
#include "dso.h"
+#include "dwarf-regs.h"
#include "event.h"
#include "branch.h"
#include "evlist.h"
@@ -33,6 +34,7 @@
#include "srcline.h"
#include "strbuf.h"
#include "symbol.h"
+#include "syscalltbl.h"
#include "thread.h"
#include "thread_map.h"
#include "tool.h"
@@ -3785,6 +3787,40 @@ static int pyrf_session__setup_types(void)
return PyType_Ready(&pyrf_session__type);
}
+static PyObject *pyrf__syscall_name(PyObject *self, PyObject *args, PyObject *kwargs)
+{
+ const char *name;
+ int id;
+ int elf_machine = EM_HOST;
+ static char * const kwlist[] = { "id", "elf_machine", NULL };
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|$i", kwlist, &id, &elf_machine))
+ return NULL;
+
+ name = syscalltbl__name(elf_machine, id);
+ if (!name)
+ Py_RETURN_NONE;
+ return PyUnicode_FromString(name);
+}
+
+static PyObject *pyrf__syscall_id(PyObject *self, PyObject *args, PyObject *kwargs)
+{
+ const char *name;
+ int id;
+ int elf_machine = EM_HOST;
+ static char * const kwlist[] = { "name", "elf_machine", NULL };
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "s|$i", kwlist, &name, &elf_machine))
+ return NULL;
+
+ id = syscalltbl__id(elf_machine, name);
+ if (id < 0) {
+ PyErr_Format(PyExc_ValueError, "Failed to find syscall %s", name);
+ return NULL;
+ }
+ return PyLong_FromLong(id);
+}
+
static PyMethodDef perf__methods[] = {
{
.ml_name = "metrics",
@@ -3818,6 +3854,18 @@ static PyMethodDef perf__methods[] = {
.ml_flags = METH_NOARGS,
.ml_doc = PyDoc_STR("Returns a sequence of pmus.")
},
+ {
+ .ml_name = "syscall_name",
+ .ml_meth = (PyCFunction) pyrf__syscall_name,
+ .ml_flags = METH_VARARGS | METH_KEYWORDS,
+ .ml_doc = PyDoc_STR("Turns a syscall number to a string.")
+ },
+ {
+ .ml_name = "syscall_id",
+ .ml_meth = (PyCFunction) pyrf__syscall_id,
+ .ml_flags = METH_VARARGS | METH_KEYWORDS,
+ .ml_doc = PyDoc_STR("Turns a syscall name to a number.")
+ },
{ .ml_name = NULL, }
};
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 09/58] perf evlist: Add reference count
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
This a no-op for most of the perf tool. The reference count is set to
1 at allocation, the put will see the 1, decrement it and perform the
delete. The purpose for adding the reference count is for the python
code. Prior to this change the python code would clone evlists, but
this has issues if events are opened, etc. This change adds a
reference count for the evlists and a later change will add it to
evsels. The combination is needed for the python code to operate
correctly (not hit asserts in the evsel clone), but the changes are
broken apart for the sake of smaller patches.
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
v2: Added evlist__put to pyrf_evlist__init in case init is called more
than once.
I double-checked trace__replay() and confirmed that trace->evlist
is not assigned to session->evlist in that function.
trace__replay creates a new session and uses its own evlist for
processing file events, leaving trace->evlist pointing to the
empty list created at startup. Therefore, the
evlist__put(trace->evlist) call in trace__exit() is safe and
correct to avoid leaking that empty list.
v7:
- Added pyrf_evlist__new to zero-initialize pevlist->evlist to fix
crash on re-initialization.
---
tools/perf/arch/x86/tests/hybrid.c | 2 +-
tools/perf/arch/x86/tests/topdown.c | 2 +-
tools/perf/arch/x86/util/iostat.c | 2 +-
tools/perf/bench/evlist-open-close.c | 18 +-
tools/perf/builtin-ftrace.c | 8 +-
tools/perf/builtin-kvm.c | 4 +-
tools/perf/builtin-lock.c | 2 +-
tools/perf/builtin-record.c | 4 +-
tools/perf/builtin-sched.c | 6 +-
tools/perf/builtin-script.c | 2 +-
tools/perf/builtin-stat.c | 10 +-
tools/perf/builtin-top.c | 52 ++---
tools/perf/builtin-trace.c | 26 +--
tools/perf/tests/backward-ring-buffer.c | 18 +-
tools/perf/tests/code-reading.c | 4 +-
tools/perf/tests/event-times.c | 4 +-
tools/perf/tests/event_update.c | 2 +-
tools/perf/tests/evsel-roundtrip-name.c | 8 +-
tools/perf/tests/expand-cgroup.c | 8 +-
tools/perf/tests/hists_cumulate.c | 2 +-
tools/perf/tests/hists_filter.c | 2 +-
tools/perf/tests/hists_link.c | 2 +-
tools/perf/tests/hists_output.c | 2 +-
tools/perf/tests/hwmon_pmu.c | 2 +-
tools/perf/tests/keep-tracking.c | 2 +-
tools/perf/tests/mmap-basic.c | 18 +-
tools/perf/tests/openat-syscall-tp-fields.c | 18 +-
tools/perf/tests/parse-events.c | 4 +-
tools/perf/tests/parse-metric.c | 4 +-
tools/perf/tests/parse-no-sample-id-all.c | 2 +-
tools/perf/tests/perf-record.c | 18 +-
tools/perf/tests/perf-time-to-tsc.c | 2 +-
tools/perf/tests/pfm.c | 4 +-
tools/perf/tests/pmu-events.c | 6 +-
tools/perf/tests/pmu.c | 4 +-
tools/perf/tests/sw-clock.c | 14 +-
tools/perf/tests/switch-tracking.c | 2 +-
tools/perf/tests/task-exit.c | 14 +-
tools/perf/tests/tool_pmu.c | 2 +-
tools/perf/tests/topology.c | 2 +-
tools/perf/util/cgroup.c | 4 +-
tools/perf/util/data-convert-bt.c | 2 +-
tools/perf/util/evlist.c | 20 +-
tools/perf/util/evlist.h | 7 +-
tools/perf/util/expr.c | 2 +-
| 12 +-
tools/perf/util/metricgroup.c | 6 +-
tools/perf/util/parse-events.c | 4 +-
tools/perf/util/perf_api_probe.c | 2 +-
tools/perf/util/python.c | 212 ++++++++------------
tools/perf/util/record.c | 2 +-
tools/perf/util/session.c | 2 +-
tools/perf/util/sideband_evlist.c | 16 +-
53 files changed, 279 insertions(+), 320 deletions(-)
diff --git a/tools/perf/arch/x86/tests/hybrid.c b/tools/perf/arch/x86/tests/hybrid.c
index e221ea104174..dfb0ffc0d030 100644
--- a/tools/perf/arch/x86/tests/hybrid.c
+++ b/tools/perf/arch/x86/tests/hybrid.c
@@ -268,7 +268,7 @@ static int test_event(const struct evlist_test *e)
ret = e->check(evlist);
}
parse_events_error__exit(&err);
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
diff --git a/tools/perf/arch/x86/tests/topdown.c b/tools/perf/arch/x86/tests/topdown.c
index 3ee4e5e71be3..2d0ae5b0d76c 100644
--- a/tools/perf/arch/x86/tests/topdown.c
+++ b/tools/perf/arch/x86/tests/topdown.c
@@ -56,7 +56,7 @@ static int event_cb(void *state, struct pmu_event_info *info)
*ret = TEST_FAIL;
}
}
- evlist__delete(evlist);
+ evlist__put(evlist);
return 0;
}
diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c
index 7442a2cd87ed..e0417552b0cb 100644
--- a/tools/perf/arch/x86/util/iostat.c
+++ b/tools/perf/arch/x86/util/iostat.c
@@ -337,7 +337,7 @@ int iostat_prepare(struct evlist *evlist, struct perf_stat_config *config)
if (evlist->core.nr_entries > 0) {
pr_warning("The -e and -M options are not supported."
"All chosen events/metrics will be dropped\n");
- evlist__delete(evlist);
+ evlist__put(evlist);
evlist = evlist__new();
if (!evlist)
return -ENOMEM;
diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c
index faf9c34b4a5d..304929d1f67f 100644
--- a/tools/perf/bench/evlist-open-close.c
+++ b/tools/perf/bench/evlist-open-close.c
@@ -76,7 +76,7 @@ static struct evlist *bench__create_evlist(char *evstr, const char *uid_str)
parse_events_error__exit(&err);
pr_err("Run 'perf list' for a list of valid events\n");
ret = 1;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
parse_events_error__exit(&err);
if (uid_str) {
@@ -85,24 +85,24 @@ static struct evlist *bench__create_evlist(char *evstr, const char *uid_str)
if (uid == UINT_MAX) {
pr_err("Invalid User: %s", uid_str);
ret = -EINVAL;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
ret = parse_uid_filter(evlist, uid);
if (ret)
- goto out_delete_evlist;
+ goto out_put_evlist;
}
ret = evlist__create_maps(evlist, &opts.target);
if (ret < 0) {
pr_err("Not enough memory to create thread/cpu maps\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist__config(evlist, &opts, NULL);
return evlist;
-out_delete_evlist:
- evlist__delete(evlist);
+out_put_evlist:
+ evlist__put(evlist);
return NULL;
}
@@ -151,7 +151,7 @@ static int bench_evlist_open_close__run(char *evstr, const char *uid_str)
evlist->core.nr_entries, evlist__count_evsel_fds(evlist));
printf(" Number of iterations:\t%d\n", iterations);
- evlist__delete(evlist);
+ evlist__put(evlist);
for (i = 0; i < iterations; i++) {
pr_debug("Started iteration %d\n", i);
@@ -162,7 +162,7 @@ static int bench_evlist_open_close__run(char *evstr, const char *uid_str)
gettimeofday(&start, NULL);
err = bench__do_evlist_open_close(evlist);
if (err) {
- evlist__delete(evlist);
+ evlist__put(evlist);
return err;
}
@@ -171,7 +171,7 @@ static int bench_evlist_open_close__run(char *evstr, const char *uid_str)
runtime_us = timeval2usec(&diff);
update_stats(&time_stats, runtime_us);
- evlist__delete(evlist);
+ evlist__put(evlist);
pr_debug("Iteration %d took:\t%" PRIu64 "us\n", i, runtime_us);
}
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 8a7dbfb14535..676239148b87 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -1999,20 +1999,20 @@ int cmd_ftrace(int argc, const char **argv)
ret = evlist__create_maps(ftrace.evlist, &ftrace.target);
if (ret < 0)
- goto out_delete_evlist;
+ goto out_put_evlist;
if (argc) {
ret = evlist__prepare_workload(ftrace.evlist, &ftrace.target,
argv, false,
ftrace__workload_exec_failed_signal);
if (ret < 0)
- goto out_delete_evlist;
+ goto out_put_evlist;
}
ret = cmd_func(&ftrace);
-out_delete_evlist:
- evlist__delete(ftrace.evlist);
+out_put_evlist:
+ evlist__put(ftrace.evlist);
out_delete_filters:
delete_filter_func(&ftrace.filters);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 0c5e6b3aac74..d88855e3c7b4 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1811,7 +1811,7 @@ static struct evlist *kvm_live_event_list(void)
out:
if (err) {
- evlist__delete(evlist);
+ evlist__put(evlist);
evlist = NULL;
}
@@ -1942,7 +1942,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
out:
perf_session__delete(kvm->session);
kvm->session = NULL;
- evlist__delete(kvm->evlist);
+ evlist__put(kvm->evlist);
return err;
}
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 5585aeb97684..c40d070f6c36 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -2145,7 +2145,7 @@ static int __cmd_contention(int argc, const char **argv)
out_delete:
lock_filter_finish();
- evlist__delete(con.evlist);
+ evlist__put(con.evlist);
lock_contention_finish(&con);
perf_session__delete(session);
perf_env__exit(&host_env);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4a5eba498c02..b4fffa936e01 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -4289,7 +4289,7 @@ int cmd_record(int argc, const char **argv)
goto out;
evlist__splice_list_tail(rec->evlist, &def_evlist->core.entries);
- evlist__delete(def_evlist);
+ evlist__put(def_evlist);
}
if (rec->opts.target.tid && !rec->opts.no_inherit_set)
@@ -4397,7 +4397,7 @@ int cmd_record(int argc, const char **argv)
auxtrace_record__free(rec->itr);
out_opts:
evlist__close_control(rec->opts.ctl_fd, rec->opts.ctl_fd_ack, &rec->opts.ctl_fd_close);
- evlist__delete(rec->evlist);
+ evlist__put(rec->evlist);
return err;
}
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 9ecda631b3ab..b3d96c4774b6 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3829,7 +3829,7 @@ static int perf_sched__schedstat_record(struct perf_sched *sched,
session = perf_session__new(&data, &sched->tool);
if (IS_ERR(session)) {
pr_err("Perf session creation failed.\n");
- evlist__delete(evlist);
+ evlist__put(evlist);
return PTR_ERR(session);
}
@@ -3925,7 +3925,7 @@ static int perf_sched__schedstat_record(struct perf_sched *sched,
else
fprintf(stderr, "[ perf sched stats: Failed !! ]\n");
- evlist__delete(evlist);
+ evlist__put(evlist);
close(fd);
return err;
}
@@ -4787,7 +4787,7 @@ static int perf_sched__schedstat_live(struct perf_sched *sched,
free_cpu_domain_info(cd_map, sv, nr);
out:
free_schedstat(&cpu_head);
- evlist__delete(evlist);
+ evlist__put(evlist);
return err;
}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 853b141a0d50..0ead134940d5 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2269,7 +2269,7 @@ static int script_find_metrics(const struct pmu_metric *pm,
}
pr_debug("Found metric '%s' whose evsels match those of in the perf data\n",
pm->metric_name);
- evlist__delete(metric_evlist);
+ evlist__put(metric_evlist);
out:
return 0;
}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 99d7db372b48..bfa3512e1686 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2113,7 +2113,7 @@ static int add_default_events(void)
stat_config.user_requested_cpu_list,
stat_config.system_wide,
stat_config.hardware_aware_grouping) < 0) {
- evlist__delete(metric_evlist);
+ evlist__put(metric_evlist);
ret = -1;
break;
}
@@ -2125,7 +2125,7 @@ static int add_default_events(void)
metricgroup__copy_metric_events(evlist, /*cgrp=*/NULL,
&evlist->metric_events,
&metric_evlist->metric_events);
- evlist__delete(metric_evlist);
+ evlist__put(metric_evlist);
}
list_sort(/*priv=*/NULL, &evlist->core.entries, default_evlist_evsel_cmp);
@@ -2146,7 +2146,7 @@ static int add_default_events(void)
metricgroup__copy_metric_events(evsel_list, /*cgrp=*/NULL,
&evsel_list->metric_events,
&evlist->metric_events);
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
@@ -2381,7 +2381,7 @@ static int __cmd_report(int argc, const char **argv)
perf_stat.session = session;
stat_config.output = stderr;
- evlist__delete(evsel_list);
+ evlist__put(evsel_list);
evsel_list = session->evlist;
ret = perf_session__process_events(session);
@@ -3060,7 +3060,7 @@ int cmd_stat(int argc, const char **argv)
if (smi_cost && smi_reset)
sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
- evlist__delete(evsel_list);
+ evlist__put(evsel_list);
evlist__close_control(stat_config.ctl_fd, stat_config.ctl_fd_ack, &stat_config.ctl_fd_close);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index f6eb543de537..c509cfef8285 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1652,14 +1652,14 @@ int cmd_top(int argc, const char **argv)
perf_env__init(&host_env);
status = perf_config(perf_top_config, &top);
if (status)
- goto out_delete_evlist;
+ goto out_put_evlist;
/*
* Since the per arch annotation init routine may need the cpuid, read
* it here, since we are not getting this from the perf.data header.
*/
status = perf_env__set_cmdline(&host_env, argc, argv);
if (status)
- goto out_delete_evlist;
+ goto out_put_evlist;
status = perf_env__read_cpuid(&host_env);
if (status) {
@@ -1680,30 +1680,30 @@ int cmd_top(int argc, const char **argv)
annotate_opts.disassembler_style = strdup(disassembler_style);
if (!annotate_opts.disassembler_style) {
status = -ENOMEM;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
}
if (objdump_path) {
annotate_opts.objdump_path = strdup(objdump_path);
if (!annotate_opts.objdump_path) {
status = -ENOMEM;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
}
if (addr2line_path) {
symbol_conf.addr2line_path = strdup(addr2line_path);
if (!symbol_conf.addr2line_path) {
status = -ENOMEM;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
}
status = symbol__validate_sym_arguments();
if (status)
- goto out_delete_evlist;
+ goto out_put_evlist;
if (annotate_check_args() < 0)
- goto out_delete_evlist;
+ goto out_put_evlist;
status = target__validate(target);
if (status) {
@@ -1718,15 +1718,15 @@ int cmd_top(int argc, const char **argv)
struct evlist *def_evlist = evlist__new_default(target, callchain_param.enabled);
if (!def_evlist)
- goto out_delete_evlist;
+ goto out_put_evlist;
evlist__splice_list_tail(top.evlist, &def_evlist->core.entries);
- evlist__delete(def_evlist);
+ evlist__put(def_evlist);
}
status = evswitch__init(&top.evswitch, top.evlist, stderr);
if (status)
- goto out_delete_evlist;
+ goto out_put_evlist;
if (symbol_conf.report_hierarchy) {
/* disable incompatible options */
@@ -1737,18 +1737,18 @@ int cmd_top(int argc, const char **argv)
pr_err("Error: --hierarchy and --fields options cannot be used together\n");
parse_options_usage(top_usage, options, "fields", 0);
parse_options_usage(NULL, options, "hierarchy", 0);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
}
if (top.stitch_lbr && !(callchain_param.record_mode == CALLCHAIN_LBR)) {
pr_err("Error: --stitch-lbr must be used with --call-graph lbr\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (nr_cgroups > 0 && opts->record_cgroup) {
pr_err("--cgroup and --all-cgroups cannot be used together\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (branch_call_mode) {
@@ -1772,7 +1772,7 @@ int cmd_top(int argc, const char **argv)
status = perf_env__read_core_pmu_caps(&host_env);
if (status) {
pr_err("PMU capability data is not available\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
}
@@ -1795,7 +1795,7 @@ int cmd_top(int argc, const char **argv)
if (IS_ERR(top.session)) {
status = PTR_ERR(top.session);
top.session = NULL;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
top.evlist->session = top.session;
@@ -1805,7 +1805,7 @@ int cmd_top(int argc, const char **argv)
if (field_order)
parse_options_usage(sort_order ? NULL : top_usage,
options, "fields", 0);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (top.uid_str) {
@@ -1814,18 +1814,18 @@ int cmd_top(int argc, const char **argv)
if (uid == UINT_MAX) {
ui__error("Invalid User: %s", top.uid_str);
status = -EINVAL;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
status = parse_uid_filter(top.evlist, uid);
if (status)
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (evlist__create_maps(top.evlist, target) < 0) {
ui__error("Couldn't create thread/CPU maps: %s\n",
errno == ENOENT ? "No such process" : str_error_r(errno, errbuf, sizeof(errbuf)));
status = -errno;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (top.delay_secs < 1)
@@ -1833,7 +1833,7 @@ int cmd_top(int argc, const char **argv)
if (record_opts__config(opts)) {
status = -EINVAL;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
top.sym_evsel = evlist__first(top.evlist);
@@ -1848,14 +1848,14 @@ int cmd_top(int argc, const char **argv)
status = symbol__annotation_init();
if (status < 0)
- goto out_delete_evlist;
+ goto out_put_evlist;
annotation_config__init();
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
status = symbol__init(NULL);
if (status < 0)
- goto out_delete_evlist;
+ goto out_put_evlist;
sort__setup_elide(stdout);
@@ -1875,13 +1875,13 @@ int cmd_top(int argc, const char **argv)
if (top.sb_evlist == NULL) {
pr_err("Couldn't create side band evlist.\n.");
status = -EINVAL;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (evlist__add_bpf_sb_event(top.sb_evlist, &host_env)) {
pr_err("Couldn't ask for PERF_RECORD_BPF_EVENT side band events.\n.");
status = -EINVAL;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
}
#endif
@@ -1896,8 +1896,8 @@ int cmd_top(int argc, const char **argv)
if (!opts->no_bpf_event)
evlist__stop_sb_thread(top.sb_evlist);
-out_delete_evlist:
- evlist__delete(top.evlist);
+out_put_evlist:
+ evlist__put(top.evlist);
perf_session__delete(top.session);
annotation_options__exit();
perf_env__exit(&host_env);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e58c49d047a2..da703d762433 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -4388,7 +4388,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
if (trace->summary_bpf) {
if (trace_prepare_bpf_summary(trace->summary_mode) < 0)
- goto out_delete_evlist;
+ goto out_put_evlist;
if (trace->summary_only)
goto create_maps;
@@ -4456,19 +4456,19 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
err = evlist__create_maps(evlist, &trace->opts.target);
if (err < 0) {
fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
err = trace__symbols_init(trace, argc, argv, evlist);
if (err < 0) {
fprintf(trace->output, "Problems initializing symbol libraries!\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (trace->summary_mode == SUMMARY__BY_TOTAL && !trace->summary_bpf) {
trace->syscall_stats = alloc_syscall_stats();
if (!trace->syscall_stats)
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist__config(evlist, &trace->opts, &callchain_param);
@@ -4477,7 +4477,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
err = evlist__prepare_workload(evlist, &trace->opts.target, argv, false, NULL);
if (err < 0) {
fprintf(trace->output, "Couldn't run the workload!\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
workload_pid = evlist->workload.pid;
}
@@ -4525,7 +4525,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
err = trace__expand_filters(trace, &evsel);
if (err)
- goto out_delete_evlist;
+ goto out_put_evlist;
err = evlist__apply_filters(evlist, &evsel, &trace->opts.target);
if (err < 0)
goto out_error_apply_filters;
@@ -4642,12 +4642,12 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
}
}
-out_delete_evlist:
+out_put_evlist:
trace_cleanup_bpf_summary();
delete_syscall_stats(trace->syscall_stats);
trace__symbols__exit(trace);
evlist__free_syscall_tp_fields(evlist);
- evlist__delete(evlist);
+ evlist__put(evlist);
cgroup__put(trace->cgroup);
trace->evlist = NULL;
trace->live = false;
@@ -4672,21 +4672,21 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
out_error:
fprintf(trace->output, "%s\n", errbuf);
- goto out_delete_evlist;
+ goto out_put_evlist;
out_error_apply_filters:
fprintf(trace->output,
"Failed to set filter \"%s\" on event %s: %m\n",
evsel->filter, evsel__name(evsel));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
out_error_mem:
fprintf(trace->output, "Not enough memory to run!\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
out_errno:
fprintf(trace->output, "%m\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
static int trace__replay(struct trace *trace)
@@ -5364,7 +5364,7 @@ static void trace__exit(struct trace *trace)
zfree(&trace->syscalls.table);
}
zfree(&trace->perfconfig_events);
- evlist__delete(trace->evlist);
+ evlist__put(trace->evlist);
trace->evlist = NULL;
ordered_events__free(&trace->oe.data);
#ifdef HAVE_LIBBPF_SUPPORT
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index c5e7999f2817..2b49b002d749 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -111,7 +111,7 @@ static int test__backward_ring_buffer(struct test_suite *test __maybe_unused, in
err = evlist__create_maps(evlist, &opts.target);
if (err < 0) {
pr_debug("Not enough memory to create thread/cpu maps\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
parse_events_error__init(&parse_error);
@@ -124,7 +124,7 @@ static int test__backward_ring_buffer(struct test_suite *test __maybe_unused, in
if (err) {
pr_debug("Failed to parse tracepoint event, try use root\n");
ret = TEST_SKIP;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist__config(evlist, &opts, NULL);
@@ -133,19 +133,19 @@ static int test__backward_ring_buffer(struct test_suite *test __maybe_unused, in
if (err < 0) {
pr_debug("perf_evlist__open: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
ret = TEST_FAIL;
err = do_test(evlist, opts.mmap_pages, &sample_count,
&comm_count);
if (err != TEST_OK)
- goto out_delete_evlist;
+ goto out_put_evlist;
if ((sample_count != NR_ITERS) || (comm_count != NR_ITERS)) {
pr_err("Unexpected counter: sample_count=%d, comm_count=%d\n",
sample_count, comm_count);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist__close(evlist);
@@ -154,16 +154,16 @@ static int test__backward_ring_buffer(struct test_suite *test __maybe_unused, in
if (err < 0) {
pr_debug("perf_evlist__open: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
err = do_test(evlist, 1, &sample_count, &comm_count);
if (err != TEST_OK)
- goto out_delete_evlist;
+ goto out_put_evlist;
ret = TEST_OK;
-out_delete_evlist:
- evlist__delete(evlist);
+out_put_evlist:
+ evlist__put(evlist);
return ret;
}
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 47043a3a2fb4..fc65a17f67f7 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -807,7 +807,7 @@ static int do_test_code_reading(bool try_kcore)
}
perf_evlist__set_maps(&evlist->core, NULL, NULL);
- evlist__delete(evlist);
+ evlist__put(evlist);
evlist = NULL;
continue;
}
@@ -844,7 +844,7 @@ static int do_test_code_reading(bool try_kcore)
out_put:
thread__put(thread);
out_err:
- evlist__delete(evlist);
+ evlist__put(evlist);
perf_cpu_map__put(cpus);
perf_thread_map__put(threads);
machine__delete(machine);
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index ae3b98bb42cf..94ab54ecd3f9 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -186,7 +186,7 @@ static int test_times(int (attach)(struct evlist *),
err = attach(evlist);
if (err == TEST_SKIP) {
pr_debug(" SKIP : not enough rights\n");
- evlist__delete(evlist);
+ evlist__put(evlist);
return err;
}
@@ -205,7 +205,7 @@ static int test_times(int (attach)(struct evlist *),
count.ena, count.run);
out_err:
- evlist__delete(evlist);
+ evlist__put(evlist);
return !err ? TEST_OK : TEST_FAIL;
}
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index facc65e29f20..73141b122d2f 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -117,7 +117,7 @@ static int test__event_update(struct test_suite *test __maybe_unused, int subtes
TEST_ASSERT_VAL("failed to synthesize attr update cpus",
!perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));
- evlist__delete(evlist);
+ evlist__put(evlist);
return 0;
}
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 1922cac13a24..6a220634c52f 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -33,7 +33,7 @@ static int perf_evsel__roundtrip_cache_name_test(void)
if (err) {
pr_debug("Failure to parse cache event '%s' possibly as PMUs don't support it",
name);
- evlist__delete(evlist);
+ evlist__put(evlist);
continue;
}
evlist__for_each_entry(evlist, evsel) {
@@ -42,7 +42,7 @@ static int perf_evsel__roundtrip_cache_name_test(void)
ret = TEST_FAIL;
}
}
- evlist__delete(evlist);
+ evlist__put(evlist);
}
}
}
@@ -66,7 +66,7 @@ static int perf_evsel__name_array_test(const char *const names[], int nr_names)
if (err) {
pr_debug("failed to parse event '%s', err %d\n",
names[i], err);
- evlist__delete(evlist);
+ evlist__put(evlist);
ret = TEST_FAIL;
continue;
}
@@ -76,7 +76,7 @@ static int perf_evsel__name_array_test(const char *const names[], int nr_names)
ret = TEST_FAIL;
}
}
- evlist__delete(evlist);
+ evlist__put(evlist);
}
return ret;
}
diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c
index dd547f2f77cc..a7a445f12693 100644
--- a/tools/perf/tests/expand-cgroup.c
+++ b/tools/perf/tests/expand-cgroup.c
@@ -106,7 +106,7 @@ static int expand_default_events(void)
TEST_ASSERT_VAL("failed to get evlist", evlist);
ret = test_expand_events(evlist);
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
@@ -133,7 +133,7 @@ static int expand_group_events(void)
ret = test_expand_events(evlist);
out:
parse_events_error__exit(&err);
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
@@ -164,7 +164,7 @@ static int expand_libpfm_events(void)
ret = test_expand_events(evlist);
out:
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
@@ -188,7 +188,7 @@ static int expand_metric_events(void)
ret = test_expand_events(evlist);
out:
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 606aa926a8fc..eca4ecb63ca8 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -744,7 +744,7 @@ static int test__hists_cumulate(struct test_suite *test __maybe_unused, int subt
out:
/* tear down everything */
- evlist__delete(evlist);
+ evlist__put(evlist);
machines__exit(&machines);
put_fake_samples();
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index cc6b26e373d1..0d09dc306019 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -332,7 +332,7 @@ static int test__hists_filter(struct test_suite *test __maybe_unused, int subtes
out:
/* tear down everything */
- evlist__delete(evlist);
+ evlist__put(evlist);
reset_output_field();
machines__exit(&machines);
put_fake_samples();
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 996f5f0b3bd1..9646c3b7b4de 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -352,7 +352,7 @@ static int test__hists_link(struct test_suite *test __maybe_unused, int subtest
out:
/* tear down everything */
- evlist__delete(evlist);
+ evlist__put(evlist);
reset_output_field();
machines__exit(&machines);
put_fake_samples();
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 7818950d786e..3f3bc978553e 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -631,7 +631,7 @@ static int test__hists_output(struct test_suite *test __maybe_unused, int subtes
out:
/* tear down everything */
- evlist__delete(evlist);
+ evlist__put(evlist);
machines__exit(&machines);
put_fake_samples();
diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index ada6e445c4c4..1b60c3a900f1 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -214,7 +214,7 @@ static int do_test(size_t i, bool with_pmu, bool with_alias)
out:
parse_events_error__exit(&err);
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 729cc9cc1cb7..51cfd6522867 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -153,7 +153,7 @@ static int test__keep_tracking(struct test_suite *test __maybe_unused, int subte
out_err:
if (evlist) {
evlist__disable(evlist);
- evlist__delete(evlist);
+ evlist__put(evlist);
}
perf_cpu_map__put(cpus);
perf_thread_map__put(threads);
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 8d04f6edb004..e6501791c505 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -94,7 +94,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
/* Permissions failure, flag the failure as a skip. */
err = TEST_SKIP;
}
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evsels[i]->core.attr.wakeup_events = 1;
@@ -106,7 +106,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
nr_events[i] = 0;
@@ -116,7 +116,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
if (evlist__mmap(evlist, 128) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
str_error_r(errno, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
for (i = 0; i < nsyscalls; ++i)
@@ -134,7 +134,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
if (event->header.type != PERF_RECORD_SAMPLE) {
pr_debug("unexpected %s event\n",
perf_event__name(event->header.type));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
perf_sample__init(&sample, /*all=*/false);
@@ -142,7 +142,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
if (err) {
pr_err("Can't parse sample, err = %d\n", err);
perf_sample__exit(&sample);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
err = -1;
@@ -151,7 +151,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
if (evsel == NULL) {
pr_debug("event with id %" PRIu64
" doesn't map to an evsel\n", sample.id);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
nr_events[evsel->core.idx]++;
perf_mmap__consume(&md->core);
@@ -166,12 +166,12 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
expected_nr_events[evsel->core.idx],
evsel__name(evsel), nr_events[evsel->core.idx]);
err = -1;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
}
-out_delete_evlist:
- evlist__delete(evlist);
+out_put_evlist:
+ evlist__put(evlist);
out_free_cpus:
perf_cpu_map__put(cpus);
out_free_threads:
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 2a139d2781a8..3ff595c7a86a 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -51,7 +51,7 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused
if (IS_ERR(evsel)) {
pr_debug("%s: evsel__newtp\n", __func__);
ret = PTR_ERR(evsel) == -EACCES ? TEST_SKIP : TEST_FAIL;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist__add(evlist, evsel);
@@ -59,7 +59,7 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused
err = evlist__create_maps(evlist, &opts.target);
if (err < 0) {
pr_debug("%s: evlist__create_maps\n", __func__);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evsel__config(evsel, &opts, NULL);
@@ -70,14 +70,14 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused
if (err < 0) {
pr_debug("perf_evlist__open: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
err = evlist__mmap(evlist, UINT_MAX);
if (err < 0) {
pr_debug("evlist__mmap: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist__enable(evlist);
@@ -115,7 +115,7 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused
if (err) {
pr_debug("Can't parse sample, err = %d\n", err);
perf_sample__exit(&sample);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
tp_flags = evsel__intval(evsel, &sample, "flags");
@@ -123,7 +123,7 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused
if (flags != tp_flags) {
pr_debug("%s: Expected flags=%#x, got %#x\n",
__func__, flags, tp_flags);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
goto out_ok;
@@ -136,13 +136,13 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused
if (++nr_polls > 5) {
pr_debug("%s: no events!\n", __func__);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
}
out_ok:
ret = TEST_OK;
-out_delete_evlist:
- evlist__delete(evlist);
+out_put_evlist:
+ evlist__put(evlist);
out:
return ret;
}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 05c3e899b425..19dc7b7475d2 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -2568,7 +2568,7 @@ static int test_event(const struct evlist_test *e)
ret = e->check(evlist);
}
parse_events_error__exit(&err);
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
@@ -2594,7 +2594,7 @@ static int test_event_fake_pmu(const char *str)
}
parse_events_error__exit(&err);
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index 7c7f489a5eb0..3f0ec839c056 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -84,7 +84,7 @@ static int __compute_metric(const char *name, struct value *vals,
cpus = perf_cpu_map__new("0");
if (!cpus) {
- evlist__delete(evlist);
+ evlist__put(evlist);
return -ENOMEM;
}
@@ -113,7 +113,7 @@ static int __compute_metric(const char *name, struct value *vals,
/* ... cleanup. */
evlist__free_stats(evlist);
perf_cpu_map__put(cpus);
- evlist__delete(evlist);
+ evlist__put(evlist);
return err;
}
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 50e68b7d43aa..d5a8d065809e 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -49,7 +49,7 @@ static int process_events(union perf_event **events, size_t count)
for (i = 0; i < count && !err; i++)
err = process_event(&evlist, events[i]);
- evlist__delete(evlist);
+ evlist__put(evlist);
return err;
}
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index ad44cc68820b..f95752b2ed1c 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -105,7 +105,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
err = evlist__create_maps(evlist, &opts.target);
if (err < 0) {
pr_debug("Not enough memory to create thread/cpu maps\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
/*
@@ -117,7 +117,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
err = evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
if (err < 0) {
pr_debug("Couldn't run the workload!\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
/*
@@ -134,7 +134,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
pr_debug("sched__get_first_possible_cpu: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
evlist__cancel_workload(evlist);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
cpu = err;
@@ -146,7 +146,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
pr_debug("sched_setaffinity: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
evlist__cancel_workload(evlist);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
/*
@@ -158,7 +158,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
pr_debug("perf_evlist__open: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
evlist__cancel_workload(evlist);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
/*
@@ -171,7 +171,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
pr_debug("evlist__mmap: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
evlist__cancel_workload(evlist);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
/*
@@ -209,7 +209,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
if (verbose > 0)
perf_event__fprintf(event, NULL, stderr);
pr_debug("Couldn't parse sample\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (verbose > 0) {
@@ -350,9 +350,9 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
++errs;
}
-out_delete_evlist:
+out_put_evlist:
CPU_FREE(cpu_mask);
- evlist__delete(evlist);
+ evlist__put(evlist);
out:
perf_sample__exit(&sample);
if (err == -EACCES)
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index cca41bd37ae3..d3538fa20af3 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -201,7 +201,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
err = TEST_OK;
out_err:
- evlist__delete(evlist);
+ evlist__put(evlist);
perf_cpu_map__put(cpus);
perf_thread_map__put(threads);
return err;
diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c
index fca4a86452df..8d19b1bfecbc 100644
--- a/tools/perf/tests/pfm.c
+++ b/tools/perf/tests/pfm.c
@@ -80,7 +80,7 @@ static int test__pfm_events(struct test_suite *test __maybe_unused,
evlist__nr_groups(evlist),
0);
- evlist__delete(evlist);
+ evlist__put(evlist);
}
return 0;
}
@@ -165,7 +165,7 @@ static int test__pfm_group(struct test_suite *test __maybe_unused,
evlist__nr_groups(evlist),
table[i].nr_groups);
- evlist__delete(evlist);
+ evlist__put(evlist);
}
return 0;
}
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index a99716862168..236bbbad5773 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -797,7 +797,7 @@ static int check_parse_id(const char *id, struct parse_events_error *error)
/*warn_if_reordered=*/true, /*fake_tp=*/false);
free(dup);
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
@@ -844,7 +844,7 @@ static int test__parsing_callback(const struct pmu_metric *pm,
cpus = perf_cpu_map__new("0");
if (!cpus) {
- evlist__delete(evlist);
+ evlist__put(evlist);
return -ENOMEM;
}
@@ -899,7 +899,7 @@ static int test__parsing_callback(const struct pmu_metric *pm,
/* ... cleanup. */
evlist__free_stats(evlist);
perf_cpu_map__put(cpus);
- evlist__delete(evlist);
+ evlist__put(evlist);
return err;
}
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 0ebf2d7b2cb4..3d931c1f99dd 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -287,7 +287,7 @@ static int test__pmu_usr_chgs(struct test_suite *test __maybe_unused, int subtes
ret = TEST_OK;
err_out:
parse_events_terms__exit(&terms);
- evlist__delete(evlist);
+ evlist__put(evlist);
test_pmu_put(dir, pmu);
return ret;
}
@@ -339,7 +339,7 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest
ret = TEST_OK;
err_out:
parse_events_error__exit(&err);
- evlist__delete(evlist);
+ evlist__put(evlist);
test_pmu_put(dir, pmu);
return ret;
}
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index b6e46975379c..bb6b62cf51d1 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -59,7 +59,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
evsel = evsel__new(&attr);
if (evsel == NULL) {
pr_debug("evsel__new\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist__add(evlist, evsel);
@@ -68,7 +68,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
if (!cpus || !threads) {
err = -ENOMEM;
pr_debug("Not enough memory to create thread/cpu maps\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
perf_evlist__set_maps(&evlist->core, cpus, threads);
@@ -80,14 +80,14 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
str_error_r(errno, sbuf, sizeof(sbuf)),
knob, (u64)attr.sample_freq);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
err = evlist__mmap(evlist, 128);
if (err < 0) {
pr_debug("failed to mmap event: %d (%s)\n", errno,
str_error_r(errno, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist__enable(evlist);
@@ -113,7 +113,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
if (err < 0) {
pr_debug("Error during parse sample\n");
perf_sample__exit(&sample);
- goto out_delete_evlist;
+ goto out_put_evlist;
}
total_periods += sample.period;
@@ -131,10 +131,10 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
err = -1;
}
-out_delete_evlist:
+out_put_evlist:
perf_cpu_map__put(cpus);
perf_thread_map__put(threads);
- evlist__delete(evlist);
+ evlist__put(evlist);
return err;
}
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 72a8289e846d..306151c83af8 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -579,7 +579,7 @@ static int test__switch_tracking(struct test_suite *test __maybe_unused, int sub
out:
if (evlist) {
evlist__disable(evlist);
- evlist__delete(evlist);
+ evlist__put(evlist);
}
perf_cpu_map__put(cpus);
perf_thread_map__put(threads);
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 4053ff2813bb..a46650b10689 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -74,7 +74,7 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _
if (!cpus || !threads) {
err = -ENOMEM;
pr_debug("Not enough memory to create thread/cpu maps\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
perf_evlist__set_maps(&evlist->core, cpus, threads);
@@ -82,7 +82,7 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _
err = evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal);
if (err < 0) {
pr_debug("Couldn't run the workload!\n");
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evsel = evlist__first(evlist);
@@ -101,14 +101,14 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _
if (err < 0) {
pr_debug("Couldn't open the evlist: %s\n",
str_error_r(-err, sbuf, sizeof(sbuf)));
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (evlist__mmap(evlist, 128) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
str_error_r(errno, sbuf, sizeof(sbuf)));
err = -1;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist__start_workload(evlist);
@@ -133,7 +133,7 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _
if (retry_count++ > 1000) {
pr_debug("Failed after retrying 1000 times\n");
err = -1;
- goto out_delete_evlist;
+ goto out_put_evlist;
}
goto retry;
@@ -144,10 +144,10 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _
err = -1;
}
-out_delete_evlist:
+out_put_evlist:
perf_cpu_map__put(cpus);
perf_thread_map__put(threads);
- evlist__delete(evlist);
+ evlist__put(evlist);
return err;
}
diff --git a/tools/perf/tests/tool_pmu.c b/tools/perf/tests/tool_pmu.c
index 1e900ef92e37..e78ff9dcea97 100644
--- a/tools/perf/tests/tool_pmu.c
+++ b/tools/perf/tests/tool_pmu.c
@@ -67,7 +67,7 @@ static int do_test(enum tool_pmu_event ev, bool with_pmu)
out:
parse_events_error__exit(&err);
- evlist__delete(evlist);
+ evlist__put(evlist);
return ret;
}
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index f54502ebef4b..4ecf5d750313 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -57,7 +57,7 @@ static int session_write_header(char *path)
!perf_session__write_header(session, session->evlist,
perf_data__fd(&data), true));
- evlist__delete(session->evlist);
+ evlist__put(session->evlist);
perf_session__delete(session);
return 0;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 1b5664d1481f..652a45aac828 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -520,8 +520,8 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, bool open_cgro
cgrp_event_expanded = true;
out_err:
- evlist__delete(orig_list);
- evlist__delete(tmp_list);
+ evlist__put(orig_list);
+ evlist__put(tmp_list);
metricgroup__rblist_exit(&orig_metric_events);
release_cgroup_list();
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 3b8f2df823a9..a85ae53db7c5 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1363,7 +1363,7 @@ static void cleanup_events(struct perf_session *session)
zfree(&evsel->priv);
}
- evlist__delete(evlist);
+ evlist__put(evlist);
session->evlist = NULL;
}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 35d65fe50e06..b5a7895debf5 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -75,7 +75,7 @@ int sigqueue(pid_t pid, int sig, const union sigval value);
#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
#define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y)
-void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
+static void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
struct perf_thread_map *threads)
{
perf_evlist__init(&evlist->core);
@@ -88,6 +88,7 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
evlist->nr_br_cntr = -1;
metricgroup__rblist_init(&evlist->metric_events);
INIT_LIST_HEAD(&evlist->deferred_samples);
+ refcount_set(&evlist->refcnt, 1);
}
struct evlist *evlist__new(void)
@@ -139,7 +140,7 @@ struct evlist *evlist__new_default(const struct target *target, bool sample_call
return evlist;
out_err:
- evlist__delete(evlist);
+ evlist__put(evlist);
return NULL;
}
@@ -148,13 +149,19 @@ struct evlist *evlist__new_dummy(void)
struct evlist *evlist = evlist__new();
if (evlist && evlist__add_dummy(evlist)) {
- evlist__delete(evlist);
+ evlist__put(evlist);
evlist = NULL;
}
return evlist;
}
+struct evlist *evlist__get(struct evlist *evlist)
+{
+ refcount_inc(&evlist->refcnt);
+ return evlist;
+}
+
/**
* evlist__set_id_pos - set the positions of event ids.
* @evlist: selected event list
@@ -193,7 +200,7 @@ static void evlist__purge(struct evlist *evlist)
evlist->core.nr_entries = 0;
}
-void evlist__exit(struct evlist *evlist)
+static void evlist__exit(struct evlist *evlist)
{
metricgroup__rblist_exit(&evlist->metric_events);
event_enable_timer__exit(&evlist->eet);
@@ -202,11 +209,14 @@ void evlist__exit(struct evlist *evlist)
perf_evlist__exit(&evlist->core);
}
-void evlist__delete(struct evlist *evlist)
+void evlist__put(struct evlist *evlist)
{
if (evlist == NULL)
return;
+ if (!refcount_dec_and_test(&evlist->refcnt))
+ return;
+
evlist__free_stats(evlist);
evlist__munmap(evlist);
evlist__close(evlist);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index e54761c670b6..a9820a6aad5b 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -61,6 +61,7 @@ struct event_enable_timer;
struct evlist {
struct perf_evlist core;
+ refcount_t refcnt;
bool enabled;
bool no_affinity;
int id_pos;
@@ -109,10 +110,8 @@ struct evsel_str_handler {
struct evlist *evlist__new(void);
struct evlist *evlist__new_default(const struct target *target, bool sample_callchains);
struct evlist *evlist__new_dummy(void);
-void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
- struct perf_thread_map *threads);
-void evlist__exit(struct evlist *evlist);
-void evlist__delete(struct evlist *evlist);
+struct evlist *evlist__get(struct evlist *evlist);
+void evlist__put(struct evlist *evlist);
void evlist__add(struct evlist *evlist, struct evsel *entry);
void evlist__remove(struct evlist *evlist, struct evsel *evsel);
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 644769e92708..cf54bbbc8ddc 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -450,7 +450,7 @@ double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const
ret = parse_event(tmp, id) ? 0 : 1;
}
out:
- evlist__delete(tmp);
+ evlist__put(tmp);
return ret;
}
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f30e48eb3fc3..f9887d2fc8ed 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -4909,12 +4909,12 @@ int perf_session__read_header(struct perf_session *session)
evsel = evsel__new(&f_attr.attr);
if (evsel == NULL)
- goto out_delete_evlist;
+ goto out_put_evlist;
evsel->needs_swap = header->needs_swap;
/*
* Do it before so that if perf_evsel__alloc_id fails, this
- * entry gets purged too at evlist__delete().
+ * entry gets purged too at evlist__put().
*/
evlist__add(session->evlist, evsel);
@@ -4925,7 +4925,7 @@ int perf_session__read_header(struct perf_session *session)
* hattr->ids threads.
*/
if (perf_evsel__alloc_id(&evsel->core, 1, nr_ids))
- goto out_delete_evlist;
+ goto out_put_evlist;
lseek(fd, f_attr.ids.offset, SEEK_SET);
@@ -4944,7 +4944,7 @@ int perf_session__read_header(struct perf_session *session)
perf_file_section__process);
if (evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent))
- goto out_delete_evlist;
+ goto out_put_evlist;
#else
perf_header__process_sections(header, fd, NULL, perf_file_section__process);
#endif
@@ -4953,8 +4953,8 @@ int perf_session__read_header(struct perf_session *session)
out_errno:
return -errno;
-out_delete_evlist:
- evlist__delete(session->evlist);
+out_put_evlist:
+ evlist__put(session->evlist);
session->evlist = NULL;
return -ENOMEM;
}
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 4db9578efd81..191ec2d8a250 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -214,7 +214,7 @@ static void metric__free(struct metric *m)
zfree(&m->metric_refs);
expr__ctx_free(m->pctx);
zfree(&m->modifier);
- evlist__delete(m->evlist);
+ evlist__put(m->evlist);
free(m);
}
@@ -1335,7 +1335,7 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
parsed_evlist = NULL;
err_out:
parse_events_error__exit(&parse_error);
- evlist__delete(parsed_evlist);
+ evlist__put(parsed_evlist);
strbuf_release(&events);
return ret;
}
@@ -1546,7 +1546,7 @@ static int parse_groups(struct evlist *perf_evlist,
if (combined_evlist) {
evlist__splice_list_tail(perf_evlist, &combined_evlist->core.entries);
- evlist__delete(combined_evlist);
+ evlist__put(combined_evlist);
}
list_for_each_entry(m, &metric_list, nd) {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1497e1f2a08c..f0809be63ad8 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2316,7 +2316,7 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte
/*
* There are 2 users - builtin-record and builtin-test objects.
- * Both call evlist__delete in case of error, so we dont
+ * Both call evlist__put in case of error, so we dont
* need to bother.
*/
return ret;
@@ -2519,7 +2519,7 @@ int parse_events_option_new_evlist(const struct option *opt, const char *str, in
}
ret = parse_events_option(opt, str, unset);
if (ret) {
- evlist__delete(*args->evlistp);
+ evlist__put(*args->evlistp);
*args->evlistp = NULL;
}
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
index e1904a330b28..f61c4ec52827 100644
--- a/tools/perf/util/perf_api_probe.c
+++ b/tools/perf/util/perf_api_probe.c
@@ -57,7 +57,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, struct perf_cpu cpu, const cha
err = 0;
out_delete:
- evlist__delete(evlist);
+ evlist__put(evlist);
return err;
}
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 1e6c99efff90..aeecdb497fac 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -1272,7 +1272,7 @@ static int pyrf_evsel__setup_types(void)
struct pyrf_evlist {
PyObject_HEAD
- struct evlist evlist;
+ struct evlist *evlist;
};
static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
@@ -1285,15 +1285,22 @@ static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads))
return -1;
+ evlist__put(pevlist->evlist);
+ pevlist->evlist = evlist__new();
+ if (!pevlist->evlist) {
+ PyErr_NoMemory();
+ return -1;
+ }
threads = ((struct pyrf_thread_map *)pthreads)->threads;
cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
- evlist__init(&pevlist->evlist, cpus, threads);
+ perf_evlist__set_maps(&pevlist->evlist->core, cpus, threads);
+
return 0;
}
static void pyrf_evlist__delete(struct pyrf_evlist *pevlist)
{
- evlist__exit(&pevlist->evlist);
+ evlist__put(pevlist->evlist);
Py_TYPE(pevlist)->tp_free((PyObject*)pevlist);
}
@@ -1302,7 +1309,7 @@ static PyObject *pyrf_evlist__all_cpus(struct pyrf_evlist *pevlist)
struct pyrf_cpu_map *pcpu_map = PyObject_New(struct pyrf_cpu_map, &pyrf_cpu_map__type);
if (pcpu_map)
- pcpu_map->cpus = perf_cpu_map__get(pevlist->evlist.core.all_cpus);
+ pcpu_map->cpus = perf_cpu_map__get(pevlist->evlist->core.all_cpus);
return (PyObject *)pcpu_map;
}
@@ -1315,7 +1322,7 @@ static PyObject *pyrf_evlist__metrics(struct pyrf_evlist *pevlist)
if (!list)
return NULL;
- for (node = rb_first_cached(&pevlist->evlist.metric_events.entries); node;
+ for (node = rb_first_cached(&pevlist->evlist->metric_events.entries); node;
node = rb_next(node)) {
struct metric_event *me = container_of(node, struct metric_event, nd);
struct list_head *pos;
@@ -1421,7 +1428,7 @@ static PyObject *pyrf_evlist__compute_metric(struct pyrf_evlist *pevlist,
if (!PyArg_ParseTuple(args, "sii", &metric, &cpu, &thread))
return NULL;
- for (node = rb_first_cached(&pevlist->evlist.metric_events.entries);
+ for (node = rb_first_cached(&pevlist->evlist->metric_events.entries);
mexp == NULL && node;
node = rb_next(node)) {
struct metric_event *me = container_of(node, struct metric_event, nd);
@@ -1437,7 +1444,7 @@ static PyObject *pyrf_evlist__compute_metric(struct pyrf_evlist *pevlist,
if (e->metric_events[0] == NULL)
continue;
- evlist__for_each_entry(&pevlist->evlist, pos2) {
+ evlist__for_each_entry(pevlist->evlist, pos2) {
if (pos2->metric_leader != e->metric_events[0])
continue;
cpu_idx = perf_cpu_map__idx(pos2->core.cpus,
@@ -1482,7 +1489,7 @@ static PyObject *pyrf_evlist__compute_metric(struct pyrf_evlist *pevlist,
static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
PyObject *args, PyObject *kwargs)
{
- struct evlist *evlist = &pevlist->evlist;
+ struct evlist *evlist = pevlist->evlist;
static char *kwlist[] = { "pages", "overwrite", NULL };
int pages = 128, overwrite = false;
@@ -1502,7 +1509,7 @@ static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
PyObject *args, PyObject *kwargs)
{
- struct evlist *evlist = &pevlist->evlist;
+ struct evlist *evlist = pevlist->evlist;
static char *kwlist[] = { "timeout", NULL };
int timeout = -1, n;
@@ -1522,7 +1529,7 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
PyObject *args __maybe_unused,
PyObject *kwargs __maybe_unused)
{
- struct evlist *evlist = &pevlist->evlist;
+ struct evlist *evlist = pevlist->evlist;
PyObject *list = PyList_New(0);
int i;
@@ -1551,7 +1558,7 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
PyObject *args,
PyObject *kwargs __maybe_unused)
{
- struct evlist *evlist = &pevlist->evlist;
+ struct evlist *evlist = pevlist->evlist;
PyObject *pevsel;
struct evsel *evsel;
@@ -1583,7 +1590,7 @@ static struct mmap *get_md(struct evlist *evlist, int cpu)
static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
PyObject *args, PyObject *kwargs)
{
- struct evlist *evlist = &pevlist->evlist;
+ struct evlist *evlist = pevlist->evlist;
union perf_event *event;
int sample_id_all = 1, cpu;
static char *kwlist[] = { "cpu", "sample_id_all", NULL };
@@ -1640,7 +1647,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
PyObject *args, PyObject *kwargs)
{
- struct evlist *evlist = &pevlist->evlist;
+ struct evlist *evlist = pevlist->evlist;
if (evlist__open(evlist) < 0) {
PyErr_SetFromErrno(PyExc_OSError);
@@ -1653,7 +1660,7 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
static PyObject *pyrf_evlist__close(struct pyrf_evlist *pevlist)
{
- struct evlist *evlist = &pevlist->evlist;
+ struct evlist *evlist = pevlist->evlist;
evlist__close(evlist);
@@ -1679,7 +1686,7 @@ static PyObject *pyrf_evlist__config(struct pyrf_evlist *pevlist)
.no_buffering = true,
.no_inherit = true,
};
- struct evlist *evlist = &pevlist->evlist;
+ struct evlist *evlist = pevlist->evlist;
evlist__config(evlist, &opts, &callchain_param);
Py_INCREF(Py_None);
@@ -1688,14 +1695,14 @@ static PyObject *pyrf_evlist__config(struct pyrf_evlist *pevlist)
static PyObject *pyrf_evlist__disable(struct pyrf_evlist *pevlist)
{
- evlist__disable(&pevlist->evlist);
+ evlist__disable(pevlist->evlist);
Py_INCREF(Py_None);
return Py_None;
}
static PyObject *pyrf_evlist__enable(struct pyrf_evlist *pevlist)
{
- evlist__enable(&pevlist->evlist);
+ evlist__enable(pevlist->evlist);
Py_INCREF(Py_None);
return Py_None;
}
@@ -1786,7 +1793,23 @@ static Py_ssize_t pyrf_evlist__length(PyObject *obj)
{
struct pyrf_evlist *pevlist = (void *)obj;
- return pevlist->evlist.core.nr_entries;
+ return pevlist->evlist->core.nr_entries;
+}
+
+static PyObject *pyrf_evsel__from_evsel(struct evsel *evsel)
+{
+ struct pyrf_evsel *pevsel = PyObject_New(struct pyrf_evsel, &pyrf_evsel__type);
+
+ if (!pevsel)
+ return NULL;
+
+ memset(&pevsel->evsel, 0, sizeof(pevsel->evsel));
+ evsel__init(&pevsel->evsel, &evsel->core.attr, evsel->core.idx);
+
+ evsel__clone(&pevsel->evsel, evsel);
+ if (evsel__is_group_leader(evsel))
+ evsel__set_leader(&pevsel->evsel, &pevsel->evsel);
+ return (PyObject *)pevsel;
}
static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
@@ -1794,17 +1817,16 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
struct pyrf_evlist *pevlist = (void *)obj;
struct evsel *pos;
- if (i >= pevlist->evlist.core.nr_entries) {
+ if (i >= pevlist->evlist->core.nr_entries) {
PyErr_SetString(PyExc_IndexError, "Index out of range");
return NULL;
}
- evlist__for_each_entry(&pevlist->evlist, pos) {
+ evlist__for_each_entry(pevlist->evlist, pos) {
if (i-- == 0)
break;
}
-
- return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel));
+ return pyrf_evsel__from_evsel(pos);
}
static PyObject *pyrf_evlist__str(PyObject *self)
@@ -1816,7 +1838,7 @@ static PyObject *pyrf_evlist__str(PyObject *self)
PyObject *result;
strbuf_addstr(&sb, "evlist([");
- evlist__for_each_entry(&pevlist->evlist, pos) {
+ evlist__for_each_entry(pevlist->evlist, pos) {
if (!first)
strbuf_addch(&sb, ',');
if (!pos->pmu)
@@ -1852,9 +1874,19 @@ static PyTypeObject pyrf_evlist__type = {
.tp_str = pyrf_evlist__str,
};
+static PyObject *pyrf_evlist__new(PyTypeObject *type, PyObject *args, PyObject *kwargs)
+{
+ struct pyrf_evlist *pevlist;
+
+ pevlist = (struct pyrf_evlist *)PyType_GenericNew(type, args, kwargs);
+ if (pevlist)
+ pevlist->evlist = NULL;
+ return (PyObject *)pevlist;
+}
+
static int pyrf_evlist__setup_types(void)
{
- pyrf_evlist__type.tp_new = PyType_GenericNew;
+ pyrf_evlist__type.tp_new = pyrf_evlist__new;
return PyType_Ready(&pyrf_evlist__type);
}
@@ -1957,157 +1989,74 @@ static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
return PyLong_FromLong(tp_pmu__id(sys, name));
}
-static PyObject *pyrf_evsel__from_evsel(struct evsel *evsel)
-{
- struct pyrf_evsel *pevsel = PyObject_New(struct pyrf_evsel, &pyrf_evsel__type);
-
- if (!pevsel)
- return NULL;
-
- memset(&pevsel->evsel, 0, sizeof(pevsel->evsel));
- evsel__init(&pevsel->evsel, &evsel->core.attr, evsel->core.idx);
-
- evsel__clone(&pevsel->evsel, evsel);
- if (evsel__is_group_leader(evsel))
- evsel__set_leader(&pevsel->evsel, &pevsel->evsel);
- return (PyObject *)pevsel;
-}
-
-static int evlist__pos(struct evlist *evlist, struct evsel *evsel)
-{
- struct evsel *pos;
- int idx = 0;
-
- evlist__for_each_entry(evlist, pos) {
- if (evsel == pos)
- return idx;
- idx++;
- }
- return -1;
-}
-
-static struct evsel *evlist__at(struct evlist *evlist, int idx)
-{
- struct evsel *pos;
- int idx2 = 0;
-
- evlist__for_each_entry(evlist, pos) {
- if (idx == idx2)
- return pos;
- idx2++;
- }
- return NULL;
-}
-
static PyObject *pyrf_evlist__from_evlist(struct evlist *evlist)
{
struct pyrf_evlist *pevlist = PyObject_New(struct pyrf_evlist, &pyrf_evlist__type);
- struct evsel *pos;
- struct rb_node *node;
if (!pevlist)
return NULL;
- memset(&pevlist->evlist, 0, sizeof(pevlist->evlist));
- evlist__init(&pevlist->evlist, evlist->core.all_cpus, evlist->core.threads);
- evlist__for_each_entry(evlist, pos) {
- struct pyrf_evsel *pevsel = (void *)pyrf_evsel__from_evsel(pos);
-
- evlist__add(&pevlist->evlist, &pevsel->evsel);
- }
- evlist__for_each_entry(&pevlist->evlist, pos) {
- struct evsel *leader = evsel__leader(pos);
-
- if (pos != leader) {
- int idx = evlist__pos(evlist, leader);
-
- if (idx >= 0)
- evsel__set_leader(pos, evlist__at(&pevlist->evlist, idx));
- else if (leader == NULL)
- evsel__set_leader(pos, pos);
- }
-
- leader = pos->metric_leader;
-
- if (pos != leader) {
- int idx = evlist__pos(evlist, leader);
-
- if (idx >= 0)
- pos->metric_leader = evlist__at(&pevlist->evlist, idx);
- else if (leader == NULL)
- pos->metric_leader = pos;
- }
- }
- metricgroup__copy_metric_events(&pevlist->evlist, /*cgrp=*/NULL,
- &pevlist->evlist.metric_events,
- &evlist->metric_events);
- for (node = rb_first_cached(&pevlist->evlist.metric_events.entries); node;
- node = rb_next(node)) {
- struct metric_event *me = container_of(node, struct metric_event, nd);
- struct list_head *mpos;
- int idx = evlist__pos(evlist, me->evsel);
-
- if (idx >= 0)
- me->evsel = evlist__at(&pevlist->evlist, idx);
- list_for_each(mpos, &me->head) {
- struct metric_expr *e = container_of(mpos, struct metric_expr, nd);
-
- for (int j = 0; e->metric_events[j]; j++) {
- idx = evlist__pos(evlist, e->metric_events[j]);
- if (idx >= 0)
- e->metric_events[j] = evlist__at(&pevlist->evlist, idx);
- }
- }
- }
+ pevlist->evlist = evlist__get(evlist);
return (PyObject *)pevlist;
}
static PyObject *pyrf__parse_events(PyObject *self, PyObject *args)
{
const char *input;
- struct evlist evlist = {};
+ struct evlist *evlist = evlist__new();
struct parse_events_error err;
PyObject *result;
PyObject *pcpus = NULL, *pthreads = NULL;
struct perf_cpu_map *cpus;
struct perf_thread_map *threads;
- if (!PyArg_ParseTuple(args, "s|OO", &input, &pcpus, &pthreads))
+ if (!evlist)
+ return PyErr_NoMemory();
+
+ if (!PyArg_ParseTuple(args, "s|OO", &input, &pcpus, &pthreads)) {
+ evlist__put(evlist);
return NULL;
+ }
threads = pthreads ? ((struct pyrf_thread_map *)pthreads)->threads : NULL;
cpus = pcpus ? ((struct pyrf_cpu_map *)pcpus)->cpus : NULL;
parse_events_error__init(&err);
- evlist__init(&evlist, cpus, threads);
- if (parse_events(&evlist, input, &err)) {
+ perf_evlist__set_maps(&evlist->core, cpus, threads);
+ if (parse_events(evlist, input, &err)) {
parse_events_error__print(&err, input);
PyErr_SetFromErrno(PyExc_OSError);
+ evlist__put(evlist);
return NULL;
}
- result = pyrf_evlist__from_evlist(&evlist);
- evlist__exit(&evlist);
+ result = pyrf_evlist__from_evlist(evlist);
+ evlist__put(evlist);
return result;
}
static PyObject *pyrf__parse_metrics(PyObject *self, PyObject *args)
{
const char *input, *pmu = NULL;
- struct evlist evlist = {};
+ struct evlist *evlist = evlist__new();
PyObject *result;
PyObject *pcpus = NULL, *pthreads = NULL;
struct perf_cpu_map *cpus;
struct perf_thread_map *threads;
int ret;
- if (!PyArg_ParseTuple(args, "s|sOO", &input, &pmu, &pcpus, &pthreads))
+ if (!evlist)
+ return PyErr_NoMemory();
+
+ if (!PyArg_ParseTuple(args, "s|sOO", &input, &pmu, &pcpus, &pthreads)) {
+ evlist__put(evlist);
return NULL;
+ }
threads = pthreads ? ((struct pyrf_thread_map *)pthreads)->threads : NULL;
cpus = pcpus ? ((struct pyrf_cpu_map *)pcpus)->cpus : NULL;
- evlist__init(&evlist, cpus, threads);
- ret = metricgroup__parse_groups(&evlist, pmu ?: "all", input,
+ perf_evlist__set_maps(&evlist->core, cpus, threads);
+ ret = metricgroup__parse_groups(evlist, pmu ?: "all", input,
/*metric_no_group=*/ false,
/*metric_no_merge=*/ false,
/*metric_no_threshold=*/ true,
@@ -2115,12 +2064,13 @@ static PyObject *pyrf__parse_metrics(PyObject *self, PyObject *args)
/*system_wide=*/true,
/*hardware_aware_grouping=*/ false);
if (ret) {
+ evlist__put(evlist);
errno = -ret;
PyErr_SetFromErrno(PyExc_OSError);
return NULL;
}
- result = pyrf_evlist__from_evlist(&evlist);
- evlist__exit(&evlist);
+ result = pyrf_evlist__from_evlist(evlist);
+ evlist__put(evlist);
return result;
}
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index e867de8ddaaa..8a5fc7d5e43c 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -264,7 +264,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
ret = true;
out_delete:
- evlist__delete(temp_evlist);
+ evlist__put(temp_evlist);
return ret;
}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index fe0de2a0277f..1ac6cd43c38b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -264,7 +264,7 @@ void perf_session__delete(struct perf_session *session)
machines__exit(&session->machines);
if (session->data) {
if (perf_data__is_read(session->data))
- evlist__delete(session->evlist);
+ evlist__put(session->evlist);
perf_data__close(session->data);
}
#ifdef HAVE_LIBTRACEEVENT
diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c
index 388846f17bc1..b84a5463e039 100644
--- a/tools/perf/util/sideband_evlist.c
+++ b/tools/perf/util/sideband_evlist.c
@@ -102,7 +102,7 @@ int evlist__start_sb_thread(struct evlist *evlist, struct target *target)
return 0;
if (evlist__create_maps(evlist, target))
- goto out_delete_evlist;
+ goto out_put_evlist;
if (evlist->core.nr_entries > 1) {
bool can_sample_identifier = perf_can_sample_identifier();
@@ -116,25 +116,25 @@ int evlist__start_sb_thread(struct evlist *evlist, struct target *target)
evlist__for_each_entry(evlist, counter) {
if (evsel__open(counter, evlist->core.user_requested_cpus,
evlist->core.threads) < 0)
- goto out_delete_evlist;
+ goto out_put_evlist;
}
if (evlist__mmap(evlist, UINT_MAX))
- goto out_delete_evlist;
+ goto out_put_evlist;
evlist__for_each_entry(evlist, counter) {
if (evsel__enable(counter))
- goto out_delete_evlist;
+ goto out_put_evlist;
}
evlist->thread.done = 0;
if (pthread_create(&evlist->thread.th, NULL, perf_evlist__poll_thread, evlist))
- goto out_delete_evlist;
+ goto out_put_evlist;
return 0;
-out_delete_evlist:
- evlist__delete(evlist);
+out_put_evlist:
+ evlist__put(evlist);
evlist = NULL;
return -1;
}
@@ -145,5 +145,5 @@ void evlist__stop_sb_thread(struct evlist *evlist)
return;
evlist->thread.done = 1;
pthread_join(evlist->thread.th, NULL);
- evlist__delete(evlist);
+ evlist__put(evlist);
}
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 15/58] perf python: Refactor and add accessors to sample event
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Add common evsel field for events and move sample specific fields to
only be present in sample events. Add accessors for sample
events. Ensure offsets are within the bounds of the event. Allocate
just enough memory for the copied event, don't make the maximum event
size each time.
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
v5:
1. Fix Uninitialized Memory: Restore zero-initialization of `pevent->sample`
in `pyrf_event__new()` to prevent wild free crashes on error paths.
v6:
- Refactored `pyrf_event__new` to take `evsel` and `session`, and use
dynamic allocation based on event size. Updated callers.
v8:
- Ensure events are properly deallocated.
---
tools/perf/util/python.c | 618 +++++++++++++++++++++++++++++++++------
1 file changed, 534 insertions(+), 84 deletions(-)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 4e7add7d18c4..1ca296000351 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -8,21 +8,28 @@
#include <internal/lib.h>
#include <perf/mmap.h>
+#include "addr_location.h"
+#include "build-id.h"
#include "callchain.h"
#include "comm.h"
#include "counts.h"
#include "data.h"
#include "debug.h"
+#include "dso.h"
#include "event.h"
#include "evlist.h"
#include "evsel.h"
#include "expr.h"
+#include "map.h"
#include "metricgroup.h"
#include "mmap.h"
#include "pmus.h"
#include "print_binary.h"
#include "record.h"
+#include "sample.h"
#include "session.h"
+#include "srccode.h"
+#include "srcline.h"
#include "strbuf.h"
#include "symbol.h"
#include "thread.h"
@@ -30,7 +37,6 @@
#include "tool.h"
#include "tp_pmu.h"
#include "trace-event.h"
-#include "util/sample.h"
#ifdef HAVE_LIBTRACEEVENT
#include <event-parse.h>
@@ -38,6 +44,8 @@
PyMODINIT_FUNC PyInit_perf(void);
+static PyObject *pyrf_evsel__from_evsel(struct evsel *evsel);
+
#define member_def(type, member, ptype, help) \
{ #member, ptype, \
offsetof(struct pyrf_event, event) + offsetof(struct type, member), \
@@ -50,21 +58,53 @@ PyMODINIT_FUNC PyInit_perf(void);
struct pyrf_event {
PyObject_HEAD
+ /** @sample: The parsed sample from the event. */
struct perf_sample sample;
- union perf_event event;
+ /** @al: The address location from machine__resolve, lazily computed. */
+ struct addr_location al;
+ /** @al_resolved: True when machine__resolve been called. */
+ bool al_resolved;
+ /** @event: The underlying perf_event that may be in a file or ring buffer. */
+ union perf_event event;
};
#define sample_members \
- sample_member_def(sample_ip, ip, T_ULONGLONG, "event ip"), \
sample_member_def(sample_pid, pid, T_INT, "event pid"), \
sample_member_def(sample_tid, tid, T_INT, "event tid"), \
sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \
- sample_member_def(sample_addr, addr, T_ULONGLONG, "event addr"), \
sample_member_def(sample_id, id, T_ULONGLONG, "event id"), \
sample_member_def(sample_stream_id, stream_id, T_ULONGLONG, "event stream id"), \
sample_member_def(sample_period, period, T_ULONGLONG, "event period"), \
sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"),
+static PyObject *pyrf_event__get_evsel(PyObject *self, void *closure __maybe_unused)
+{
+ struct pyrf_event *pevent = (void *)self;
+
+ if (!pevent->sample.evsel)
+ Py_RETURN_NONE;
+
+ return pyrf_evsel__from_evsel(pevent->sample.evsel);
+}
+
+static PyGetSetDef pyrf_event__getset[] = {
+ {
+ .name = "evsel",
+ .get = pyrf_event__get_evsel,
+ .set = NULL,
+ .doc = "tracking event.",
+ },
+ { .name = NULL, },
+};
+
+static void pyrf_event__delete(struct pyrf_event *pevent)
+{
+ if (pevent->al_resolved)
+ addr_location__exit(&pevent->al);
+ perf_sample__exit(&pevent->sample);
+ Py_TYPE(pevent)->tp_free((PyObject *)pevent);
+}
+
static const char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object.");
static PyMemberDef pyrf_mmap_event__members[] = {
@@ -103,9 +143,11 @@ static PyTypeObject pyrf_mmap_event__type = {
PyVarObject_HEAD_INIT(NULL, 0)
.tp_name = "perf.mmap_event",
.tp_basicsize = sizeof(struct pyrf_event),
+ .tp_dealloc = (destructor)pyrf_event__delete,
.tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
.tp_doc = pyrf_mmap_event__doc,
.tp_members = pyrf_mmap_event__members,
+ .tp_getset = pyrf_event__getset,
.tp_repr = (reprfunc)pyrf_mmap_event__repr,
};
@@ -138,9 +180,11 @@ static PyTypeObject pyrf_task_event__type = {
PyVarObject_HEAD_INIT(NULL, 0)
.tp_name = "perf.task_event",
.tp_basicsize = sizeof(struct pyrf_event),
+ .tp_dealloc = (destructor)pyrf_event__delete,
.tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
.tp_doc = pyrf_task_event__doc,
.tp_members = pyrf_task_event__members,
+ .tp_getset = pyrf_event__getset,
.tp_repr = (reprfunc)pyrf_task_event__repr,
};
@@ -167,9 +211,11 @@ static PyTypeObject pyrf_comm_event__type = {
PyVarObject_HEAD_INIT(NULL, 0)
.tp_name = "perf.comm_event",
.tp_basicsize = sizeof(struct pyrf_event),
+ .tp_dealloc = (destructor)pyrf_event__delete,
.tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
.tp_doc = pyrf_comm_event__doc,
.tp_members = pyrf_comm_event__members,
+ .tp_getset = pyrf_event__getset,
.tp_repr = (reprfunc)pyrf_comm_event__repr,
};
@@ -199,9 +245,11 @@ static PyTypeObject pyrf_throttle_event__type = {
PyVarObject_HEAD_INIT(NULL, 0)
.tp_name = "perf.throttle_event",
.tp_basicsize = sizeof(struct pyrf_event),
+ .tp_dealloc = (destructor)pyrf_event__delete,
.tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
.tp_doc = pyrf_throttle_event__doc,
.tp_members = pyrf_throttle_event__members,
+ .tp_getset = pyrf_event__getset,
.tp_repr = (reprfunc)pyrf_throttle_event__repr,
};
@@ -234,9 +282,11 @@ static PyTypeObject pyrf_lost_event__type = {
PyVarObject_HEAD_INIT(NULL, 0)
.tp_name = "perf.lost_event",
.tp_basicsize = sizeof(struct pyrf_event),
+ .tp_dealloc = (destructor)pyrf_event__delete,
.tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
.tp_doc = pyrf_lost_event__doc,
.tp_members = pyrf_lost_event__members,
+ .tp_getset = pyrf_event__getset,
.tp_repr = (reprfunc)pyrf_lost_event__repr,
};
@@ -264,9 +314,11 @@ static PyTypeObject pyrf_read_event__type = {
PyVarObject_HEAD_INIT(NULL, 0)
.tp_name = "perf.read_event",
.tp_basicsize = sizeof(struct pyrf_event),
+ .tp_dealloc = (destructor)pyrf_event__delete,
.tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
.tp_doc = pyrf_read_event__doc,
.tp_members = pyrf_read_event__members,
+ .tp_getset = pyrf_event__getset,
.tp_repr = (reprfunc)pyrf_read_event__repr,
};
@@ -274,16 +326,17 @@ static const char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object
static PyMemberDef pyrf_sample_event__members[] = {
sample_members
+ sample_member_def(sample_ip, ip, T_ULONGLONG, "event ip"),
+ sample_member_def(sample_addr, addr, T_ULONGLONG, "event addr"),
+ sample_member_def(sample_phys_addr, phys_addr, T_ULONGLONG, "event physical addr"),
+ sample_member_def(sample_weight, weight, T_ULONGLONG, "event weight"),
+ sample_member_def(sample_data_src, data_src, T_ULONGLONG, "event data source"),
+ sample_member_def(sample_insn_count, insn_cnt, T_ULONGLONG, "event instruction count"),
+ sample_member_def(sample_cyc_count, cyc_cnt, T_ULONGLONG, "event cycle count"),
member_def(perf_event_header, type, T_UINT, "event type"),
{ .name = NULL, },
};
-static void pyrf_sample_event__delete(struct pyrf_event *pevent)
-{
- perf_sample__exit(&pevent->sample);
- Py_TYPE(pevent)->tp_free((PyObject*)pevent);
-}
-
static PyObject *pyrf_sample_event__repr(const struct pyrf_event *pevent)
{
PyObject *ret;
@@ -301,6 +354,8 @@ static PyObject *pyrf_sample_event__repr(const struct pyrf_event *pevent)
#ifdef HAVE_LIBTRACEEVENT
static bool is_tracepoint(const struct pyrf_event *pevent)
{
+ if (!pevent->sample.evsel)
+ return false;
return pevent->sample.evsel->core.attr.type == PERF_TYPE_TRACEPOINT;
}
@@ -371,6 +426,199 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
}
#endif /* HAVE_LIBTRACEEVENT */
+static int pyrf_sample_event__resolve_al(struct pyrf_event *pevent)
+{
+ struct evsel *evsel = pevent->sample.evsel;
+ struct evlist *evlist = evsel ? evsel->evlist : NULL;
+ struct perf_session *session = evlist ? evlist__session(evlist) : NULL;
+
+ if (pevent->al_resolved)
+ return 0;
+
+ if (!session)
+ return -1;
+
+ addr_location__init(&pevent->al);
+ if (machine__resolve(&session->machines.host, &pevent->al, &pevent->sample) < 0) {
+ addr_location__exit(&pevent->al);
+ return -1;
+ }
+
+ pevent->al_resolved = true;
+ return 0;
+}
+
+static PyObject *pyrf_sample_event__get_dso(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ if (pyrf_sample_event__resolve_al(pevent) < 0 || !pevent->al.map)
+ Py_RETURN_NONE;
+
+ return PyUnicode_FromString(dso__name(map__dso(pevent->al.map)));
+}
+
+static PyObject *pyrf_sample_event__get_dso_long_name(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ if (pyrf_sample_event__resolve_al(pevent) < 0 || !pevent->al.map)
+ Py_RETURN_NONE;
+
+ return PyUnicode_FromString(dso__long_name(map__dso(pevent->al.map)));
+}
+
+static PyObject *pyrf_sample_event__get_dso_bid(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ char sbuild_id[SBUILD_ID_SIZE];
+
+ if (pyrf_sample_event__resolve_al(pevent) < 0 || !pevent->al.map)
+ Py_RETURN_NONE;
+
+ build_id__snprintf(dso__bid(map__dso(pevent->al.map)), sbuild_id, sizeof(sbuild_id));
+ return PyUnicode_FromString(sbuild_id);
+}
+
+static PyObject *pyrf_sample_event__get_map_start(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ if (pyrf_sample_event__resolve_al(pevent) < 0 || !pevent->al.map)
+ Py_RETURN_NONE;
+
+ return PyLong_FromUnsignedLong(map__start(pevent->al.map));
+}
+
+static PyObject *pyrf_sample_event__get_map_end(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ if (pyrf_sample_event__resolve_al(pevent) < 0 || !pevent->al.map)
+ Py_RETURN_NONE;
+
+ return PyLong_FromUnsignedLong(map__end(pevent->al.map));
+}
+
+static PyObject *pyrf_sample_event__get_map_pgoff(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ if (pyrf_sample_event__resolve_al(pevent) < 0 || !pevent->al.map)
+ Py_RETURN_NONE;
+
+ return PyLong_FromUnsignedLongLong(map__pgoff(pevent->al.map));
+}
+
+static PyObject *pyrf_sample_event__get_symbol(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ if (pyrf_sample_event__resolve_al(pevent) < 0 || !pevent->al.sym)
+ Py_RETURN_NONE;
+
+ return PyUnicode_FromString(pevent->al.sym->name);
+}
+
+static PyObject *pyrf_sample_event__get_sym_start(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ if (pyrf_sample_event__resolve_al(pevent) < 0 || !pevent->al.sym)
+ Py_RETURN_NONE;
+
+ return PyLong_FromUnsignedLongLong(pevent->al.sym->start);
+}
+
+static PyObject *pyrf_sample_event__get_sym_end(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ if (pyrf_sample_event__resolve_al(pevent) < 0 || !pevent->al.sym)
+ Py_RETURN_NONE;
+
+ return PyLong_FromUnsignedLongLong(pevent->al.sym->end);
+}
+
+static PyObject *pyrf_sample_event__get_raw_buf(struct pyrf_event *pevent,
+ void *closure __maybe_unused)
+{
+ if (pevent->event.header.type != PERF_RECORD_SAMPLE)
+ Py_RETURN_NONE;
+
+ return PyBytes_FromStringAndSize((const char *)pevent->sample.raw_data,
+ pevent->sample.raw_size);
+}
+
+static PyObject *pyrf_sample_event__srccode(PyObject *self, PyObject *args)
+{
+ struct pyrf_event *pevent = (void *)self;
+ u64 addr = pevent->sample.ip;
+ char *srcfile = NULL;
+ char *srccode = NULL;
+ unsigned int line = 0;
+ int len = 0;
+ PyObject *result;
+ struct addr_location al;
+
+ if (!PyArg_ParseTuple(args, "|K", &addr))
+ return NULL;
+
+ if (pyrf_sample_event__resolve_al(pevent) < 0)
+ Py_RETURN_NONE;
+
+ if (addr != pevent->sample.ip) {
+ addr_location__init(&al);
+ thread__find_symbol_fb(pevent->al.thread, pevent->sample.cpumode, addr, &al);
+ } else {
+ addr_location__init(&al);
+ al.thread = thread__get(pevent->al.thread);
+ al.map = map__get(pevent->al.map);
+ al.sym = pevent->al.sym;
+ al.addr = pevent->al.addr;
+ }
+
+ if (al.map) {
+ struct dso *dso = map__dso(al.map);
+
+ if (dso) {
+ srcfile = get_srcline_split(dso, map__rip_2objdump(al.map, addr),
+ &line);
+ }
+ }
+ addr_location__exit(&al);
+
+ if (srcfile) {
+ srccode = find_sourceline(srcfile, line, &len);
+ result = Py_BuildValue("(sIs#)", srcfile, line, srccode, (Py_ssize_t)len);
+ free(srcfile);
+ } else {
+ result = Py_BuildValue("(sIs#)", NULL, 0, NULL, (Py_ssize_t)0);
+ }
+
+ return result;
+}
+
+static PyObject *pyrf_sample_event__insn(PyObject *self, PyObject *args __maybe_unused)
+{
+ struct pyrf_event *pevent = (void *)self;
+ struct thread *thread;
+ struct machine *machine;
+
+ if (pyrf_sample_event__resolve_al(pevent) < 0)
+ Py_RETURN_NONE;
+
+ thread = pevent->al.thread;
+
+ if (!thread || !thread__maps(thread))
+ Py_RETURN_NONE;
+
+ machine = maps__machine(thread__maps(thread));
+ if (!machine)
+ Py_RETURN_NONE;
+
+ if (pevent->sample.ip && !pevent->sample.insn_len)
+ perf_sample__fetch_insn(&pevent->sample, thread, machine);
+
+ if (!pevent->sample.insn_len)
+ Py_RETURN_NONE;
+
+ return PyBytes_FromStringAndSize((const char *)pevent->sample.insn,
+ pevent->sample.insn_len);
+}
+
static PyObject*
pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name)
{
@@ -384,13 +632,102 @@ pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name)
return obj ?: PyObject_GenericGetAttr((PyObject *) pevent, attr_name);
}
+static PyGetSetDef pyrf_sample_event__getset[] = {
+ {
+ .name = "raw_buf",
+ .get = (getter)pyrf_sample_event__get_raw_buf,
+ .set = NULL,
+ .doc = "event raw buffer.",
+ },
+ {
+ .name = "evsel",
+ .get = pyrf_event__get_evsel,
+ .set = NULL,
+ .doc = "tracking event.",
+ },
+ {
+ .name = "dso",
+ .get = (getter)pyrf_sample_event__get_dso,
+ .set = NULL,
+ .doc = "event dso short name.",
+ },
+ {
+ .name = "dso_long_name",
+ .get = (getter)pyrf_sample_event__get_dso_long_name,
+ .set = NULL,
+ .doc = "event dso long name.",
+ },
+ {
+ .name = "dso_bid",
+ .get = (getter)pyrf_sample_event__get_dso_bid,
+ .set = NULL,
+ .doc = "event dso build id.",
+ },
+ {
+ .name = "map_start",
+ .get = (getter)pyrf_sample_event__get_map_start,
+ .set = NULL,
+ .doc = "event map start address.",
+ },
+ {
+ .name = "map_end",
+ .get = (getter)pyrf_sample_event__get_map_end,
+ .set = NULL,
+ .doc = "event map end address.",
+ },
+ {
+ .name = "map_pgoff",
+ .get = (getter)pyrf_sample_event__get_map_pgoff,
+ .set = NULL,
+ .doc = "event map page offset.",
+ },
+ {
+ .name = "symbol",
+ .get = (getter)pyrf_sample_event__get_symbol,
+ .set = NULL,
+ .doc = "event symbol name.",
+ },
+ {
+ .name = "sym_start",
+ .get = (getter)pyrf_sample_event__get_sym_start,
+ .set = NULL,
+ .doc = "event symbol start address.",
+ },
+ {
+ .name = "sym_end",
+ .get = (getter)pyrf_sample_event__get_sym_end,
+ .set = NULL,
+ .doc = "event symbol end address.",
+ },
+ { .name = NULL, },
+};
+
+static PyMethodDef pyrf_sample_event__methods[] = {
+ {
+ .ml_name = "srccode",
+ .ml_meth = (PyCFunction)pyrf_sample_event__srccode,
+ .ml_flags = METH_VARARGS,
+ .ml_doc = PyDoc_STR("Get source code for an address.")
+ },
+ {
+ .ml_name = "insn",
+ .ml_meth = (PyCFunction)pyrf_sample_event__insn,
+ .ml_flags = METH_NOARGS,
+ .ml_doc = PyDoc_STR("Get instruction bytes for a sample.")
+ },
+ { .ml_name = NULL, }
+};
+
static PyTypeObject pyrf_sample_event__type = {
PyVarObject_HEAD_INIT(NULL, 0)
.tp_name = "perf.sample_event",
.tp_basicsize = sizeof(struct pyrf_event),
+ .tp_dealloc = (destructor)pyrf_event__delete,
.tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
.tp_doc = pyrf_sample_event__doc,
.tp_members = pyrf_sample_event__members,
+ .tp_getset = pyrf_sample_event__getset,
+ .tp_methods = pyrf_sample_event__methods,
.tp_repr = (reprfunc)pyrf_sample_event__repr,
.tp_getattro = (getattrofunc) pyrf_sample_event__getattro,
};
@@ -426,25 +763,17 @@ static PyTypeObject pyrf_context_switch_event__type = {
PyVarObject_HEAD_INIT(NULL, 0)
.tp_name = "perf.context_switch_event",
.tp_basicsize = sizeof(struct pyrf_event),
+ .tp_dealloc = (destructor)pyrf_event__delete,
.tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
.tp_doc = pyrf_context_switch_event__doc,
.tp_members = pyrf_context_switch_event__members,
+ .tp_getset = pyrf_event__getset,
.tp_repr = (reprfunc)pyrf_context_switch_event__repr,
};
static int pyrf_event__setup_types(void)
{
int err;
- pyrf_mmap_event__type.tp_new =
- pyrf_task_event__type.tp_new =
- pyrf_comm_event__type.tp_new =
- pyrf_lost_event__type.tp_new =
- pyrf_read_event__type.tp_new =
- pyrf_sample_event__type.tp_new =
- pyrf_context_switch_event__type.tp_new =
- pyrf_throttle_event__type.tp_new = PyType_GenericNew;
-
- pyrf_sample_event__type.tp_dealloc = (destructor)pyrf_sample_event__delete,
err = PyType_Ready(&pyrf_mmap_event__type);
if (err < 0)
@@ -488,33 +817,175 @@ static PyTypeObject *pyrf_event__type[] = {
[PERF_RECORD_SWITCH_CPU_WIDE] = &pyrf_context_switch_event__type,
};
-static PyObject *pyrf_event__new(const union perf_event *event)
+static PyObject *pyrf_event__new(const union perf_event *event, struct evsel *evsel,
+ struct perf_session *session __maybe_unused)
{
struct pyrf_event *pevent;
- PyTypeObject *ptype;
+ size_t size;
+ int err;
+ size_t min_size = sizeof(struct perf_event_header);
- if ((event->header.type < PERF_RECORD_MMAP ||
- event->header.type > PERF_RECORD_SAMPLE) &&
- !(event->header.type == PERF_RECORD_SWITCH ||
- event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)) {
- PyErr_Format(PyExc_TypeError, "Unexpected header type %u",
+ if (event->header.type >= ARRAY_SIZE(pyrf_event__type) ||
+ pyrf_event__type[event->header.type] == NULL) {
+ return PyErr_Format(PyExc_TypeError, "Unexpected header type %u",
event->header.type);
- return NULL;
}
- // FIXME this better be dynamic or we need to parse everything
- // before calling perf_mmap__consume(), including tracepoint fields.
- if (sizeof(pevent->event) < event->header.size) {
- PyErr_Format(PyExc_TypeError, "Unexpected event size: %zd < %u",
- sizeof(pevent->event), event->header.size);
- return NULL;
+ switch (event->header.type) {
+ case PERF_RECORD_MMAP:
+ min_size = offsetof(struct perf_record_mmap, filename) + 1;
+ break;
+ case PERF_RECORD_MMAP2:
+ min_size = offsetof(struct perf_record_mmap2, filename) + 1;
+ break;
+ case PERF_RECORD_COMM:
+ min_size = sizeof(struct perf_record_comm);
+ break;
+ case PERF_RECORD_FORK:
+ case PERF_RECORD_EXIT:
+ min_size = sizeof(struct perf_record_fork);
+ break;
+ case PERF_RECORD_THROTTLE:
+ case PERF_RECORD_UNTHROTTLE:
+ min_size = sizeof(struct perf_record_throttle);
+ break;
+ case PERF_RECORD_LOST:
+ min_size = sizeof(struct perf_record_lost);
+ break;
+ case PERF_RECORD_READ:
+ min_size = sizeof(struct perf_record_read);
+ break;
+ case PERF_RECORD_SWITCH:
+ case PERF_RECORD_SWITCH_CPU_WIDE:
+ min_size = sizeof(struct perf_record_switch);
+ break;
+ case PERF_RECORD_AUX:
+ min_size = sizeof(struct perf_record_aux);
+ break;
+ case PERF_RECORD_ITRACE_START:
+ min_size = sizeof(struct perf_record_itrace_start);
+ break;
+ case PERF_RECORD_LOST_SAMPLES:
+ min_size = sizeof(struct perf_record_lost_samples);
+ break;
+ case PERF_RECORD_NAMESPACES:
+ min_size = offsetof(struct perf_record_namespaces, link_info);
+ break;
+ case PERF_RECORD_KSYMBOL:
+ min_size = sizeof(struct perf_record_ksymbol);
+ break;
+ case PERF_RECORD_BPF_EVENT:
+ min_size = sizeof(struct perf_record_bpf_event);
+ break;
+ case PERF_RECORD_CGROUP:
+ min_size = sizeof(struct perf_record_cgroup);
+ break;
+ case PERF_RECORD_TEXT_POKE:
+ min_size = offsetof(struct perf_record_text_poke_event, bytes);
+ break;
+ case PERF_RECORD_AUX_OUTPUT_HW_ID:
+ min_size = sizeof(struct perf_record_aux_output_hw_id);
+ break;
+ case PERF_RECORD_CALLCHAIN_DEFERRED:
+ min_size = sizeof(struct perf_record_callchain_deferred);
+ break;
+ case PERF_RECORD_HEADER_ATTR:
+ min_size = sizeof(struct perf_record_header_attr);
+ break;
+ case PERF_RECORD_HEADER_TRACING_DATA:
+ min_size = sizeof(struct perf_record_header_tracing_data);
+ break;
+ case PERF_RECORD_HEADER_BUILD_ID:
+ min_size = offsetof(struct perf_record_header_build_id, filename) + 1;
+ break;
+ case PERF_RECORD_ID_INDEX:
+ min_size = offsetof(struct perf_record_id_index, entries);
+ break;
+ case PERF_RECORD_AUXTRACE_INFO:
+ min_size = offsetof(struct perf_record_auxtrace_info, priv);
+ break;
+ case PERF_RECORD_AUXTRACE:
+ min_size = sizeof(struct perf_record_auxtrace);
+ break;
+ case PERF_RECORD_AUXTRACE_ERROR:
+ min_size = sizeof(struct perf_record_auxtrace_error);
+ break;
+ case PERF_RECORD_THREAD_MAP:
+ min_size = offsetof(struct perf_record_thread_map, entries);
+ break;
+ case PERF_RECORD_CPU_MAP:
+ min_size = sizeof(struct perf_record_cpu_map);
+ break;
+ case PERF_RECORD_STAT_CONFIG:
+ min_size = offsetof(struct perf_record_stat_config, data);
+ break;
+ case PERF_RECORD_STAT:
+ min_size = sizeof(struct perf_record_stat);
+ break;
+ case PERF_RECORD_STAT_ROUND:
+ min_size = sizeof(struct perf_record_stat_round);
+ break;
+ case PERF_RECORD_EVENT_UPDATE:
+ min_size = sizeof(struct perf_record_event_update);
+ break;
+ case PERF_RECORD_TIME_CONV:
+ min_size = sizeof(struct perf_record_time_conv);
+ break;
+ case PERF_RECORD_HEADER_FEATURE:
+ min_size = offsetof(struct perf_record_header_feature, data);
+ break;
+ case PERF_RECORD_COMPRESSED:
+ min_size = offsetof(struct perf_record_compressed, data);
+ break;
+ case PERF_RECORD_COMPRESSED2:
+ min_size = offsetof(struct perf_record_compressed2, data);
+ break;
+ case PERF_RECORD_BPF_METADATA:
+ min_size = offsetof(struct perf_record_bpf_metadata, entries);
+ break;
+ case PERF_RECORD_SCHEDSTAT_CPU:
+ min_size = sizeof(struct perf_record_schedstat_cpu);
+ break;
+ case PERF_RECORD_SCHEDSTAT_DOMAIN:
+ min_size = sizeof(struct perf_record_schedstat_domain);
+ break;
+ default:
+ break;
}
+ if (event->header.size < min_size)
+ return PyErr_Format(PyExc_ValueError, "Event size %u too small for type %u",
+ event->header.size, event->header.type);
+
+ /* Allocate just enough memory for the size of event. */
+ size = offsetof(struct pyrf_event, event) + event->header.size;
+ pevent = (struct pyrf_event *)PyObject_Malloc(size);
+ if (pevent == NULL)
+ return PyErr_NoMemory();
+
+ /* Copy the event for memory safety and initilaize variables. */
+ PyObject_Init((PyObject *)pevent, pyrf_event__type[event->header.type]);
+ memcpy(&pevent->event, event, event->header.size);
+
+ if (event->header.type == PERF_RECORD_MMAP) {
+ /* Ensure '\0' string termination. */
+ size_t max_len = pevent->event.header.size - offsetof(struct perf_record_mmap, filename);
- ptype = pyrf_event__type[event->header.type];
- pevent = PyObject_New(struct pyrf_event, ptype);
- if (pevent != NULL) {
- memcpy(&pevent->event, event, event->header.size);
- perf_sample__init(&pevent->sample, /*all=*/false);
+ pevent->event.mmap.filename[max_len - 1] = '\0';
+ }
+
+ perf_sample__init(&pevent->sample, /*all=*/true);
+ pevent->al_resolved = false;
+ addr_location__init(&pevent->al);
+
+ if (!evsel)
+ return (PyObject *)pevent;
+
+ /* Parse the sample again so that pointers are within the copied event. */
+ err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample);
+ if (err < 0) {
+ Py_DECREF(pevent);
+ return PyErr_Format(PyExc_OSError,
+ "perf: can't parse sample, err=%d", err);
}
return (PyObject *)pevent;
}
@@ -1207,7 +1678,7 @@ static PyObject *pyrf_evsel__str(PyObject *self)
struct pyrf_evsel *pevsel = (void *)self;
struct evsel *evsel = pevsel->evsel;
- return PyUnicode_FromFormat("evsel(%s/%s/)", evsel__pmu_name(evsel), evsel__name(evsel));
+ return PyUnicode_FromFormat("evsel(%s)", evsel__name(evsel));
}
static PyMethodDef pyrf_evsel__methods[] = {
@@ -1769,9 +2240,11 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
{
struct evlist *evlist = pevlist->evlist;
union perf_event *event;
+ struct evsel *evsel;
int sample_id_all = 1, cpu;
static char *kwlist[] = { "cpu", "sample_id_all", NULL };
struct mmap *md;
+ PyObject *pyevent;
int err;
if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
@@ -1779,44 +2252,31 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
return NULL;
md = get_md(evlist, cpu);
- if (!md) {
- PyErr_Format(PyExc_TypeError, "Unknown CPU '%d'", cpu);
- return NULL;
- }
+ if (!md)
+ return PyErr_Format(PyExc_TypeError, "Unknown CPU '%d'", cpu);
- if (perf_mmap__read_init(&md->core) < 0)
- goto end;
+ err = perf_mmap__read_init(&md->core);
+ if (err < 0) {
+ return PyErr_Format(PyExc_OSError,
+ "perf: error mmap read init, err=%d", err);
+ }
event = perf_mmap__read_event(&md->core);
- if (event != NULL) {
- PyObject *pyevent = pyrf_event__new(event);
- struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
- struct evsel *evsel;
-
- if (pyevent == NULL)
- return PyErr_NoMemory();
-
- evsel = evlist__event2evsel(evlist, event);
- if (!evsel) {
- Py_DECREF(pyevent);
- Py_INCREF(Py_None);
- return Py_None;
- }
+ if (event == NULL)
+ Py_RETURN_NONE;
+ evsel = evlist__event2evsel(evlist, event);
+ if (!evsel) {
+ /* Unknown evsel. */
perf_mmap__consume(&md->core);
-
- err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample);
- if (err) {
- Py_DECREF(pyevent);
- return PyErr_Format(PyExc_OSError,
- "perf: can't parse sample, err=%d", err);
- }
-
- return pyevent;
+ Py_RETURN_NONE;
}
-end:
- Py_INCREF(Py_None);
- return Py_None;
+ pyevent = pyrf_event__new(event, evsel, evlist__session(evlist));
+ perf_mmap__consume(&md->core);
+ if (pyevent == NULL)
+ return PyErr_Occurred() ? NULL : PyErr_NoMemory();
+
+ return pyevent;
}
static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
@@ -2011,10 +2471,7 @@ static PyObject *pyrf_evlist__str(PyObject *self)
evlist__for_each_entry(pevlist->evlist, pos) {
if (!first)
strbuf_addch(&sb, ',');
- if (!pos->pmu)
- strbuf_addstr(&sb, evsel__name(pos));
- else
- strbuf_addf(&sb, "%s/%s/", pos->pmu->name, evsel__name(pos));
+ strbuf_addstr(&sb, evsel__name(pos));
first = false;
}
strbuf_addstr(&sb, "])");
@@ -2525,19 +2982,12 @@ static int pyrf_session_tool__sample(const struct perf_tool *tool,
struct machine *machine __maybe_unused)
{
struct pyrf_session *psession = container_of(tool, struct pyrf_session, tool);
- PyObject *pyevent = pyrf_event__new(event);
- struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
+ PyObject *pyevent = pyrf_event__new(event, sample->evsel, psession->session);
PyObject *ret;
if (pyevent == NULL)
return -ENOMEM;
- memcpy(&pevent->event, event, event->header.size);
- if (evsel__parse_sample(evsel, &pevent->event, &pevent->sample) < 0) {
- Py_DECREF(pyevent);
- return -1;
- }
-
ret = PyObject_CallFunction(psession->sample, "O", pyevent);
if (!ret) {
Py_DECREF(pyevent);
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 10/58] perf evsel: Add reference count
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
As with evlist this a no-op for most of the perf tool. The reference
count is set to 1 at allocation, the put will see the 1, decrement it
and perform the delete. The purpose for adding the reference count is
for the python code. Prior to this change the python code would clone
evsels, but this has issues if events are opened, etc. leading to
assertion failures. With a reference count the same evsel can be used
and the reference count incremented for the python usage. To not
change the python evsel API getset functions are added for the evsel
members, no set function is provided for size as it doesn't make sense
to alter this.
Signed-off-by: Ian Rogers <irogers@google.com>
---
v2:
1. Fixed Potential Crash in pyrf_event__new : Initialized
pevent->evsel = NULL; to avoid garbage pointer dereference if
evlist__event2evsel() fails in read_on_cpu .
2. Fixed Memory Leak in pyrf_evsel__init : Added
evsel__put(pevsel->evsel) before overwriting it to handle repeated
__init__ calls.
3. Fixed Exception Contract: Added PyErr_NoMemory() when evsel__new()
fails in pyrf_evsel__init .
4. Fixed NULL Pointer Dereference on Property Access: Added a custom
tp_getattro ( pyrf_evsel__getattro ) to pyrf_evsel__type to check
if pevsel->evsel is NULL and raise a ValueError if so, covering all
property accesses.
5. Fixed Reference Count in pyrf_evlist__add : Added evsel__get(evsel)
when adding to the evlist .
6. Fixed Reference Count in pyrf_evlist__read_on_cpu : Added
evsel__get(evsel) when assigning to pevent->evsel .
v7:
- Added pyrf_evsel__new to zero-initialize pevsel->evsel to fix
crash on re-initialization.
v8:
- Added O! type validation to pyrf_evlist__add to prevent type
confusion.
---
tools/perf/builtin-trace.c | 12 +-
tools/perf/tests/evsel-tp-sched.c | 4 +-
tools/perf/tests/openat-syscall-all-cpus.c | 6 +-
tools/perf/tests/openat-syscall.c | 6 +-
tools/perf/util/bpf_counter_cgroup.c | 2 +-
tools/perf/util/cgroup.c | 2 +-
tools/perf/util/evlist.c | 2 +-
tools/perf/util/evsel.c | 26 ++-
tools/perf/util/evsel.h | 11 +-
tools/perf/util/parse-events.y | 2 +-
tools/perf/util/pfm.c | 2 +-
tools/perf/util/print-events.c | 2 +-
tools/perf/util/python.c | 245 +++++++++++++++++----
tools/perf/util/session.c | 1 +
14 files changed, 249 insertions(+), 74 deletions(-)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index da703d762433..6ea935c13538 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -448,10 +448,10 @@ static int evsel__init_tp_ptr_field(struct evsel *evsel, struct tp_field *field,
({ struct syscall_tp *sc = __evsel__syscall_tp(evsel);\
evsel__init_tp_ptr_field(evsel, &sc->name, #name); })
-static void evsel__delete_priv(struct evsel *evsel)
+static void evsel__put_and_free_priv(struct evsel *evsel)
{
zfree(&evsel->priv);
- evsel__delete(evsel);
+ evsel__put(evsel);
}
static int evsel__init_syscall_tp(struct evsel *evsel)
@@ -531,7 +531,7 @@ static struct evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *
return evsel;
out_delete:
- evsel__delete_priv(evsel);
+ evsel__put_and_free_priv(evsel);
return NULL;
}
@@ -3584,7 +3584,7 @@ static bool evlist__add_vfs_getname(struct evlist *evlist)
list_del_init(&evsel->core.node);
evsel->evlist = NULL;
- evsel__delete(evsel);
+ evsel__put(evsel);
}
return found;
@@ -3698,9 +3698,9 @@ static int trace__add_syscall_newtp(struct trace *trace)
return ret;
out_delete_sys_exit:
- evsel__delete_priv(sys_exit);
+ evsel__put_and_free_priv(sys_exit);
out_delete_sys_enter:
- evsel__delete_priv(sys_enter);
+ evsel__put_and_free_priv(sys_enter);
goto out;
}
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 226196fb9677..9e456f88a13a 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -64,7 +64,7 @@ static int test__perf_evsel__tp_sched_test(struct test_suite *test __maybe_unuse
if (evsel__test_field(evsel, "next_prio", 4, true))
ret = TEST_FAIL;
- evsel__delete(evsel);
+ evsel__put(evsel);
evsel = evsel__newtp("sched", "sched_wakeup");
@@ -85,7 +85,7 @@ static int test__perf_evsel__tp_sched_test(struct test_suite *test __maybe_unuse
if (evsel__test_field(evsel, "target_cpu", 4, true))
ret = TEST_FAIL;
- evsel__delete(evsel);
+ evsel__put(evsel);
return ret;
}
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 0be43f8db3bd..cc63df2b3bc5 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -59,7 +59,7 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
err = TEST_SKIP;
- goto out_evsel_delete;
+ goto out_evsel_put;
}
perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
@@ -116,8 +116,8 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
evsel__free_counts(evsel);
out_close_fd:
perf_evsel__close_fd(&evsel->core);
-out_evsel_delete:
- evsel__delete(evsel);
+out_evsel_put:
+ evsel__put(evsel);
out_cpu_map_delete:
perf_cpu_map__put(cpus);
out_thread_map_delete:
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index b54cbe5f1808..9f16f0dd3a29 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -42,7 +42,7 @@ static int test__openat_syscall_event(struct test_suite *test __maybe_unused,
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
err = TEST_SKIP;
- goto out_evsel_delete;
+ goto out_evsel_put;
}
for (i = 0; i < nr_openat_calls; ++i) {
@@ -64,8 +64,8 @@ static int test__openat_syscall_event(struct test_suite *test __maybe_unused,
err = TEST_OK;
out_close_fd:
perf_evsel__close_fd(&evsel->core);
-out_evsel_delete:
- evsel__delete(evsel);
+out_evsel_put:
+ evsel__put(evsel);
out_thread_map_delete:
perf_thread_map__put(threads);
return err;
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index 519fee3dc3d0..339df94ef438 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -316,7 +316,7 @@ static int bperf_cgrp__destroy(struct evsel *evsel)
return 0;
bperf_cgroup_bpf__destroy(skel);
- evsel__delete(cgrp_switch); // it'll destroy on_switch progs too
+ evsel__put(cgrp_switch); // it'll destroy on_switch progs too
return 0;
}
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 652a45aac828..914744724467 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -469,7 +469,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, bool open_cgro
/* copy the list and set to the new cgroup. */
evlist__for_each_entry(orig_list, pos) {
- struct evsel *evsel = evsel__clone(/*dest=*/NULL, pos);
+ struct evsel *evsel = evsel__clone(pos);
if (evsel == NULL)
goto out_err;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b5a7895debf5..a362f338f104 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -194,7 +194,7 @@ static void evlist__purge(struct evlist *evlist)
evlist__for_each_entry_safe(evlist, n, pos) {
list_del_init(&pos->core.node);
pos->evlist = NULL;
- evsel__delete(pos);
+ evsel__put(pos);
}
evlist->core.nr_entries = 0;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e03727d395e9..a54aae079c22 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -388,10 +388,11 @@ bool evsel__is_function_event(struct evsel *evsel)
#undef FUNCTION_EVENT
}
-void evsel__init(struct evsel *evsel,
+static void evsel__init(struct evsel *evsel,
struct perf_event_attr *attr, int idx)
{
perf_evsel__init(&evsel->core, attr, idx);
+ refcount_set(&evsel->refcnt, 1);
evsel->tracking = !idx;
evsel->unit = strdup("");
evsel->scale = 1.0;
@@ -472,7 +473,7 @@ static int evsel__copy_config_terms(struct evsel *dst, struct evsel *src)
* The assumption is that @orig is not configured nor opened yet.
* So we only care about the attributes that can be set while it's parsed.
*/
-struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig)
+struct evsel *evsel__clone(struct evsel *orig)
{
struct evsel *evsel;
@@ -485,11 +486,7 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig)
if (orig->bpf_obj)
return NULL;
- if (dest)
- evsel = dest;
- else
- evsel = evsel__new(&orig->core.attr);
-
+ evsel = evsel__new(&orig->core.attr);
if (evsel == NULL)
return NULL;
@@ -574,7 +571,7 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig)
return evsel;
out_err:
- evsel__delete(evsel);
+ evsel__put(evsel);
return NULL;
}
@@ -633,6 +630,12 @@ struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool
return ERR_PTR(err);
}
+struct evsel *evsel__get(struct evsel *evsel)
+{
+ refcount_inc(&evsel->refcnt);
+ return evsel;
+}
+
#ifdef HAVE_LIBTRACEEVENT
struct tep_event *evsel__tp_format(struct evsel *evsel)
{
@@ -1857,7 +1860,7 @@ void evsel__set_priv_destructor(void (*destructor)(void *priv))
evsel__priv_destructor = destructor;
}
-void evsel__exit(struct evsel *evsel)
+static void evsel__exit(struct evsel *evsel)
{
assert(list_empty(&evsel->core.node));
assert(evsel->evlist == NULL);
@@ -1892,11 +1895,14 @@ void evsel__exit(struct evsel *evsel)
xyarray__delete(evsel->start_times);
}
-void evsel__delete(struct evsel *evsel)
+void evsel__put(struct evsel *evsel)
{
if (!evsel)
return;
+ if (!refcount_dec_and_test(&evsel->refcnt))
+ return;
+
evsel__exit(evsel);
free(evsel);
}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b099c8e5dd86..35b1bbca9036 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -6,6 +6,7 @@
#include <linux/list.h>
#include <linux/perf_event.h>
+#include <linux/refcount.h>
#include <linux/types.h>
#include <sys/types.h>
@@ -47,6 +48,7 @@ typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
struct evsel {
struct perf_evsel core;
struct evlist *evlist;
+ refcount_t refcnt;
off_t id_offset;
int id_pos;
int is_pos;
@@ -262,7 +264,7 @@ static inline struct evsel *evsel__new(struct perf_event_attr *attr)
return evsel__new_idx(attr, 0);
}
-struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig);
+struct evsel *evsel__clone(struct evsel *orig);
int copy_config_terms(struct list_head *dst, struct list_head *src);
void free_config_terms(struct list_head *config_terms);
@@ -277,14 +279,13 @@ static inline struct evsel *evsel__newtp(const char *sys, const char *name)
return evsel__newtp_idx(sys, name, 0, true);
}
+struct evsel *evsel__get(struct evsel *evsel);
+void evsel__put(struct evsel *evsel);
+
#ifdef HAVE_LIBTRACEEVENT
struct tep_event *evsel__tp_format(struct evsel *evsel);
#endif
-void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx);
-void evsel__exit(struct evsel *evsel);
-void evsel__delete(struct evsel *evsel);
-
void evsel__set_priv_destructor(void (*destructor)(void *priv));
struct callchain_param;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index c194de5ec1ec..b531b1f0ceb3 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -47,7 +47,7 @@ static void free_list_evsel(struct list_head* list_evsel)
list_for_each_entry_safe(evsel, tmp, list_evsel, core.node) {
list_del_init(&evsel->core.node);
- evsel__delete(evsel);
+ evsel__put(evsel);
}
free(list_evsel);
}
diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c
index d9043f4afbe7..5f53c2f68a96 100644
--- a/tools/perf/util/pfm.c
+++ b/tools/perf/util/pfm.c
@@ -159,7 +159,7 @@ static bool is_libpfm_event_supported(const char *name, struct perf_cpu_map *cpu
result = false;
evsel__close(evsel);
- evsel__delete(evsel);
+ evsel__put(evsel);
return result;
}
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index cb27e2898aa0..0242243681b6 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -174,7 +174,7 @@ bool is_event_supported(u8 type, u64 config)
}
evsel__close(evsel);
- evsel__delete(evsel);
+ evsel__put(evsel);
}
perf_thread_map__put(tmap);
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index aeecdb497fac..3573c7dd312b 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -274,6 +274,7 @@ static PyMemberDef pyrf_sample_event__members[] = {
static void pyrf_sample_event__delete(struct pyrf_event *pevent)
{
+ evsel__put(pevent->evsel);
perf_sample__exit(&pevent->sample);
Py_TYPE(pevent)->tp_free((PyObject*)pevent);
}
@@ -506,8 +507,10 @@ static PyObject *pyrf_event__new(const union perf_event *event)
ptype = pyrf_event__type[event->header.type];
pevent = PyObject_New(struct pyrf_event, ptype);
- if (pevent != NULL)
+ if (pevent != NULL) {
memcpy(&pevent->event, event, event->header.size);
+ pevent->evsel = NULL;
+ }
return (PyObject *)pevent;
}
@@ -945,7 +948,7 @@ static int pyrf_counts_values__setup_types(void)
struct pyrf_evsel {
PyObject_HEAD
- struct evsel evsel;
+ struct evsel *evsel;
};
static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
@@ -1053,20 +1056,25 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
attr.sample_id_all = sample_id_all;
attr.size = sizeof(attr);
- evsel__init(&pevsel->evsel, &attr, idx);
+ evsel__put(pevsel->evsel);
+ pevsel->evsel = evsel__new(&attr);
+ if (!pevsel->evsel) {
+ PyErr_NoMemory();
+ return -1;
+ }
return 0;
}
static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
{
- evsel__exit(&pevsel->evsel);
+ evsel__put(pevsel->evsel);
Py_TYPE(pevsel)->tp_free((PyObject*)pevsel);
}
static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
PyObject *args, PyObject *kwargs)
{
- struct evsel *evsel = &pevsel->evsel;
+ struct evsel *evsel = pevsel->evsel;
struct perf_cpu_map *cpus = NULL;
struct perf_thread_map *threads = NULL;
PyObject *pcpus = NULL, *pthreads = NULL;
@@ -1102,7 +1110,7 @@ static PyObject *pyrf_evsel__cpus(struct pyrf_evsel *pevsel)
struct pyrf_cpu_map *pcpu_map = PyObject_New(struct pyrf_cpu_map, &pyrf_cpu_map__type);
if (pcpu_map)
- pcpu_map->cpus = perf_cpu_map__get(pevsel->evsel.core.cpus);
+ pcpu_map->cpus = perf_cpu_map__get(pevsel->evsel->core.cpus);
return (PyObject *)pcpu_map;
}
@@ -1113,7 +1121,7 @@ static PyObject *pyrf_evsel__threads(struct pyrf_evsel *pevsel)
PyObject_New(struct pyrf_thread_map, &pyrf_thread_map__type);
if (pthread_map)
- pthread_map->threads = perf_thread_map__get(pevsel->evsel.core.threads);
+ pthread_map->threads = perf_thread_map__get(pevsel->evsel->core.threads);
return (PyObject *)pthread_map;
}
@@ -1147,7 +1155,7 @@ static int evsel__ensure_counts(struct evsel *evsel)
static PyObject *pyrf_evsel__read(struct pyrf_evsel *pevsel,
PyObject *args, PyObject *kwargs)
{
- struct evsel *evsel = &pevsel->evsel;
+ struct evsel *evsel = pevsel->evsel;
int cpu = 0, cpu_idx, thread = 0, thread_idx;
struct perf_counts_values *old_count, *new_count;
struct pyrf_counts_values *count_values = PyObject_New(struct pyrf_counts_values,
@@ -1192,7 +1200,7 @@ static PyObject *pyrf_evsel__read(struct pyrf_evsel *pevsel,
static PyObject *pyrf_evsel__str(PyObject *self)
{
struct pyrf_evsel *pevsel = (void *)self;
- struct evsel *evsel = &pevsel->evsel;
+ struct evsel *evsel = pevsel->evsel;
return PyUnicode_FromFormat("evsel(%s/%s/)", evsel__pmu_name(evsel), evsel__name(evsel));
}
@@ -1225,30 +1233,183 @@ static PyMethodDef pyrf_evsel__methods[] = {
{ .ml_name = NULL, }
};
-#define evsel_member_def(member, ptype, help) \
- { #member, ptype, \
- offsetof(struct pyrf_evsel, evsel.member), \
- 0, help }
+static PyObject *pyrf_evsel__get_tracking(PyObject *self, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
-#define evsel_attr_member_def(member, ptype, help) \
- { #member, ptype, \
- offsetof(struct pyrf_evsel, evsel.core.attr.member), \
- 0, help }
+ if (pevsel->evsel->tracking)
+ Py_RETURN_TRUE;
+ else
+ Py_RETURN_FALSE;
+}
-static PyMemberDef pyrf_evsel__members[] = {
- evsel_member_def(tracking, T_BOOL, "tracking event."),
- evsel_attr_member_def(type, T_UINT, "attribute type."),
- evsel_attr_member_def(size, T_UINT, "attribute size."),
- evsel_attr_member_def(config, T_ULONGLONG, "attribute config."),
- evsel_attr_member_def(sample_period, T_ULONGLONG, "attribute sample_period."),
- evsel_attr_member_def(sample_type, T_ULONGLONG, "attribute sample_type."),
- evsel_attr_member_def(read_format, T_ULONGLONG, "attribute read_format."),
- evsel_attr_member_def(wakeup_events, T_UINT, "attribute wakeup_events."),
- { .name = NULL, },
+static int pyrf_evsel__set_tracking(PyObject *self, PyObject *val, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ pevsel->evsel->tracking = Py_IsTrue(val) ? true : false;
+ return 0;
+}
+
+static int pyrf_evsel__set_attr_config(PyObject *self, PyObject *val, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ pevsel->evsel->core.attr.config = PyLong_AsUnsignedLongLong(val);
+ return PyErr_Occurred() ? -1 : 0;
+}
+
+static PyObject *pyrf_evsel__get_attr_config(PyObject *self, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ return PyLong_FromUnsignedLongLong(pevsel->evsel->core.attr.config);
+}
+
+static int pyrf_evsel__set_attr_read_format(PyObject *self, PyObject *val, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ pevsel->evsel->core.attr.read_format = PyLong_AsUnsignedLongLong(val);
+ return PyErr_Occurred() ? -1 : 0;
+}
+
+static PyObject *pyrf_evsel__get_attr_read_format(PyObject *self, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ return PyLong_FromUnsignedLongLong(pevsel->evsel->core.attr.read_format);
+}
+
+static int pyrf_evsel__set_attr_sample_period(PyObject *self, PyObject *val, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ pevsel->evsel->core.attr.sample_period = PyLong_AsUnsignedLongLong(val);
+ return PyErr_Occurred() ? -1 : 0;
+}
+
+static PyObject *pyrf_evsel__get_attr_sample_period(PyObject *self, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ return PyLong_FromUnsignedLongLong(pevsel->evsel->core.attr.sample_period);
+}
+
+static int pyrf_evsel__set_attr_sample_type(PyObject *self, PyObject *val, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ pevsel->evsel->core.attr.sample_type = PyLong_AsUnsignedLongLong(val);
+ return PyErr_Occurred() ? -1 : 0;
+}
+
+static PyObject *pyrf_evsel__get_attr_sample_type(PyObject *self, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ return PyLong_FromUnsignedLongLong(pevsel->evsel->core.attr.sample_type);
+}
+
+static PyObject *pyrf_evsel__get_attr_size(PyObject *self, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ return PyLong_FromUnsignedLong(pevsel->evsel->core.attr.size);
+}
+
+static int pyrf_evsel__set_attr_type(PyObject *self, PyObject *val, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ pevsel->evsel->core.attr.type = PyLong_AsUnsignedLong(val);
+ return PyErr_Occurred() ? -1 : 0;
+}
+
+static PyObject *pyrf_evsel__get_attr_type(PyObject *self, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ return PyLong_FromUnsignedLong(pevsel->evsel->core.attr.type);
+}
+
+static int pyrf_evsel__set_attr_wakeup_events(PyObject *self, PyObject *val, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ pevsel->evsel->core.attr.wakeup_events = PyLong_AsUnsignedLong(val);
+ return PyErr_Occurred() ? -1 : 0;
+}
+
+static PyObject *pyrf_evsel__get_attr_wakeup_events(PyObject *self, void */*closure*/)
+{
+ struct pyrf_evsel *pevsel = (void *)self;
+
+ return PyLong_FromUnsignedLong(pevsel->evsel->core.attr.wakeup_events);
+}
+
+static PyGetSetDef pyrf_evsel__getset[] = {
+ {
+ .name = "tracking",
+ .get = pyrf_evsel__get_tracking,
+ .set = pyrf_evsel__set_tracking,
+ .doc = "tracking event.",
+ },
+ {
+ .name = "config",
+ .get = pyrf_evsel__get_attr_config,
+ .set = pyrf_evsel__set_attr_config,
+ .doc = "attribute config.",
+ },
+ {
+ .name = "read_format",
+ .get = pyrf_evsel__get_attr_read_format,
+ .set = pyrf_evsel__set_attr_read_format,
+ .doc = "attribute read_format.",
+ },
+ {
+ .name = "sample_period",
+ .get = pyrf_evsel__get_attr_sample_period,
+ .set = pyrf_evsel__set_attr_sample_period,
+ .doc = "attribute sample_period.",
+ },
+ {
+ .name = "sample_type",
+ .get = pyrf_evsel__get_attr_sample_type,
+ .set = pyrf_evsel__set_attr_sample_type,
+ .doc = "attribute sample_type.",
+ },
+ {
+ .name = "size",
+ .get = pyrf_evsel__get_attr_size,
+ .doc = "attribute size.",
+ },
+ {
+ .name = "type",
+ .get = pyrf_evsel__get_attr_type,
+ .set = pyrf_evsel__set_attr_type,
+ .doc = "attribute type.",
+ },
+ {
+ .name = "wakeup_events",
+ .get = pyrf_evsel__get_attr_wakeup_events,
+ .set = pyrf_evsel__set_attr_wakeup_events,
+ .doc = "attribute wakeup_events.",
+ },
+ { .name = NULL},
};
static const char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object.");
+static PyObject *pyrf_evsel__getattro(struct pyrf_evsel *pevsel, PyObject *attr_name)
+{
+ if (!pevsel->evsel) {
+ PyErr_SetString(PyExc_ValueError, "evsel not initialized");
+ return NULL;
+ }
+ return PyObject_GenericGetAttr((PyObject *) pevsel, attr_name);
+}
+
static PyTypeObject pyrf_evsel__type = {
PyVarObject_HEAD_INIT(NULL, 0)
.tp_name = "perf.evsel",
@@ -1256,16 +1417,27 @@ static PyTypeObject pyrf_evsel__type = {
.tp_dealloc = (destructor)pyrf_evsel__delete,
.tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
.tp_doc = pyrf_evsel__doc,
- .tp_members = pyrf_evsel__members,
+ .tp_getset = pyrf_evsel__getset,
.tp_methods = pyrf_evsel__methods,
.tp_init = (initproc)pyrf_evsel__init,
.tp_str = pyrf_evsel__str,
.tp_repr = pyrf_evsel__str,
+ .tp_getattro = (getattrofunc) pyrf_evsel__getattro,
};
+static PyObject *pyrf_evsel__new(PyTypeObject *type, PyObject *args, PyObject *kwargs)
+{
+ struct pyrf_evsel *pevsel;
+
+ pevsel = (struct pyrf_evsel *)PyType_GenericNew(type, args, kwargs);
+ if (pevsel)
+ pevsel->evsel = NULL;
+ return (PyObject *)pevsel;
+}
+
static int pyrf_evsel__setup_types(void)
{
- pyrf_evsel__type.tp_new = PyType_GenericNew;
+ pyrf_evsel__type.tp_new = pyrf_evsel__new;
return PyType_Ready(&pyrf_evsel__type);
}
@@ -1562,13 +1734,13 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
PyObject *pevsel;
struct evsel *evsel;
- if (!PyArg_ParseTuple(args, "O", &pevsel))
+ if (!PyArg_ParseTuple(args, "O!", &pyrf_evsel__type, &pevsel))
return NULL;
Py_INCREF(pevsel);
- evsel = &((struct pyrf_evsel *)pevsel)->evsel;
+ evsel = ((struct pyrf_evsel *)pevsel)->evsel;
evsel->core.idx = evlist->core.nr_entries;
- evlist__add(evlist, evsel);
+ evlist__add(evlist, evsel__get(evsel));
return Py_BuildValue("i", evlist->core.nr_entries);
}
@@ -1626,7 +1798,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
return Py_None;
}
- pevent->evsel = evsel;
+ pevent->evsel = evsel__get(evsel);
perf_mmap__consume(&md->core);
@@ -1803,12 +1975,7 @@ static PyObject *pyrf_evsel__from_evsel(struct evsel *evsel)
if (!pevsel)
return NULL;
- memset(&pevsel->evsel, 0, sizeof(pevsel->evsel));
- evsel__init(&pevsel->evsel, &evsel->core.attr, evsel->core.idx);
-
- evsel__clone(&pevsel->evsel, evsel);
- if (evsel__is_group_leader(evsel))
- evsel__set_leader(&pevsel->evsel, &pevsel->evsel);
+ pevsel->evsel = evsel__get(evsel);
return (PyObject *)pevsel;
}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1ac6cd43c38b..deb5b9dfe44c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1373,6 +1373,7 @@ static int evlist__deliver_deferred_callchain(struct evlist *evlist,
sample->evsel = evlist__id2evsel(evlist, sample->id);
ret = tool->callchain_deferred(tool, event, sample,
sample->evsel, machine);
+ evsel__put(sample->evsel);
sample->evsel = saved_evsel;
return ret;
}
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 14/58] perf python: Add python session abstraction wrapping perf's session
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Sessions are necessary to be able to use perf.data files within a
tool. Add a wrapper python type that incorporates the tool. Allow a
sample callback to be passed when creating the session. When
process_events is run this callback will be called, if supplied, for
sample events.
An example use looks like:
```
$ perf record -e cycles,instructions -a sleep 3
$ PYTHONPATH=..../perf/python python3
Python 3.13.7 (main, Aug 20 2025, 22:17:40) [GCC 14.2.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import perf
>>> count=0
... def handle_sample(x):
... global count
... if count < 3:
... print(dir(x))
... count = count + 1
... perf.session(perf.data("perf.data"),sample=handle_sample).process_events()
...
['__class__', '__delattr__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getstate__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__le__', '__lt__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', 'sample_addr', 'sample_cpu', 'sample_id', 'sample_ip', 'sample_period', 'sample_pid', 'sample_stream_id', 'sample_tid', 'sample_time', 'type']
['__class__', '__delattr__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getstate__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__le__', '__lt__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', 'sample_addr', 'sample_cpu', 'sample_id', 'sample_ip', 'sample_period', 'sample_pid', 'sample_stream_id', 'sample_tid', 'sample_time', 'type']
['__class__', '__delattr__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getstate__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__le__', '__lt__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', 'sample_addr', 'sample_cpu', 'sample_id', 'sample_ip', 'sample_period', 'sample_pid', 'sample_stream_id', 'sample_tid', 'sample_time', 'type']
```
Also, add the ability to get the thread associated with a session. For
threads, allow the comm string to be retrieved. This can be useful for
filtering threads. Connect up some of the standard event handling in
psession->tool to better support queries of the machine. Also connect
up the symbols.
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
v2:
1. Fixed Potential Crash in pyrf_thread__comm : Used
thread__comm_str() to safely retrieve the command name, avoiding a
crash if thread__comm() returns NULL.
2. Fixed Double Free Risk: Zeroed out user_regs , intr_regs , and
callchain in the shallow copy of perf_sample to prevent Python from
attempting to free pointers it doesn't own.
3. Fixed Memory Leak & Exception Handling in Callback: Handled the
return value of PyObject_CallFunction() to avoid leaks, and checked
for failure to abort the loop and propagate Python exceptions
cleanly.
4. Enforced Type Safety: Used O! with &pyrf_data__type in
PyArg_ParseTupleAndKeywords to prevent bad casts from passing
arbitrary objects as perf.data.
5. Added Missing Build ID Handler: Registered
perf_event__process_build_id to allow correct symbol resolution.
6. Fixed Double Free Crash on Init Failure: Set session and pdata to
NULL on failure to prevent tp_dealloc from double-freeing them.
7. Preserved C-level Errors: Made pyrf_session__process_events return
the error code integer rather than always returning None .
v7:
- Fixed NULL comm handling.
- Avoided swallowing exceptions in module init.
- Fixed checkpatch warning for missing blank line.
v8:
- Switch from pyrf_session__init to pyrf_session__new to avoid dealing with a
potentially NULL session variable.
- Added pid, tid, ppid, and cpu attributes to perf.thread.
---
tools/perf/util/python.c | 310 ++++++++++++++++++++++++++++++++++++++-
1 file changed, 304 insertions(+), 6 deletions(-)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index c002181d96f4..4e7add7d18c4 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -9,8 +9,10 @@
#include <perf/mmap.h>
#include "callchain.h"
+#include "comm.h"
#include "counts.h"
#include "data.h"
+#include "debug.h"
#include "event.h"
#include "evlist.h"
#include "evsel.h"
@@ -20,8 +22,12 @@
#include "pmus.h"
#include "print_binary.h"
#include "record.h"
+#include "session.h"
#include "strbuf.h"
+#include "symbol.h"
+#include "thread.h"
#include "thread_map.h"
+#include "tool.h"
#include "tp_pmu.h"
#include "trace-event.h"
#include "util/sample.h"
@@ -2413,6 +2419,287 @@ static int pyrf_data__setup_types(void)
return PyType_Ready(&pyrf_data__type);
}
+struct pyrf_thread {
+ PyObject_HEAD
+
+ struct thread *thread;
+};
+
+static void pyrf_thread__delete(struct pyrf_thread *pthread)
+{
+ thread__put(pthread->thread);
+ Py_TYPE(pthread)->tp_free((PyObject *)pthread);
+}
+
+static PyObject *pyrf_thread__comm(PyObject *obj)
+{
+ struct pyrf_thread *pthread = (void *)obj;
+ const char *str = thread__comm_str(pthread->thread);
+
+ if (!str)
+ Py_RETURN_NONE;
+
+ return PyUnicode_FromString(str);
+}
+
+static PyMethodDef pyrf_thread__methods[] = {
+ {
+ .ml_name = "comm",
+ .ml_meth = (PyCFunction)pyrf_thread__comm,
+ .ml_flags = METH_NOARGS,
+ .ml_doc = PyDoc_STR("Comm(and) associated with this thread.")
+ },
+ { .ml_name = NULL, }
+};
+
+static PyObject *pyrf_thread__get_pid(struct pyrf_thread *pthread, void *closure __maybe_unused)
+{
+ return PyLong_FromLong(thread__pid(pthread->thread));
+}
+
+static PyObject *pyrf_thread__get_tid(struct pyrf_thread *pthread, void *closure __maybe_unused)
+{
+ return PyLong_FromLong(thread__tid(pthread->thread));
+}
+
+static PyObject *pyrf_thread__get_ppid(struct pyrf_thread *pthread, void *closure __maybe_unused)
+{
+ return PyLong_FromLong(thread__ppid(pthread->thread));
+}
+
+static PyObject *pyrf_thread__get_cpu(struct pyrf_thread *pthread, void *closure __maybe_unused)
+{
+ return PyLong_FromLong(thread__cpu(pthread->thread));
+}
+
+static PyGetSetDef pyrf_thread__getset[] = {
+ { .name = "pid", .get = (getter)pyrf_thread__get_pid, .doc = "process ID" },
+ { .name = "tid", .get = (getter)pyrf_thread__get_tid, .doc = "thread ID" },
+ { .name = "ppid", .get = (getter)pyrf_thread__get_ppid, .doc = "parent process ID" },
+ { .name = "cpu", .get = (getter)pyrf_thread__get_cpu, .doc = "cpu number" },
+ { .name = NULL }
+};
+
+static const char pyrf_thread__doc[] = PyDoc_STR("perf thread object.");
+
+static PyTypeObject pyrf_thread__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.thread",
+ .tp_basicsize = sizeof(struct pyrf_thread),
+ .tp_dealloc = (destructor)pyrf_thread__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_methods = pyrf_thread__methods,
+ .tp_getset = pyrf_thread__getset,
+ .tp_doc = pyrf_thread__doc,
+};
+
+static int pyrf_thread__setup_types(void)
+{
+ return PyType_Ready(&pyrf_thread__type);
+}
+
+static PyObject *pyrf_thread__from_thread(struct thread *thread)
+{
+ struct pyrf_thread *pthread = PyObject_New(struct pyrf_thread, &pyrf_thread__type);
+
+ if (!pthread)
+ return NULL;
+
+ pthread->thread = thread__get(thread);
+ return (PyObject *)pthread;
+}
+
+struct pyrf_session {
+ PyObject_HEAD
+
+ struct perf_session *session;
+ struct perf_tool tool;
+ struct pyrf_data *pdata;
+ PyObject *sample;
+};
+
+static int pyrf_session_tool__sample(const struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct evsel *evsel,
+ struct machine *machine __maybe_unused)
+{
+ struct pyrf_session *psession = container_of(tool, struct pyrf_session, tool);
+ PyObject *pyevent = pyrf_event__new(event);
+ struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
+ PyObject *ret;
+
+ if (pyevent == NULL)
+ return -ENOMEM;
+
+ memcpy(&pevent->event, event, event->header.size);
+ if (evsel__parse_sample(evsel, &pevent->event, &pevent->sample) < 0) {
+ Py_DECREF(pyevent);
+ return -1;
+ }
+
+ ret = PyObject_CallFunction(psession->sample, "O", pyevent);
+ if (!ret) {
+ Py_DECREF(pyevent);
+ return -1;
+ }
+ Py_DECREF(ret);
+ Py_DECREF(pyevent);
+ return 0;
+}
+
+static PyObject *pyrf_session__find_thread(struct pyrf_session *psession, PyObject *args)
+{
+ struct machine *machine;
+ struct thread *thread = NULL;
+ PyObject *result;
+ int pid;
+
+ if (!PyArg_ParseTuple(args, "i", &pid))
+ return NULL;
+
+ machine = &psession->session->machines.host;
+ thread = machine__find_thread(machine, pid, pid);
+
+ if (!thread) {
+ machine = perf_session__find_machine(psession->session, pid);
+ if (machine)
+ thread = machine__find_thread(machine, pid, pid);
+ }
+
+ if (!thread) {
+ PyErr_Format(PyExc_TypeError, "Failed to find thread %d", pid);
+ return NULL;
+ }
+ result = pyrf_thread__from_thread(thread);
+ thread__put(thread);
+ return result;
+}
+
+static PyObject *pyrf_session__new(PyTypeObject *type, PyObject *args, PyObject *kwargs)
+{
+ struct pyrf_data *pdata;
+ PyObject *sample = NULL;
+ static char *kwlist[] = { "data", "sample", NULL };
+ struct pyrf_session *psession;
+ struct perf_session *session;
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O!|O", kwlist, &pyrf_data__type, &pdata,
+ &sample))
+ return NULL;
+
+ psession = PyObject_New(struct pyrf_session, type);
+ if (!psession)
+ return NULL;
+
+ psession->session = NULL;
+ psession->sample = NULL;
+
+ Py_INCREF(pdata);
+ psession->pdata = pdata;
+
+ perf_tool__init(&psession->tool, /*ordered_events=*/true);
+ psession->tool.ordering_requires_timestamps = true;
+
+ #define ADD_TOOL(name) \
+ do { \
+ if (name) { \
+ if (!PyCallable_Check(name)) { \
+ PyErr_SetString(PyExc_TypeError, #name " must be callable"); \
+ goto err_out; \
+ } \
+ psession->tool.name = pyrf_session_tool__##name; \
+ Py_INCREF(name); \
+ psession->name = name; \
+ } \
+ } while (0)
+
+ ADD_TOOL(sample);
+ #undef ADD_TOOL
+
+ psession->tool.comm = perf_event__process_comm;
+ psession->tool.mmap = perf_event__process_mmap;
+ psession->tool.mmap2 = perf_event__process_mmap2;
+ psession->tool.namespaces = perf_event__process_namespaces;
+ psession->tool.cgroup = perf_event__process_cgroup;
+ psession->tool.exit = perf_event__process_exit;
+ psession->tool.fork = perf_event__process_fork;
+ psession->tool.ksymbol = perf_event__process_ksymbol;
+ psession->tool.text_poke = perf_event__process_text_poke;
+ psession->tool.build_id = perf_event__process_build_id;
+ session = perf_session__new(&pdata->data, &psession->tool);
+ if (IS_ERR(session)) {
+ PyErr_Format(PyExc_IOError, "failed to create session: %ld", PTR_ERR(session));
+ goto err_out;
+ }
+ psession->session = session;
+
+ if (symbol__init(perf_session__env(session)) < 0) {
+ PyErr_SetString(PyExc_OSError, "perf: symbol__init failed");
+ goto err_out;
+ }
+
+ if (perf_session__create_kernel_maps(session) < 0)
+ pr_warning("Cannot read kernel map\n");
+
+ return (PyObject *)psession;
+err_out:
+ Py_DECREF(psession);
+ return NULL;
+}
+
+static void pyrf_session__delete(struct pyrf_session *psession)
+{
+ perf_session__delete(psession->session);
+ Py_XDECREF(psession->pdata);
+ Py_XDECREF(psession->sample);
+ Py_TYPE(psession)->tp_free((PyObject *)psession);
+}
+
+static PyObject *pyrf_session__find_thread_events(struct pyrf_session *psession)
+{
+ int err = perf_session__process_events(psession->session);
+
+ if (PyErr_Occurred())
+ return NULL;
+
+ return PyLong_FromLong(err);
+}
+
+static PyMethodDef pyrf_session__methods[] = {
+ {
+ .ml_name = "process_events",
+ .ml_meth = (PyCFunction)pyrf_session__find_thread_events,
+ .ml_flags = METH_NOARGS,
+ .ml_doc = PyDoc_STR("Iterate and process events.")
+ },
+ {
+ .ml_name = "find_thread",
+ .ml_meth = (PyCFunction)pyrf_session__find_thread,
+ .ml_flags = METH_VARARGS,
+ .ml_doc = PyDoc_STR("Returns the thread associated with a pid.")
+ },
+ { .ml_name = NULL, }
+};
+
+static const char pyrf_session__doc[] = PyDoc_STR("perf session object.");
+
+static PyTypeObject pyrf_session__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.session",
+ .tp_basicsize = sizeof(struct pyrf_session),
+ .tp_dealloc = (destructor)pyrf_session__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_methods = pyrf_session__methods,
+ .tp_doc = pyrf_session__doc,
+ .tp_new = pyrf_session__new,
+};
+
+static int pyrf_session__setup_types(void)
+{
+ return PyType_Ready(&pyrf_session__type);
+}
+
static PyMethodDef perf__methods[] = {
{
.ml_name = "metrics",
@@ -2467,8 +2754,10 @@ PyMODINIT_FUNC PyInit_perf(void)
};
PyObject *module = PyModule_Create(&moduledef);
- if (module == NULL ||
- pyrf_event__setup_types() < 0 ||
+ if (module == NULL)
+ return NULL;
+
+ if (pyrf_event__setup_types() < 0 ||
pyrf_evlist__setup_types() < 0 ||
pyrf_evsel__setup_types() < 0 ||
pyrf_thread_map__setup_types() < 0 ||
@@ -2476,8 +2765,12 @@ PyMODINIT_FUNC PyInit_perf(void)
pyrf_pmu_iterator__setup_types() < 0 ||
pyrf_pmu__setup_types() < 0 ||
pyrf_counts_values__setup_types() < 0 ||
- pyrf_data__setup_types() < 0)
- return module;
+ pyrf_data__setup_types() < 0 ||
+ pyrf_session__setup_types() < 0 ||
+ pyrf_thread__setup_types() < 0) {
+ Py_DECREF(module);
+ return NULL;
+ }
/* The page_size is placed in util object. */
page_size = sysconf(_SC_PAGE_SIZE);
@@ -2527,6 +2820,9 @@ PyMODINIT_FUNC PyInit_perf(void)
Py_INCREF(&pyrf_data__type);
PyModule_AddObject(module, "data", (PyObject *)&pyrf_data__type);
+ Py_INCREF(&pyrf_session__type);
+ PyModule_AddObject(module, "session", (PyObject *)&pyrf_session__type);
+
dict = PyModule_GetDict(module);
if (dict == NULL)
goto error;
@@ -2540,7 +2836,9 @@ PyMODINIT_FUNC PyInit_perf(void)
}
error:
- if (PyErr_Occurred())
- PyErr_SetString(PyExc_ImportError, "perf: Init failed!");
+ if (PyErr_Occurred()) {
+ Py_XDECREF(module);
+ return NULL;
+ }
return module;
}
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 16/58] perf python: Add mmap2 event
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
If mmap is handled so should mmap2 events. Add support as a distinct
python event type.
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/python.c | 60 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 60 insertions(+)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 1ca296000351..ae009bc9a0d7 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -151,6 +151,54 @@ static PyTypeObject pyrf_mmap_event__type = {
.tp_repr = (reprfunc)pyrf_mmap_event__repr,
};
+static const char pyrf_mmap2_event__doc[] = PyDoc_STR("perf mmap2 event object.");
+
+static PyMemberDef pyrf_mmap2_event__members[] = {
+ sample_members
+ member_def(perf_event_header, type, T_UINT, "event type"),
+ member_def(perf_event_header, misc, T_UINT, "event misc"),
+ member_def(perf_record_mmap2, pid, T_UINT, "event pid"),
+ member_def(perf_record_mmap2, tid, T_UINT, "event tid"),
+ member_def(perf_record_mmap2, start, T_ULONGLONG, "start of the map"),
+ member_def(perf_record_mmap2, len, T_ULONGLONG, "map length"),
+ member_def(perf_record_mmap2, pgoff, T_ULONGLONG, "page offset"),
+ member_def(perf_record_mmap2, prot, T_UINT, "protection"),
+ member_def(perf_record_mmap2, flags, T_UINT, "flags"),
+ member_def(perf_record_mmap2, filename, T_STRING_INPLACE, "backing store"),
+ { .name = NULL, },
+};
+
+static PyObject *pyrf_mmap2_event__repr(const struct pyrf_event *pevent)
+{
+ PyObject *ret;
+ char *s;
+
+ if (asprintf(&s, "{ type: mmap2, pid: %u, tid: %u, start: %#" PRI_lx64 ", "
+ "length: %#" PRI_lx64 ", offset: %#" PRI_lx64 ", "
+ "flags: %#x, prot: %#x, filename: %s }",
+ pevent->event.mmap2.pid, pevent->event.mmap2.tid,
+ pevent->event.mmap2.start, pevent->event.mmap2.len,
+ pevent->event.mmap2.pgoff, pevent->event.mmap2.flags,
+ pevent->event.mmap2.prot, pevent->event.mmap2.filename) < 0)
+ return PyErr_NoMemory();
+
+ ret = PyUnicode_FromString(s);
+ free(s);
+ return ret;
+}
+
+static PyTypeObject pyrf_mmap2_event__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.mmap2_event",
+ .tp_basicsize = sizeof(struct pyrf_event),
+ .tp_dealloc = (destructor)pyrf_event__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_mmap2_event__doc,
+ .tp_members = pyrf_mmap2_event__members,
+ .tp_getset = pyrf_event__getset,
+ .tp_repr = (reprfunc)pyrf_mmap2_event__repr,
+};
+
static const char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object.");
static PyMemberDef pyrf_task_event__members[] = {
@@ -776,6 +824,9 @@ static int pyrf_event__setup_types(void)
int err;
err = PyType_Ready(&pyrf_mmap_event__type);
+ if (err < 0)
+ goto out;
+ err = PyType_Ready(&pyrf_mmap2_event__type);
if (err < 0)
goto out;
err = PyType_Ready(&pyrf_lost_event__type);
@@ -805,6 +856,7 @@ static int pyrf_event__setup_types(void)
static PyTypeObject *pyrf_event__type[] = {
[PERF_RECORD_MMAP] = &pyrf_mmap_event__type,
+ [PERF_RECORD_MMAP2] = &pyrf_mmap2_event__type,
[PERF_RECORD_LOST] = &pyrf_lost_event__type,
[PERF_RECORD_COMM] = &pyrf_comm_event__type,
[PERF_RECORD_EXIT] = &pyrf_task_event__type,
@@ -971,6 +1023,11 @@ static PyObject *pyrf_event__new(const union perf_event *event, struct evsel *ev
size_t max_len = pevent->event.header.size - offsetof(struct perf_record_mmap, filename);
pevent->event.mmap.filename[max_len - 1] = '\0';
+ } else if (event->header.type == PERF_RECORD_MMAP2) {
+ /* Ensure '\0' string termination. */
+ size_t max_len = pevent->event.header.size - offsetof(struct perf_record_mmap2, filename);
+
+ pevent->event.mmap2.filename[max_len - 1] = '\0';
}
perf_sample__init(&pevent->sample, /*all=*/true);
@@ -3234,6 +3291,9 @@ PyMODINIT_FUNC PyInit_perf(void)
Py_INCREF(&pyrf_mmap_event__type);
PyModule_AddObject(module, "mmap_event", (PyObject *)&pyrf_mmap_event__type);
+ Py_INCREF(&pyrf_mmap2_event__type);
+ PyModule_AddObject(module, "mmap2_event", (PyObject *)&pyrf_mmap2_event__type);
+
Py_INCREF(&pyrf_lost_event__type);
PyModule_AddObject(module, "lost_event", (PyObject *)&pyrf_lost_event__type);
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 13/58] perf python: Add wrapper for perf_data file abstraction
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
The perf_data struct is needed for session supported.
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
v2:
1. Fixed Memory & FD Leaks in pyrf_data__init : Added cleanup of old
state (closing file and freeing path) if __init__ is called
multiple times on the same object.
2. Fixed Invalid Free in pyrf_data__delete : Ensured pdata->data.path
is always dynamically allocated via strdup() , even for the default
"perf.data" . This avoids passing a static string literal to free().
3. Fixed NULL Pointer Dereference in pyrf_data__str : Added a check
for NULL path to prevent segfaults if str() or repr() is called on
an uninitialized object.
4. Guarded fd Argument Usage: Added a check to ensure that if an fd is
provided, it corresponds to a pipe, failing gracefully with a
ValueError otherwise.
v7:
- Added pyrf_data__new to zero-initialize pdata->data to fix
crash on re-initialization.
---
tools/perf/util/python.c | 103 ++++++++++++++++++++++++++++++++++++++-
1 file changed, 102 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 61a7ee1f4c2f..c002181d96f4 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -10,6 +10,7 @@
#include "callchain.h"
#include "counts.h"
+#include "data.h"
#include "event.h"
#include "evlist.h"
#include "evsel.h"
@@ -2316,6 +2317,102 @@ static PyObject *pyrf__metrics(PyObject *self, PyObject *args)
return list;
}
+struct pyrf_data {
+ PyObject_HEAD
+
+ struct perf_data data;
+};
+
+static int pyrf_data__init(struct pyrf_data *pdata, PyObject *args, PyObject *kwargs)
+{
+ static char *kwlist[] = { "path", "fd", NULL };
+ char *path = NULL;
+ int fd = -1;
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|si", kwlist, &path, &fd))
+ return -1;
+
+ if (pdata->data.open)
+ perf_data__close(&pdata->data);
+ free((char *)pdata->data.path);
+
+ if (!path)
+ path = "perf.data";
+
+ pdata->data.path = strdup(path);
+ if (!pdata->data.path) {
+ PyErr_NoMemory();
+ return -1;
+ }
+
+ if (fd != -1) {
+ struct stat st;
+
+ if (fstat(fd, &st) < 0 || !S_ISFIFO(st.st_mode)) {
+ PyErr_SetString(PyExc_ValueError,
+ "fd argument is only supported for pipes");
+ free((char *)pdata->data.path);
+ pdata->data.path = NULL;
+ return -1;
+ }
+ }
+
+ pdata->data.mode = PERF_DATA_MODE_READ;
+ pdata->data.file.fd = fd;
+ if (perf_data__open(&pdata->data) < 0) {
+ PyErr_Format(PyExc_IOError, "Failed to open perf data: %s",
+ pdata->data.path ? pdata->data.path : "perf.data");
+ return -1;
+ }
+ return 0;
+}
+
+static void pyrf_data__delete(struct pyrf_data *pdata)
+{
+ perf_data__close(&pdata->data);
+ free((char *)pdata->data.path);
+ Py_TYPE(pdata)->tp_free((PyObject *)pdata);
+}
+
+static PyObject *pyrf_data__str(PyObject *self)
+{
+ const struct pyrf_data *pdata = (const struct pyrf_data *)self;
+
+ if (!pdata->data.path)
+ return PyUnicode_FromString("[uninitialized]");
+ return PyUnicode_FromString(pdata->data.path);
+}
+
+static PyObject *pyrf_data__new(PyTypeObject *type, PyObject *args, PyObject *kwargs)
+{
+ struct pyrf_data *pdata;
+
+ pdata = (struct pyrf_data *)PyType_GenericNew(type, args, kwargs);
+ if (pdata)
+ memset(&pdata->data, 0, sizeof(pdata->data));
+ return (PyObject *)pdata;
+}
+
+static const char pyrf_data__doc[] = PyDoc_STR("perf data file object.");
+
+static PyTypeObject pyrf_data__type = {
+ PyVarObject_HEAD_INIT(NULL, 0)
+ .tp_name = "perf.data",
+ .tp_basicsize = sizeof(struct pyrf_data),
+ .tp_dealloc = (destructor)pyrf_data__delete,
+ .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+ .tp_doc = pyrf_data__doc,
+ .tp_init = (initproc)pyrf_data__init,
+ .tp_repr = pyrf_data__str,
+ .tp_str = pyrf_data__str,
+};
+
+static int pyrf_data__setup_types(void)
+{
+ pyrf_data__type.tp_new = pyrf_data__new;
+ return PyType_Ready(&pyrf_data__type);
+}
+
static PyMethodDef perf__methods[] = {
{
.ml_name = "metrics",
@@ -2378,7 +2475,8 @@ PyMODINIT_FUNC PyInit_perf(void)
pyrf_cpu_map__setup_types() < 0 ||
pyrf_pmu_iterator__setup_types() < 0 ||
pyrf_pmu__setup_types() < 0 ||
- pyrf_counts_values__setup_types() < 0)
+ pyrf_counts_values__setup_types() < 0 ||
+ pyrf_data__setup_types() < 0)
return module;
/* The page_size is placed in util object. */
@@ -2426,6 +2524,9 @@ PyMODINIT_FUNC PyInit_perf(void)
Py_INCREF(&pyrf_counts_values__type);
PyModule_AddObject(module, "counts_values", (PyObject *)&pyrf_counts_values__type);
+ Py_INCREF(&pyrf_data__type);
+ PyModule_AddObject(module, "data", (PyObject *)&pyrf_data__type);
+
dict = PyModule_GetDict(module);
if (dict == NULL)
goto error;
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 12/58] perf python: Use evsel in sample in pyrf_event
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Avoid a duplicated evsel by using the one in sample. Add
evsel__get/put to the evsel in perf_sample.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/evsel.c | 2 +-
tools/perf/util/python.c | 10 +++-------
tools/perf/util/sample.c | 17 ++++++++++++-----
3 files changed, 16 insertions(+), 13 deletions(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3015b9b4b4da..9b16d832810f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3235,7 +3235,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
union u64_swap u;
perf_sample__init(data, /*all=*/true);
- data->evsel = evsel;
+ data->evsel = evsel__get(evsel);
data->cpu = data->pid = data->tid = -1;
data->stream_id = data->id = data->time = -1ULL;
data->period = evsel->core.attr.sample_period;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 4b8d6349b7b1..61a7ee1f4c2f 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -43,7 +43,6 @@ PyMODINIT_FUNC PyInit_perf(void);
struct pyrf_event {
PyObject_HEAD
- struct evsel *evsel;
struct perf_sample sample;
union perf_event event;
};
@@ -274,7 +273,6 @@ static PyMemberDef pyrf_sample_event__members[] = {
static void pyrf_sample_event__delete(struct pyrf_event *pevent)
{
- evsel__put(pevent->evsel);
perf_sample__exit(&pevent->sample);
Py_TYPE(pevent)->tp_free((PyObject*)pevent);
}
@@ -296,7 +294,7 @@ static PyObject *pyrf_sample_event__repr(const struct pyrf_event *pevent)
#ifdef HAVE_LIBTRACEEVENT
static bool is_tracepoint(const struct pyrf_event *pevent)
{
- return pevent->evsel->core.attr.type == PERF_TYPE_TRACEPOINT;
+ return pevent->sample.evsel->core.attr.type == PERF_TYPE_TRACEPOINT;
}
static PyObject*
@@ -343,7 +341,7 @@ tracepoint_field(const struct pyrf_event *pe, struct tep_format_field *field)
static PyObject*
get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
{
- struct evsel *evsel = pevent->evsel;
+ struct evsel *evsel = pevent->sample.evsel;
struct tep_event *tp_format = evsel__tp_format(evsel);
struct tep_format_field *field;
@@ -509,7 +507,7 @@ static PyObject *pyrf_event__new(const union perf_event *event)
pevent = PyObject_New(struct pyrf_event, ptype);
if (pevent != NULL) {
memcpy(&pevent->event, event, event->header.size);
- pevent->evsel = NULL;
+ perf_sample__init(&pevent->sample, /*all=*/false);
}
return (PyObject *)pevent;
}
@@ -1798,8 +1796,6 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
return Py_None;
}
- pevent->evsel = evsel__get(evsel);
-
perf_mmap__consume(&md->core);
err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample);
diff --git a/tools/perf/util/sample.c b/tools/perf/util/sample.c
index cf73329326d7..7ec534dedc5c 100644
--- a/tools/perf/util/sample.c
+++ b/tools/perf/util/sample.c
@@ -1,18 +1,23 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include "sample.h"
+
+#include <stdlib.h>
+#include <string.h>
+
+#include <elf.h>
+#include <linux/zalloc.h>
+
#include "debug.h"
+#include "evsel.h"
#include "thread.h"
-#include <elf.h>
+#include "../../arch/x86/include/asm/insn.h"
+
#ifndef EM_CSKY
#define EM_CSKY 252
#endif
#ifndef EM_LOONGARCH
#define EM_LOONGARCH 258
#endif
-#include <linux/zalloc.h>
-#include <stdlib.h>
-#include <string.h>
-#include "../../arch/x86/include/asm/insn.h"
void perf_sample__init(struct perf_sample *sample, bool all)
{
@@ -29,6 +34,8 @@ void perf_sample__init(struct perf_sample *sample, bool all)
void perf_sample__exit(struct perf_sample *sample)
{
+ evsel__put(sample->evsel);
+ sample->evsel = NULL;
zfree(&sample->user_regs);
zfree(&sample->intr_regs);
if (sample->merged_callchain) {
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 08/58] perf data: Add open flag
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Avoid double opens and ensure only open files are closed. This
addresses some issues with python integration where the data file
wants to be opened before being given to a session.
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
Changes in v2:
1. Fixed File Rotation: In perf_data__switch() , I added data->open =
false; after the file is closed. This ensures that the subsequent
perf_data__open() call will not exit early and will successfully
open the new file.
2. Fixed Memory Leak: In open_dir() , I added a call to
zfree(&data->file.path) if mkdir() fails, preventing the leak of
the path string.
---
tools/perf/util/data.c | 26 ++++++++++++++++++++++----
tools/perf/util/data.h | 4 +++-
2 files changed, 25 insertions(+), 5 deletions(-)
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 94dc534a7386..17baf71897d1 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -346,8 +346,10 @@ static int open_dir(struct perf_data *data)
return -1;
if (perf_data__is_write(data) &&
- mkdir(data->path, S_IRWXU) < 0)
+ mkdir(data->path, S_IRWXU) < 0) {
+ zfree(&data->file.path);
return -1;
+ }
ret = open_file(data);
@@ -360,9 +362,16 @@ static int open_dir(struct perf_data *data)
int perf_data__open(struct perf_data *data)
{
- if (check_pipe(data))
+ int ret;
+
+ if (data->open)
return 0;
+ if (check_pipe(data)) {
+ data->open = true;
+ return 0;
+ }
+
/* currently it allows stdio for pipe only */
data->file.use_stdio = false;
@@ -375,16 +384,24 @@ int perf_data__open(struct perf_data *data)
if (perf_data__is_read(data))
data->is_dir = is_dir(data);
- return perf_data__is_dir(data) ?
- open_dir(data) : open_file_dup(data);
+ ret = perf_data__is_dir(data) ? open_dir(data) : open_file_dup(data);
+
+ if (!ret)
+ data->open = true;
+
+ return ret;
}
void perf_data__close(struct perf_data *data)
{
+ if (!data->open)
+ return;
+
if (perf_data__is_dir(data))
perf_data__close_dir(data);
perf_data_file__close(&data->file);
+ data->open = false;
}
static ssize_t perf_data_file__read(struct perf_data_file *file, void *buf, size_t size)
@@ -457,6 +474,7 @@ int perf_data__switch(struct perf_data *data,
if (!at_exit) {
perf_data_file__close(&data->file);
+ data->open = false;
ret = perf_data__open(data);
if (ret < 0)
goto out;
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 8299fb5fa7da..76f57f60361f 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -50,6 +50,8 @@ struct perf_data {
const char *path;
/** @file: Underlying file to be used. */
struct perf_data_file file;
+ /** @open: Has the file or directory been opened. */
+ bool open;
/** @is_pipe: Underlying file is a pipe. */
bool is_pipe;
/** @is_dir: Underlying file is a directory. */
@@ -59,7 +61,7 @@ struct perf_data {
/** @in_place_update: A file opened for reading but will be written to. */
bool in_place_update;
/** @mode: Read or write mode. */
- enum perf_data_mode mode;
+ enum perf_data_mode mode:8;
struct {
/** @version: perf_dir_version. */
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 07/58] perf evsel/evlist: Avoid unnecessary #includes
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Use forward declarations and remove unnecessary #includes in
evsel.h. Sort the forward declarations in evsel.h and evlist.h.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/evlist.h | 15 +++++++++------
tools/perf/util/evsel.h | 20 +++++++++++---------
2 files changed, 20 insertions(+), 15 deletions(-)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index e507f5f20ef6..e54761c670b6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -2,29 +2,32 @@
#ifndef __PERF_EVLIST_H
#define __PERF_EVLIST_H 1
+#include <signal.h>
+
#include <linux/compiler.h>
#include <linux/kernel.h>
-#include <linux/refcount.h>
#include <linux/list.h>
+#include <linux/refcount.h>
+#include <pthread.h>
+#include <unistd.h>
+
#include <api/fd/array.h>
#include <internal/evlist.h>
#include <internal/evsel.h>
#include <perf/evlist.h>
+
#include "affinity.h"
#include "events_stats.h"
#include "evsel.h"
#include "rblist.h"
-#include <pthread.h>
-#include <signal.h>
-#include <unistd.h>
-struct pollfd;
-struct thread_map;
struct perf_cpu_map;
struct perf_stat_config;
+struct pollfd;
struct record_opts;
struct strbuf;
struct target;
+struct thread_map;
/*
* State machine of bkw_mmap_state:
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 339b5c08a33d..b099c8e5dd86 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -2,28 +2,30 @@
#ifndef __PERF_EVSEL_H
#define __PERF_EVSEL_H 1
-#include <linux/list.h>
#include <stdbool.h>
-#include <sys/types.h>
+
+#include <linux/list.h>
#include <linux/perf_event.h>
#include <linux/types.h>
+#include <sys/types.h>
+
#include <internal/evsel.h>
#include <perf/evsel.h>
+
#include "symbol_conf.h"
-#include "pmus.h"
-#include "pmu.h"
+struct bperf_follower_bpf;
+struct bperf_leader_bpf;
+struct bpf_counter_ops;
struct bpf_object;
struct cgroup;
+struct hashmap;
struct perf_counts;
+struct perf_pmu;
struct perf_stat_config;
struct perf_stat_evsel;
-union perf_event;
-struct bpf_counter_ops;
struct target;
-struct hashmap;
-struct bperf_leader_bpf;
-struct bperf_follower_bpf;
+union perf_event;
typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 06/58] perf python: Add missed explicit dependencies
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Fix missing #include of pmus.h found while cleaning the evsel/evlist
header files.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/python.c | 17 ++++++++++-------
1 file changed, 10 insertions(+), 7 deletions(-)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index cc1019d29a5d..1e6c99efff90 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -5,26 +5,29 @@
#include <poll.h>
#include <linux/err.h>
#include <perf/cpumap.h>
-#ifdef HAVE_LIBTRACEEVENT
-#include <event-parse.h>
-#endif
+#include <internal/lib.h>
#include <perf/mmap.h>
+
#include "callchain.h"
#include "counts.h"
+#include "event.h"
#include "evlist.h"
#include "evsel.h"
-#include "event.h"
#include "expr.h"
+#include "metricgroup.h"
+#include "mmap.h"
+#include "pmus.h"
#include "print_binary.h"
#include "record.h"
#include "strbuf.h"
#include "thread_map.h"
#include "tp_pmu.h"
#include "trace-event.h"
-#include "metricgroup.h"
-#include "mmap.h"
#include "util/sample.h"
-#include <internal/lib.h>
+
+#ifdef HAVE_LIBTRACEEVENT
+#include <event-parse.h>
+#endif
PyMODINIT_FUNC PyInit_perf(void);
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 05/58] perf util: Sort includes and add missed explicit dependencies
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Fix missing includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/bpf_off_cpu.c | 30 +++++-----
tools/perf/util/bpf_trace_augment.c | 8 +--
tools/perf/util/evlist.c | 91 +++++++++++++++--------------
tools/perf/util/evsel.c | 75 ++++++++++++------------
tools/perf/util/map.h | 9 ++-
tools/perf/util/perf_api_probe.c | 18 +++---
tools/perf/util/s390-sample-raw.c | 19 +++---
tools/perf/util/stat-shadow.c | 20 ++++---
tools/perf/util/stat.c | 16 +++--
9 files changed, 152 insertions(+), 134 deletions(-)
diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index a3b699a5322f..48cb930cdd2e 100644
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -1,23 +1,25 @@
// SPDX-License-Identifier: GPL-2.0
-#include "util/bpf_counter.h"
-#include "util/debug.h"
-#include "util/evsel.h"
-#include "util/evlist.h"
-#include "util/off_cpu.h"
-#include "util/perf-hooks.h"
-#include "util/record.h"
-#include "util/session.h"
-#include "util/target.h"
-#include "util/cpumap.h"
-#include "util/thread_map.h"
-#include "util/cgroup.h"
-#include "util/strlist.h"
+#include <linux/time64.h>
+
#include <bpf/bpf.h>
#include <bpf/btf.h>
#include <internal/xyarray.h>
-#include <linux/time64.h>
+#include "bpf_counter.h"
#include "bpf_skel/off_cpu.skel.h"
+#include "cgroup.h"
+#include "cpumap.h"
+#include "debug.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "off_cpu.h"
+#include "parse-events.h"
+#include "perf-hooks.h"
+#include "record.h"
+#include "session.h"
+#include "strlist.h"
+#include "target.h"
+#include "thread_map.h"
#define MAX_STACKS 32
#define MAX_PROC 4096
diff --git a/tools/perf/util/bpf_trace_augment.c b/tools/perf/util/bpf_trace_augment.c
index 9e706f0fa53d..a9cf2a77ded1 100644
--- a/tools/perf/util/bpf_trace_augment.c
+++ b/tools/perf/util/bpf_trace_augment.c
@@ -1,11 +1,11 @@
#include <bpf/libbpf.h>
#include <internal/xyarray.h>
-#include "util/debug.h"
-#include "util/evlist.h"
-#include "util/trace_augment.h"
-
#include "bpf_skel/augmented_raw_syscalls.skel.h"
+#include "debug.h"
+#include "evlist.h"
+#include "parse-events.h"
+#include "trace_augment.h"
static struct augmented_raw_syscalls_bpf *skel;
static struct evsel *bpf_output;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ee971d15b3c6..35d65fe50e06 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -5,67 +5,68 @@
* Parts came from builtin-{top,stat,record}.c, see those files for further
* copyright notes.
*/
-#include <api/fs/fs.h>
+#include "evlist.h"
+
#include <errno.h>
#include <inttypes.h>
-#include <poll.h>
-#include "cpumap.h"
-#include "util/mmap.h"
-#include "thread_map.h"
-#include "target.h"
-#include "dwarf-regs.h"
-#include "evlist.h"
-#include "evsel.h"
-#include "record.h"
-#include "debug.h"
-#include "units.h"
-#include "bpf_counter.h"
-#include <internal/lib.h> // page_size
-#include "affinity.h"
-#include "../perf.h"
-#include "asm/bug.h"
-#include "bpf-event.h"
-#include "util/event.h"
-#include "util/string2.h"
-#include "util/perf_api_probe.h"
-#include "util/evsel_fprintf.h"
-#include "util/pmu.h"
-#include "util/sample.h"
-#include "util/bpf-filter.h"
-#include "util/stat.h"
-#include "util/util.h"
-#include "util/env.h"
-#include "util/intel-tpebs.h"
-#include "util/metricgroup.h"
-#include "util/strbuf.h"
#include <signal.h>
-#include <unistd.h>
-#include <sched.h>
#include <stdlib.h>
-#include "parse-events.h"
-#include <subcmd/parse-options.h>
-
#include <fcntl.h>
-#include <sys/ioctl.h>
-#include <sys/mman.h>
-#include <sys/prctl.h>
-#include <sys/timerfd.h>
-#include <sys/wait.h>
-
#include <linux/bitops.h>
+#include <linux/err.h>
#include <linux/hash.h>
#include <linux/log2.h>
-#include <linux/err.h>
#include <linux/string.h>
#include <linux/time64.h>
#include <linux/zalloc.h>
+#include <poll.h>
+#include <sched.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/timerfd.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include <api/fs/fs.h>
+#include <internal/lib.h> // page_size
+#include <internal/xyarray.h>
+#include <perf/cpumap.h>
#include <perf/evlist.h>
#include <perf/evsel.h>
-#include <perf/cpumap.h>
#include <perf/mmap.h>
+#include <subcmd/parse-options.h>
-#include <internal/xyarray.h>
+#include "../perf.h"
+#include "affinity.h"
+#include "asm/bug.h"
+#include "bpf-event.h"
+#include "bpf-filter.h"
+#include "bpf_counter.h"
+#include "cpumap.h"
+#include "debug.h"
+#include "dwarf-regs.h"
+#include "env.h"
+#include "event.h"
+#include "evsel.h"
+#include "evsel_fprintf.h"
+#include "intel-tpebs.h"
+#include "metricgroup.h"
+#include "mmap.h"
+#include "parse-events.h"
+#include "perf_api_probe.h"
+#include "pmu.h"
+#include "pmus.h"
+#include "record.h"
+#include "sample.h"
+#include "stat.h"
+#include "strbuf.h"
+#include "string2.h"
+#include "target.h"
+#include "thread_map.h"
+#include "units.h"
+#include "util.h"
#ifdef LACKS_SIGQUEUE_PROTOTYPE
int sigqueue(pid_t pid, int sig, const union sigval value);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2ee87fd84d3e..e03727d395e9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -11,68 +11,71 @@
*/
#define __SANE_USERSPACE_TYPES__
-#include <byteswap.h>
+#include "evsel.h"
+
#include <errno.h>
#include <inttypes.h>
+#include <stdlib.h>
+
+#include <dirent.h>
#include <linux/bitops.h>
-#include <api/fs/fs.h>
-#include <api/fs/tracing_path.h>
-#include <linux/hw_breakpoint.h>
-#include <linux/perf_event.h>
#include <linux/compiler.h>
+#include <linux/ctype.h>
#include <linux/err.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/perf_event.h>
#include <linux/zalloc.h>
#include <sys/ioctl.h>
#include <sys/resource.h>
#include <sys/syscall.h>
#include <sys/types.h>
-#include <dirent.h>
-#include <stdlib.h>
+
+#include <api/fs/fs.h>
+#include <api/fs/tracing_path.h>
+#include <byteswap.h>
+#include <internal/lib.h>
+#include <internal/threadmap.h>
+#include <internal/xyarray.h>
+#include <perf/cpumap.h>
#include <perf/evsel.h>
+
+#include "../perf-sys.h"
#include "asm/bug.h"
+#include "bpf-filter.h"
#include "bpf_counter.h"
#include "callchain.h"
#include "cgroup.h"
#include "counts.h"
+#include "debug.h"
+#include "drm_pmu.h"
#include "dwarf-regs.h"
+#include "env.h"
#include "event.h"
-#include "evsel.h"
-#include "time-utils.h"
-#include "util/env.h"
-#include "util/evsel_config.h"
-#include "util/evsel_fprintf.h"
#include "evlist.h"
-#include <perf/cpumap.h>
-#include "thread_map.h"
-#include "target.h"
+#include "evsel_config.h"
+#include "evsel_fprintf.h"
+#include "hashmap.h"
+#include "hist.h"
+#include "hwmon_pmu.h"
+#include "intel-tpebs.h"
+#include "memswap.h"
+#include "off_cpu.h"
+#include "parse-branch-options.h"
#include "perf_regs.h"
+#include "pmu.h"
+#include "pmus.h"
#include "record.h"
-#include "debug.h"
-#include "trace-event.h"
+#include "rlimit.h"
#include "session.h"
#include "stat.h"
#include "string2.h"
-#include "memswap.h"
-#include "util.h"
-#include "util/hashmap.h"
-#include "off_cpu.h"
-#include "pmu.h"
-#include "pmus.h"
-#include "drm_pmu.h"
-#include "hwmon_pmu.h"
+#include "target.h"
+#include "thread_map.h"
+#include "time-utils.h"
#include "tool_pmu.h"
#include "tp_pmu.h"
-#include "rlimit.h"
-#include "../perf-sys.h"
-#include "util/parse-branch-options.h"
-#include "util/bpf-filter.h"
-#include "util/hist.h"
-#include <internal/xyarray.h>
-#include <internal/lib.h>
-#include <internal/threadmap.h>
-#include "util/intel-tpebs.h"
-
-#include <linux/ctype.h>
+#include "trace-event.h"
+#include "util.h"
#ifdef HAVE_LIBTRACEEVENT
#include <event-parse.h>
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 979b3e11b9bc..fb0279810ae9 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -2,14 +2,13 @@
#ifndef __PERF_MAP_H
#define __PERF_MAP_H
-#include <linux/refcount.h>
-#include <linux/compiler.h>
-#include <linux/list.h>
-#include <linux/rbtree.h>
+#include <stdbool.h>
#include <stdio.h>
#include <string.h>
-#include <stdbool.h>
+
+#include <linux/refcount.h>
#include <linux/types.h>
+
#include <internal/rc_check.h>
struct dso;
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
index 6ecf38314f01..e1904a330b28 100644
--- a/tools/perf/util/perf_api_probe.c
+++ b/tools/perf/util/perf_api_probe.c
@@ -1,14 +1,18 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#include "perf_api_probe.h"
-#include "perf-sys.h"
-#include "util/cloexec.h"
-#include "util/evlist.h"
-#include "util/evsel.h"
-#include "util/parse-events.h"
-#include "util/perf_api_probe.h"
-#include <perf/cpumap.h>
#include <errno.h>
+#include <perf/cpumap.h>
+
+#include "cloexec.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "parse-events.h"
+#include "perf-sys.h"
+#include "pmu.h"
+#include "pmus.h"
+
typedef void (*setup_probe_fn_t)(struct evsel *evsel);
static int perf_do_probe_api(setup_probe_fn_t fn, struct perf_cpu cpu, const char *str)
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index c6ae0ae8d86a..6bf0edf80d4e 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -12,25 +12,26 @@
* sample was taken from.
*/
-#include <unistd.h>
+#include <inttypes.h>
#include <stdio.h>
#include <string.h>
-#include <inttypes.h>
-#include <sys/stat.h>
+#include <asm/byteorder.h>
#include <linux/compiler.h>
#include <linux/err.h>
-#include <asm/byteorder.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include "color.h"
#include "debug.h"
-#include "session.h"
#include "evlist.h"
-#include "color.h"
#include "hashmap.h"
-#include "sample-raw.h"
+#include "pmu.h"
+#include "pmus.h"
#include "s390-cpumcf-kernel.h"
-#include "util/pmu.h"
-#include "util/sample.h"
+#include "sample-raw.h"
+#include "sample.h"
+#include "session.h"
static size_t ctrset_size(struct cf_ctrset_entry *set)
{
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index bc2d44df7baf..48524450326d 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -2,20 +2,24 @@
#include <errno.h>
#include <math.h>
#include <stdio.h>
-#include "evsel.h"
-#include "stat.h"
+
+#include <linux/zalloc.h>
+
+#include "cgroup.h"
#include "color.h"
#include "debug.h"
-#include "pmu.h"
-#include "rblist.h"
#include "evlist.h"
+#include "evsel.h"
#include "expr.h"
-#include "metricgroup.h"
-#include "cgroup.h"
-#include "units.h"
+#include "hashmap.h"
#include "iostat.h"
-#include "util/hashmap.h"
+#include "metricgroup.h"
+#include "pmu.h"
+#include "pmus.h"
+#include "rblist.h"
+#include "stat.h"
#include "tool_pmu.h"
+#include "units.h"
static bool tool_pmu__is_time_event(const struct perf_stat_config *config,
const struct evsel *evsel, int *tool_aggr_idx)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 14d169e22e8f..66eb9a66a4f7 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,21 +1,25 @@
// SPDX-License-Identifier: GPL-2.0
+#include "stat.h"
+
#include <errno.h>
-#include <linux/err.h>
#include <inttypes.h>
#include <math.h>
#include <string.h>
+
+#include <linux/err.h>
+#include <linux/zalloc.h>
+
#include "counts.h"
#include "cpumap.h"
#include "debug.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "hashmap.h"
#include "header.h"
-#include "stat.h"
+#include "pmu.h"
#include "session.h"
#include "target.h"
-#include "evlist.h"
-#include "evsel.h"
#include "thread_map.h"
-#include "util/hashmap.h"
-#include <linux/zalloc.h>
void update_stats(struct stats *stats, u64 val)
{
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 04/58] perf script: Sort includes and add missed explicit dependencies
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Fix missing #include of pmu.h found while cleaning the evsel/evlist
header files. Sort the remaining header files for consistency with the
rest of the code. Doing this exposed a missing forward declaration of
addr_location in print_insn.h, add this and sort the forward
declarations.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/builtin-script.c | 111 ++++++++++++++++++-----------------
tools/perf/util/print_insn.h | 5 +-
2 files changed, 60 insertions(+), 56 deletions(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c8ac9f01a36b..853b141a0d50 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1,74 +1,77 @@
// SPDX-License-Identifier: GPL-2.0
-#include "builtin.h"
+#include <errno.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <stdio.h>
+
+#include <dirent.h>
+#include <fcntl.h>
+#include <linux/bitmap.h>
+#include <linux/compiler.h>
+#include <linux/ctype.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/stringify.h>
+#include <linux/time64.h>
+#include <linux/unaligned.h>
+#include <linux/zalloc.h>
+#include <sys/param.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/utsname.h>
+#include <unistd.h>
+#include <perf/evlist.h>
+#include <subcmd/exec-cmd.h>
+#include <subcmd/pager.h>
+#include <subcmd/parse-options.h>
+
+#include "asm/bug.h"
+#include "builtin.h"
+#include "perf.h"
+#include "print_binary.h"
+#include "print_insn.h"
+#include "ui/ui.h"
+#include "util/annotate.h"
+#include "util/auxtrace.h"
+#include "util/cgroup.h"
+#include "util/color.h"
#include "util/counts.h"
+#include "util/cpumap.h"
+#include "util/data.h"
#include "util/debug.h"
+#include "util/dlfilter.h"
#include "util/dso.h"
-#include <subcmd/exec-cmd.h>
-#include "util/header.h"
-#include <subcmd/parse-options.h>
-#include "util/perf_regs.h"
-#include "util/session.h"
-#include "util/tool.h"
-#include "util/map.h"
-#include "util/srcline.h"
-#include "util/symbol.h"
-#include "util/thread.h"
-#include "util/trace-event.h"
+#include "util/dump-insn.h"
#include "util/env.h"
+#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/evsel_fprintf.h"
#include "util/evswitch.h"
+#include "util/header.h"
+#include "util/map.h"
+#include "util/mem-events.h"
+#include "util/mem-info.h"
+#include "util/metricgroup.h"
+#include "util/path.h"
+#include "util/perf_regs.h"
+#include "util/pmu.h"
+#include "util/record.h"
+#include "util/session.h"
#include "util/sort.h"
-#include "util/data.h"
-#include "util/auxtrace.h"
-#include "util/cpumap.h"
-#include "util/thread_map.h"
+#include "util/srcline.h"
#include "util/stat.h"
-#include "util/color.h"
#include "util/string2.h"
+#include "util/symbol.h"
#include "util/thread-stack.h"
+#include "util/thread.h"
+#include "util/thread_map.h"
#include "util/time-utils.h"
-#include "util/path.h"
-#include "util/event.h"
-#include "util/mem-info.h"
-#include "util/metricgroup.h"
-#include "ui/ui.h"
-#include "print_binary.h"
-#include "print_insn.h"
-#include <linux/bitmap.h>
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/stringify.h>
-#include <linux/time64.h>
-#include <linux/zalloc.h>
-#include <linux/unaligned.h>
-#include <sys/utsname.h>
-#include "asm/bug.h"
-#include "util/mem-events.h"
-#include "util/dump-insn.h"
-#include <dirent.h>
-#include <errno.h>
-#include <inttypes.h>
-#include <signal.h>
-#include <stdio.h>
-#include <sys/param.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <subcmd/pager.h>
-#include <perf/evlist.h>
-#include <linux/err.h>
-#include "util/dlfilter.h"
-#include "util/record.h"
+#include "util/tool.h"
+#include "util/trace-event.h"
#include "util/util.h"
-#include "util/cgroup.h"
-#include "util/annotate.h"
-#include "perf.h"
-#include <linux/ctype.h>
#ifdef HAVE_LIBTRACEEVENT
#include <event-parse.h>
#endif
diff --git a/tools/perf/util/print_insn.h b/tools/perf/util/print_insn.h
index 07d11af3fc1c..a54f7e858e49 100644
--- a/tools/perf/util/print_insn.h
+++ b/tools/perf/util/print_insn.h
@@ -5,10 +5,11 @@
#include <stddef.h>
#include <stdio.h>
-struct perf_sample;
-struct thread;
+struct addr_location;
struct machine;
struct perf_insn;
+struct perf_sample;
+struct thread;
#define PRINT_INSN_IMM_HEX (1<<0)
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 03/58] perf tests: Sort includes and add missed explicit dependencies
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Fix missing #includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/tests/hwmon_pmu.c | 14 +++++++++-----
tools/perf/tests/mmap-basic.c | 18 +++++++++++-------
2 files changed, 20 insertions(+), 12 deletions(-)
diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index 4aa4aac94f09..ada6e445c4c4 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -1,15 +1,19 @@
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-#include "debug.h"
-#include "evlist.h"
#include "hwmon_pmu.h"
-#include "parse-events.h"
-#include "tests.h"
+
#include <errno.h>
+
#include <fcntl.h>
-#include <sys/stat.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/string.h>
+#include <sys/stat.h>
+
+#include "debug.h"
+#include "evlist.h"
+#include "parse-events.h"
+#include "pmus.h"
+#include "tests.h"
static const struct test_event {
const char *name;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 3313c236104e..8d04f6edb004 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -1,25 +1,29 @@
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
-#include <fcntl.h>
#include <inttypes.h>
#include <stdlib.h>
+
+#include <fcntl.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
#include <perf/cpumap.h>
+#include <perf/evlist.h>
+#include <perf/mmap.h>
#include "cpumap.h"
#include "debug.h"
#include "event.h"
#include "evlist.h"
#include "evsel.h"
-#include "thread_map.h"
+#include "pmu.h"
+#include "pmus.h"
#include "tests.h"
+#include "thread_map.h"
#include "util/affinity.h"
#include "util/mmap.h"
#include "util/sample.h"
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <perf/evlist.h>
-#include <perf/mmap.h>
/*
* This test will generate random numbers of calls to some getpid syscalls,
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 02/58] perf arch x86: Sort includes and add missed explicit dependencies
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Fix missing #includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/arch/x86/util/intel-bts.c | 20 +++++++++++--------
tools/perf/arch/x86/util/intel-pt.c | 29 +++++++++++++++-------------
2 files changed, 28 insertions(+), 21 deletions(-)
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 85c8186300c8..100a23d27998 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -4,26 +4,30 @@
* Copyright (c) 2013-2015, Intel Corporation.
*/
+#include "../../../util/intel-bts.h"
+
#include <errno.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
+
#include <linux/bitops.h>
+#include <linux/kernel.h>
#include <linux/log2.h>
+#include <linux/types.h>
#include <linux/zalloc.h>
+#include <internal/lib.h> // page_size
+
+#include "../../../util/auxtrace.h"
#include "../../../util/cpumap.h"
+#include "../../../util/debug.h"
#include "../../../util/event.h"
-#include "../../../util/evsel.h"
#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
#include "../../../util/mmap.h"
-#include "../../../util/session.h"
+#include "../../../util/pmu.h"
#include "../../../util/pmus.h"
-#include "../../../util/debug.h"
#include "../../../util/record.h"
+#include "../../../util/session.h"
#include "../../../util/tsc.h"
-#include "../../../util/auxtrace.h"
-#include "../../../util/intel-bts.h"
-#include <internal/lib.h> // page_size
#define KiB(x) ((x) * 1024)
#define MiB(x) ((x) * 1024 * 1024)
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index c131a727774f..0307ff15d9fc 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -3,36 +3,39 @@
* intel_pt.c: Intel Processor Trace support
* Copyright (c) 2013-2015, Intel Corporation.
*/
+#include "../../../util/intel-pt.h"
#include <errno.h>
#include <stdbool.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
+
#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
#include <linux/log2.h>
+#include <linux/types.h>
#include <linux/zalloc.h>
-#include <linux/err.h>
-#include "../../../util/session.h"
+#include <api/fs/fs.h>
+#include <internal/lib.h> // page_size
+#include <subcmd/parse-options.h>
+
+#include "../../../util/auxtrace.h"
+#include "../../../util/config.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/debug.h"
#include "../../../util/event.h"
#include "../../../util/evlist.h"
#include "../../../util/evsel.h"
#include "../../../util/evsel_config.h"
-#include "../../../util/config.h"
-#include "../../../util/cpumap.h"
#include "../../../util/mmap.h"
-#include <subcmd/parse-options.h>
#include "../../../util/parse-events.h"
-#include "../../../util/pmus.h"
-#include "../../../util/debug.h"
-#include "../../../util/auxtrace.h"
#include "../../../util/perf_api_probe.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmus.h"
#include "../../../util/record.h"
+#include "../../../util/session.h"
#include "../../../util/target.h"
#include "../../../util/tsc.h"
-#include <internal/lib.h> // page_size
-#include "../../../util/intel-pt.h"
-#include <api/fs/fs.h>
#include "cpuid.h"
#define KiB(x) ((x) * 1024)
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v8 00/58] perf: Reorganize scripting support
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260425224951.174663-1-irogers@google.com>
The perf script command has long supported running Python and Perl scripts by
embedding libpython and libperl. This approach has several drawbacks:
- overhead by creating Python dictionaries for every event (whether used or
not),
- complex build dependencies on specific Python/Perl versions,
- complications with threading due to perf being the interpreter,
- no clear way to run standalone scripts like ilist.py.
This series takes a different approach with some initial implementation posted
as an RFC last October:
https://lore.kernel.org/linux-perf-users/20251029053413.355154-1-irogers@google.com/
with the motivation coming up on the mailing list earlier:
https://lore.kernel.org/lkml/CAP-5=fWDqE8SYfOLZkg_0=4Ayx6E7O+h7uUp4NDeCFkiN4b7-w@mail.gmail.com/
The changes remove the embedded libpython and libperl support from perf
entirely. Instead, they expand the existing perf Python module to provide full
access to perf data files and events, allowing scripts to be run as standalone
Python applications.
To demonstrate the benefits, we ported all existing Python and Perl scripts to
use the new Python session API. The performance improvement is dramatic. For
example, porting mem-phys-addr.py:
Before (using embedded libpython in perf script):
```
$ perf mem record a sleep 1
$ time perf script tools/perf/scripts/python/mem-phys-addr.py
Event: cpu_core/mem-loads-aux/
Memory type count percentage
--------------------------------------- ---------- ----------
0-fff : Reserved 3217 100.0
real 0m3.754s
user 0m0.023s
sys 0m0.018s
```
After (using standalone Python script with perf module):
```
$ PYTHONPATH=/tmp/perf/python time python3 tools/perf/python/mem-phys-addr.py
Event: evsel(cpu_core/mem-loads-aux/)
Memory type count percentage
--------------------------------------- ---------- ----------
0-fff : Reserved 3217 100.0
real 0m0.106s
user 0m0.021s
sys 0m0.020s
```
This is a roughly 35x speedup!
The change is large (11713 insertions, 16153 deletions, net 4440
deletions) due to porting all existing perl and python code to the new
API. Gemini was used to achieve this and to improve the code quality.
---
v8 Changes
----------
- Make schedstat and itrace=L fixes separate patches:
https://lore.kernel.org/lkml/20260428070328.1880314-1-irogers@google.com/
https://lore.kernel.org/lkml/20260428070811.1883202-1-irogers@google.com/
- Fixed Heap Out-Of-Bounds / Uninitialized Memory in `pyrf_event__new`:
Use `/*all=*/true` in `perf_sample__init` to prevent garbage memory in
sample structures.
- Fixed Type Confusion in `pyrf_evlist__add`: Added strict `O!` type
validation to avoid unsafe casts when adding evsels to an evlist.
- Exposed Thread Identifiers: Added `pid`, `tid`, `ppid`, and `cpu`
attributes to the Python `perf.thread` type to allow thread identification.
- Fixed Process Resolution: Wrapped thread resolution in `compaction-times.py`,
`check-perf-trace.py`, and `task-analyzer.py` in `try-except` blocks to
safely handle untracked PIDs instead of raising uncaught `TypeError` crashes.
- Fixed Potential Data Loss in `futex-contention.py`: Updated process
resolution in `handle_start` to fall back to `'unknown'` on lookup errors,
ensuring events are always tracked.
- Synchronized Type Stubs File: Added the `mmap2_event` class and new `evsel`
and `thread` attributes to `perf.pyi`.
v7 Changes
----------
- Fixed heap out-of-bounds in `pyrf_event__new` by adding comprehensive
size checks for all event types.
- Fixed undefined symbol `syscalltbl__id` when building without
libtraceevent by making `syscalltbl.o` unconditional in `Build`.
- Fixed several issues in `python.c`:
- Handled NULL return from `thread__comm_str` in `pyrf_thread__comm`.
- Avoided swallowing exceptions in module initialization.
- Added custom `tp_new` methods for `evlist`, `evsel`, and `data` types
to zero-initialize pointers and avoid crashes on re-initialization.
- Fixed lower priority review comments:
- Avoided permanent iterator exhaustion on `brstack` in
`perf_brstack_max.py` by converting it to a list.
- Removed dead code (unused `self.unhandled` dictionary) in
`failed-syscalls-by-pid.py`.
v6 Changes
----------
- Refactored `pyrf_event__new` to take `evsel` and `session` arguments,
and use dynamic allocation based on the actual event size to improve
memory safety and efficiency.
- Moved callchain and branch stack resolution logic from
`pyrf_session_tool__sample` into `pyrf_event__new`, centralizing
initialization.
- Added an optional keyword-only `elf_machine` argument to `syscall_name`
and `syscall_id` functions to allow specifying non-host architectures,
defaulting to `EM_HOST`.
- Renamed `process` method to `find_thread` in the Python API and C
implementation for better intention-revealing naming.
- Fixed a terminal injection vulnerability in `flamegraph.py` by not
printing unverified downloaded content in the prompt.
- Fixed CWD exposure and symlink attack risks in `gecko.py` by using a
secure temporary directory for the HTTP server.
- Fixed a severe performance issue in `event_analyzing_sample.py` by
removing SQLite autocommit mode and batching commits.
- Fixed `AttributeError` crashes in `rw-by-file.py` and `rw-by-pid.py` by
correctly extracting event names.
- Fixed man page formatting issues in `perf-script-python.txt` by using
indented code blocks.
- Updated `perf.pyi` stubs file to reflect all API changes.
- Verified all commit messages with `checkpatch.pl` and ensured lines are
wrapped appropriately.
- Fixed segmentation faults in `perf sched stats` in diff mode.
v5 Changes
----------
Resending due to partial send of v4 due to a quota limit.
v4 Changes
----------
1. Git Fixup Cleanups
- Squashed the lingering `fixup!` commit remaining from the previous session back
into `perf check-perf-trace: Port check-perf-trace to use python module`.
v3 Changes
----------
1. Memory Safety & Reference Counting Fixes
- Stored transient mmap event data inside the Python object's permanent
`pevent->event` and invoked `evsel__parse_sample()` to safely point
attributes into it, resolving Use-After-Free vulnerabilities.
- Nullified `sample->evsel` after calling `evsel__put()` in
`perf_sample__exit()` to protect against potential refcount double-put
crashes in error paths.
- Reordered operations inside `evlist__remove()` to invoke
`perf_evlist__remove()` before reference release.
- Patched an `evsel` reference leak inside `evlist__deliver_deferred_callchain()`.
2. Sashiko AI Review Cleanups
- Corrected the broken event name equality check in `gecko.py` to search
for a substring match within the parsed event string.
- Fixed a latent `AttributeError` crash in `task-analyzer.py` by properly
assigning the session instance.
- Safeguarded thread reporting in `check-perf-trace.py` by utilizing
`sample_tid` instead of `sample_pid`, and wrapping the session thread
resolution in a try-except block.
3. Omitted Minor Issues
- The minor review comments (such as permanent iterator exhaustion on
`brstack`, or dead-code in `failed-syscalls-by-pid.py`) have been omitted
because they do not affect correctness, lead to crashes, or require
significant architectural rework.
v2 Changes
----------
1. String Match and Event Name Accuracy
- Replaced loose substring event matching across the script suite with exact
matches or specific prefix constraints (syscalls:sys_exit_,
evsel(skb:kfree_skb), etc.).
- Added getattr() safety checks to prevent script failures caused by
unresolved attributes from older kernel traces.
2. OOM and Memory Protections
- Refactored netdev-times.py to compute and process network statistics
chronologically on-the-fly, eliminating an unbounded in-memory list
that caused Out-Of-Memory crashes on large files.
- Implemented threshold limits on intel-pt-events.py to cap memory allocation
during event interleaving.
- Optimized export-to-sqlite.py to periodically commit database transactions
(every 10,000 samples) to reduce temporary SQLite journal sizes.
3. Portability & Environment Independence
- Re-keyed internal tracking dictionaries in scripts like powerpc-hcalls.py to
use thread PIDs instead of CPUs, ensuring correctness when threads migrate.
- Switched net_dropmonitor.py from host-specific /proc/kallsyms parsing to
perf's built-in symbol resolution API.
- Added the --iomem parameter to mem-phys-addr.py to support offline analysis
of data collected on different architectures.
4. Standalone Scripting Improvements
- Patched builtin-script.c to ensure --input parameters are successfully passed
down to standalone execution pipelines via execvp().
- Guarded against string buffer overflows during .py extension path resolving.
5. Code Cleanups
- Removed stale perl subdirectories from being detected by the TUI script
browser.
- Ran the entire script suite through mypy and pylint to achieve strict static
type checking and resolve unreferenced variables.
Ian Rogers (58):
perf arch arm: Sort includes and add missed explicit dependencies
perf arch x86: Sort includes and add missed explicit dependencies
perf tests: Sort includes and add missed explicit dependencies
perf script: Sort includes and add missed explicit dependencies
perf util: Sort includes and add missed explicit dependencies
perf python: Add missed explicit dependencies
perf evsel/evlist: Avoid unnecessary #includes
perf data: Add open flag
perf evlist: Add reference count
perf evsel: Add reference count
perf evlist: Add reference count checking
perf python: Use evsel in sample in pyrf_event
perf python: Add wrapper for perf_data file abstraction
perf python: Add python session abstraction wrapping perf's session
perf python: Refactor and add accessors to sample event
perf python: Add mmap2 event
perf python: Add callchain support
perf python: Extend API for stat events in python.c
perf python: Expose brstack in sample event
perf python: Add syscall name/id to convert syscall number and name
perf python: Add config file access
perf python: Add perf.pyi stubs file
perf python: Add LiveSession helper
perf python: Move exported-sql-viewer.py and parallel-perf.py to
tools/perf/python/
perf stat-cpi: Port stat-cpi to use python module
perf mem-phys-addr: Port mem-phys-addr to use python module
perf syscall-counts: Port syscall-counts to use python module
perf syscall-counts-by-pid: Port syscall-counts-by-pid to use python
module
perf futex-contention: Port futex-contention to use python module
perf flamegraph: Port flamegraph to use python module
perf gecko: Port gecko to use python module
perf arm-cs-trace-disasm: Port arm-cs-trace-disasm to use python
module
perf check-perf-trace: Port check-perf-trace to use python module
perf compaction-times: Port compaction-times to use python module
perf event_analyzing_sample: Port event_analyzing_sample to use python
module
perf export-to-sqlite: Port export-to-sqlite to use python module
perf export-to-postgresql: Port export-to-postgresql to use python
module
perf failed-syscalls-by-pid: Port failed-syscalls-by-pid to use python
module
perf intel-pt-events: Port intel-pt-events/libxed to use python module
perf net_dropmonitor: Port net_dropmonitor to use python module
perf netdev-times: Port netdev-times to use python module
perf powerpc-hcalls: Port powerpc-hcalls to use python module
perf sched-migration: Port sched-migration/SchedGui to use python
module
perf sctop: Port sctop to use python module
perf stackcollapse: Port stackcollapse to use python module
perf task-analyzer: Port task-analyzer to use python module
perf failed-syscalls: Port failed-syscalls to use python module
perf rw-by-file: Port rw-by-file to use python module
perf rw-by-pid: Port rw-by-pid to use python module
perf rwtop: Port rwtop to use python module
perf wakeup-latency: Port wakeup-latency to use python module
perf test: Migrate Intel PT virtual LBR test to use Python API
perf: Remove libperl support, legacy Perl scripts and tests
perf: Remove libpython support and legacy Python scripts
perf Makefile: Update Python script installation path
perf script: Refactor to support standalone scripts and remove legacy
features
perf Documentation: Update for standalone Python scripts and remove
obsolete data
perf python: Improve perf script -l descriptions
tools/build/Makefile.feature | 5 +-
tools/build/feature/Makefile | 23 +-
tools/build/feature/test-all.c | 6 +-
tools/build/feature/test-libperl.c | 10 -
tools/build/feature/test-libpython.c | 10 -
tools/build/feature/test-python-module.c | 12 +
tools/perf/Documentation/perf-check.txt | 2 -
tools/perf/Documentation/perf-script-perl.txt | 216 --
.../perf/Documentation/perf-script-python.txt | 713 +----
tools/perf/Documentation/perf-script.txt | 70 +-
tools/perf/Makefile.config | 37 +-
tools/perf/Makefile.perf | 22 +-
tools/perf/arch/arm/util/cs-etm.c | 36 +-
tools/perf/arch/arm64/util/arm-spe.c | 8 +-
tools/perf/arch/arm64/util/hisi-ptt.c | 2 +-
tools/perf/arch/x86/tests/hybrid.c | 22 +-
tools/perf/arch/x86/tests/topdown.c | 2 +-
tools/perf/arch/x86/util/auxtrace.c | 2 +-
tools/perf/arch/x86/util/intel-bts.c | 26 +-
tools/perf/arch/x86/util/intel-pt.c | 38 +-
tools/perf/arch/x86/util/iostat.c | 8 +-
tools/perf/bench/evlist-open-close.c | 29 +-
tools/perf/builtin-annotate.c | 2 +-
tools/perf/builtin-check.c | 3 +-
tools/perf/builtin-ftrace.c | 14 +-
tools/perf/builtin-inject.c | 4 +-
tools/perf/builtin-kvm.c | 14 +-
tools/perf/builtin-kwork.c | 8 +-
tools/perf/builtin-lock.c | 2 +-
tools/perf/builtin-record.c | 95 +-
tools/perf/builtin-report.c | 6 +-
tools/perf/builtin-sched.c | 26 +-
tools/perf/builtin-script.c | 906 +++---
tools/perf/builtin-stat.c | 81 +-
tools/perf/builtin-top.c | 104 +-
tools/perf/builtin-trace.c | 60 +-
tools/perf/python/SchedGui.py | 219 ++
tools/perf/python/arm-cs-trace-disasm.py | 338 +++
tools/perf/python/check-perf-trace.py | 120 +
tools/perf/python/compaction-times.py | 333 +++
tools/perf/python/counting.py | 1 +
tools/perf/python/event_analyzing_sample.py | 297 ++
tools/perf/python/export-to-postgresql.py | 701 +++++
tools/perf/python/export-to-sqlite.py | 372 +++
.../python/exported-sql-viewer.py | 6 +-
tools/perf/python/failed-syscalls-by-pid.py | 116 +
tools/perf/python/failed-syscalls.py | 78 +
tools/perf/python/flamegraph.py | 250 ++
tools/perf/python/futex-contention.py | 87 +
tools/perf/python/gecko.py | 385 +++
tools/perf/python/intel-pt-events.py | 435 +++
tools/perf/python/libxed.py | 122 +
.../{scripts => }/python/mem-phys-addr.py | 66 +-
tools/perf/python/net_dropmonitor.py | 58 +
tools/perf/python/netdev-times.py | 472 ++++
.../{scripts => }/python/parallel-perf.py | 0
tools/perf/python/perf.pyi | 605 ++++
tools/perf/python/perf_live.py | 52 +
tools/perf/python/powerpc-hcalls.py | 211 ++
tools/perf/python/rw-by-file.py | 103 +
tools/perf/python/rw-by-pid.py | 158 ++
tools/perf/python/rwtop.py | 219 ++
tools/perf/python/sched-migration.py | 469 +++
tools/perf/python/sctop.py | 186 ++
tools/perf/python/stackcollapse.py | 126 +
tools/perf/python/stat-cpi.py | 151 +
tools/perf/python/syscall-counts-by-pid.py | 88 +
tools/perf/python/syscall-counts.py | 72 +
tools/perf/python/task-analyzer.py | 551 ++++
tools/perf/python/tracepoint.py | 1 +
tools/perf/python/twatch.py | 1 +
tools/perf/python/wakeup-latency.py | 88 +
tools/perf/scripts/Build | 4 -
tools/perf/scripts/perl/Perf-Trace-Util/Build | 9 -
.../scripts/perl/Perf-Trace-Util/Context.c | 122 -
.../scripts/perl/Perf-Trace-Util/Context.xs | 42 -
.../scripts/perl/Perf-Trace-Util/Makefile.PL | 18 -
.../perf/scripts/perl/Perf-Trace-Util/README | 59 -
.../Perf-Trace-Util/lib/Perf/Trace/Context.pm | 55 -
.../Perf-Trace-Util/lib/Perf/Trace/Core.pm | 192 --
.../Perf-Trace-Util/lib/Perf/Trace/Util.pm | 94 -
.../perf/scripts/perl/Perf-Trace-Util/typemap | 1 -
.../scripts/perl/bin/check-perf-trace-record | 2 -
.../scripts/perl/bin/failed-syscalls-record | 3 -
.../scripts/perl/bin/failed-syscalls-report | 10 -
tools/perf/scripts/perl/bin/rw-by-file-record | 3 -
tools/perf/scripts/perl/bin/rw-by-file-report | 10 -
tools/perf/scripts/perl/bin/rw-by-pid-record | 2 -
tools/perf/scripts/perl/bin/rw-by-pid-report | 3 -
tools/perf/scripts/perl/bin/rwtop-record | 2 -
tools/perf/scripts/perl/bin/rwtop-report | 20 -
.../scripts/perl/bin/wakeup-latency-record | 6 -
.../scripts/perl/bin/wakeup-latency-report | 3 -
tools/perf/scripts/perl/check-perf-trace.pl | 106 -
tools/perf/scripts/perl/failed-syscalls.pl | 47 -
tools/perf/scripts/perl/rw-by-file.pl | 106 -
tools/perf/scripts/perl/rw-by-pid.pl | 184 --
tools/perf/scripts/perl/rwtop.pl | 203 --
tools/perf/scripts/perl/wakeup-latency.pl | 107 -
.../perf/scripts/python/Perf-Trace-Util/Build | 4 -
.../scripts/python/Perf-Trace-Util/Context.c | 225 --
.../Perf-Trace-Util/lib/Perf/Trace/Core.py | 116 -
.../lib/Perf/Trace/EventClass.py | 97 -
.../lib/Perf/Trace/SchedGui.py | 184 --
.../Perf-Trace-Util/lib/Perf/Trace/Util.py | 92 -
.../scripts/python/arm-cs-trace-disasm.py | 355 ---
.../python/bin/compaction-times-record | 2 -
.../python/bin/compaction-times-report | 4 -
.../python/bin/event_analyzing_sample-record | 8 -
.../python/bin/event_analyzing_sample-report | 3 -
.../python/bin/export-to-postgresql-record | 8 -
.../python/bin/export-to-postgresql-report | 29 -
.../python/bin/export-to-sqlite-record | 8 -
.../python/bin/export-to-sqlite-report | 29 -
.../python/bin/failed-syscalls-by-pid-record | 3 -
.../python/bin/failed-syscalls-by-pid-report | 10 -
.../perf/scripts/python/bin/flamegraph-record | 2 -
.../perf/scripts/python/bin/flamegraph-report | 3 -
.../python/bin/futex-contention-record | 2 -
.../python/bin/futex-contention-report | 4 -
tools/perf/scripts/python/bin/gecko-record | 2 -
tools/perf/scripts/python/bin/gecko-report | 7 -
.../scripts/python/bin/intel-pt-events-record | 13 -
.../scripts/python/bin/intel-pt-events-report | 3 -
.../scripts/python/bin/mem-phys-addr-record | 19 -
.../scripts/python/bin/mem-phys-addr-report | 3 -
.../scripts/python/bin/net_dropmonitor-record | 2 -
.../scripts/python/bin/net_dropmonitor-report | 4 -
.../scripts/python/bin/netdev-times-record | 8 -
.../scripts/python/bin/netdev-times-report | 5 -
.../scripts/python/bin/powerpc-hcalls-record | 2 -
.../scripts/python/bin/powerpc-hcalls-report | 2 -
.../scripts/python/bin/sched-migration-record | 2 -
.../scripts/python/bin/sched-migration-report | 3 -
tools/perf/scripts/python/bin/sctop-record | 3 -
tools/perf/scripts/python/bin/sctop-report | 24 -
.../scripts/python/bin/stackcollapse-record | 8 -
.../scripts/python/bin/stackcollapse-report | 3 -
.../python/bin/syscall-counts-by-pid-record | 3 -
.../python/bin/syscall-counts-by-pid-report | 10 -
.../scripts/python/bin/syscall-counts-record | 3 -
.../scripts/python/bin/syscall-counts-report | 10 -
.../scripts/python/bin/task-analyzer-record | 2 -
.../scripts/python/bin/task-analyzer-report | 3 -
tools/perf/scripts/python/check-perf-trace.py | 84 -
tools/perf/scripts/python/compaction-times.py | 311 --
.../scripts/python/event_analyzing_sample.py | 192 --
.../scripts/python/export-to-postgresql.py | 1114 --------
tools/perf/scripts/python/export-to-sqlite.py | 799 ------
.../scripts/python/failed-syscalls-by-pid.py | 79 -
tools/perf/scripts/python/flamegraph.py | 267 --
tools/perf/scripts/python/futex-contention.py | 57 -
tools/perf/scripts/python/gecko.py | 395 ---
tools/perf/scripts/python/intel-pt-events.py | 494 ----
tools/perf/scripts/python/libxed.py | 107 -
tools/perf/scripts/python/net_dropmonitor.py | 78 -
tools/perf/scripts/python/netdev-times.py | 473 ----
tools/perf/scripts/python/powerpc-hcalls.py | 202 --
tools/perf/scripts/python/sched-migration.py | 462 ---
tools/perf/scripts/python/sctop.py | 89 -
tools/perf/scripts/python/stackcollapse.py | 127 -
tools/perf/scripts/python/stat-cpi.py | 79 -
.../scripts/python/syscall-counts-by-pid.py | 75 -
tools/perf/scripts/python/syscall-counts.py | 65 -
tools/perf/scripts/python/task-analyzer.py | 934 ------
tools/perf/tests/backward-ring-buffer.c | 26 +-
tools/perf/tests/code-reading.c | 14 +-
tools/perf/tests/event-times.c | 6 +-
tools/perf/tests/event_update.c | 4 +-
tools/perf/tests/evsel-roundtrip-name.c | 8 +-
tools/perf/tests/evsel-tp-sched.c | 4 +-
tools/perf/tests/expand-cgroup.c | 12 +-
tools/perf/tests/hists_cumulate.c | 2 +-
tools/perf/tests/hists_filter.c | 2 +-
tools/perf/tests/hists_link.c | 2 +-
tools/perf/tests/hists_output.c | 2 +-
tools/perf/tests/hwmon_pmu.c | 21 +-
tools/perf/tests/keep-tracking.c | 10 +-
tools/perf/tests/make | 9 +-
tools/perf/tests/mmap-basic.c | 42 +-
tools/perf/tests/openat-syscall-all-cpus.c | 6 +-
tools/perf/tests/openat-syscall-tp-fields.c | 26 +-
tools/perf/tests/openat-syscall.c | 6 +-
tools/perf/tests/parse-events.c | 139 +-
tools/perf/tests/parse-metric.c | 8 +-
tools/perf/tests/parse-no-sample-id-all.c | 2 +-
tools/perf/tests/perf-record.c | 38 +-
tools/perf/tests/perf-time-to-tsc.c | 12 +-
tools/perf/tests/pfm.c | 12 +-
tools/perf/tests/pmu-events.c | 11 +-
tools/perf/tests/pmu.c | 4 +-
tools/perf/tests/sample-parsing.c | 42 +-
.../perf/tests/shell/lib/perf_brstack_max.py | 43 +
tools/perf/tests/shell/script.sh | 4 +-
tools/perf/tests/shell/script_perl.sh | 102 -
tools/perf/tests/shell/script_python.sh | 113 -
.../tests/shell/test_arm_coresight_disasm.sh | 12 +-
tools/perf/tests/shell/test_intel_pt.sh | 35 +-
tools/perf/tests/shell/test_task_analyzer.sh | 79 +-
tools/perf/tests/sw-clock.c | 20 +-
tools/perf/tests/switch-tracking.c | 10 +-
tools/perf/tests/task-exit.c | 20 +-
tools/perf/tests/time-utils-test.c | 14 +-
tools/perf/tests/tool_pmu.c | 7 +-
tools/perf/tests/topology.c | 4 +-
tools/perf/ui/browsers/annotate.c | 2 +-
tools/perf/ui/browsers/hists.c | 22 +-
tools/perf/ui/browsers/scripts.c | 21 +-
tools/perf/util/Build | 3 +-
tools/perf/util/amd-sample-raw.c | 2 +-
tools/perf/util/annotate-data.c | 2 +-
tools/perf/util/annotate.c | 10 +-
tools/perf/util/auxtrace.c | 14 +-
tools/perf/util/block-info.c | 4 +-
tools/perf/util/bpf_counter.c | 2 +-
tools/perf/util/bpf_counter_cgroup.c | 10 +-
tools/perf/util/bpf_ftrace.c | 9 +-
tools/perf/util/bpf_lock_contention.c | 12 +-
tools/perf/util/bpf_off_cpu.c | 44 +-
tools/perf/util/bpf_trace_augment.c | 8 +-
tools/perf/util/cgroup.c | 26 +-
tools/perf/util/cs-etm.c | 5 +-
tools/perf/util/data-convert-bt.c | 2 +-
tools/perf/util/data.c | 26 +-
tools/perf/util/data.h | 4 +-
tools/perf/util/evlist.c | 492 ++--
tools/perf/util/evlist.h | 273 +-
tools/perf/util/evsel.c | 109 +-
tools/perf/util/evsel.h | 35 +-
tools/perf/util/expr.c | 2 +-
tools/perf/util/header.c | 51 +-
tools/perf/util/header.h | 2 +-
tools/perf/util/intel-tpebs.c | 7 +-
tools/perf/util/map.h | 9 +-
tools/perf/util/metricgroup.c | 12 +-
tools/perf/util/parse-events.c | 10 +-
tools/perf/util/parse-events.y | 2 +-
tools/perf/util/perf_api_probe.c | 20 +-
tools/perf/util/pfm.c | 4 +-
tools/perf/util/print-events.c | 2 +-
tools/perf/util/print_insn.h | 5 +-
tools/perf/util/python.c | 2507 ++++++++++++++---
tools/perf/util/record.c | 11 +-
tools/perf/util/s390-sample-raw.c | 19 +-
tools/perf/util/sample-raw.c | 4 +-
tools/perf/util/sample.c | 17 +-
tools/perf/util/scripting-engines/Build | 9 -
.../util/scripting-engines/trace-event-perl.c | 773 -----
.../scripting-engines/trace-event-python.c | 2209 ---------------
tools/perf/util/session.c | 59 +-
tools/perf/util/sideband_evlist.c | 40 +-
tools/perf/util/sort.c | 2 +-
tools/perf/util/stat-display.c | 6 +-
tools/perf/util/stat-shadow.c | 24 +-
tools/perf/util/stat.c | 20 +-
tools/perf/util/stream.c | 4 +-
tools/perf/util/synthetic-events.c | 11 +-
tools/perf/util/time-utils.c | 12 +-
tools/perf/util/top.c | 4 +-
tools/perf/util/trace-event-parse.c | 65 -
tools/perf/util/trace-event-scripting.c | 410 ---
tools/perf/util/trace-event.h | 75 +-
262 files changed, 11713 insertions(+), 16153 deletions(-)
delete mode 100644 tools/build/feature/test-libperl.c
delete mode 100644 tools/build/feature/test-libpython.c
create mode 100644 tools/build/feature/test-python-module.c
delete mode 100644 tools/perf/Documentation/perf-script-perl.txt
create mode 100755 tools/perf/python/SchedGui.py
create mode 100755 tools/perf/python/arm-cs-trace-disasm.py
create mode 100755 tools/perf/python/check-perf-trace.py
create mode 100755 tools/perf/python/compaction-times.py
create mode 100755 tools/perf/python/event_analyzing_sample.py
create mode 100755 tools/perf/python/export-to-postgresql.py
create mode 100755 tools/perf/python/export-to-sqlite.py
rename tools/perf/{scripts => }/python/exported-sql-viewer.py (99%)
create mode 100755 tools/perf/python/failed-syscalls-by-pid.py
create mode 100755 tools/perf/python/failed-syscalls.py
create mode 100755 tools/perf/python/flamegraph.py
create mode 100755 tools/perf/python/futex-contention.py
create mode 100755 tools/perf/python/gecko.py
create mode 100755 tools/perf/python/intel-pt-events.py
create mode 100755 tools/perf/python/libxed.py
rename tools/perf/{scripts => }/python/mem-phys-addr.py (73%)
mode change 100644 => 100755
create mode 100755 tools/perf/python/net_dropmonitor.py
create mode 100755 tools/perf/python/netdev-times.py
rename tools/perf/{scripts => }/python/parallel-perf.py (100%)
create mode 100644 tools/perf/python/perf.pyi
create mode 100755 tools/perf/python/perf_live.py
create mode 100755 tools/perf/python/powerpc-hcalls.py
create mode 100755 tools/perf/python/rw-by-file.py
create mode 100755 tools/perf/python/rw-by-pid.py
create mode 100755 tools/perf/python/rwtop.py
create mode 100755 tools/perf/python/sched-migration.py
create mode 100755 tools/perf/python/sctop.py
create mode 100755 tools/perf/python/stackcollapse.py
create mode 100755 tools/perf/python/stat-cpi.py
create mode 100755 tools/perf/python/syscall-counts-by-pid.py
create mode 100755 tools/perf/python/syscall-counts.py
create mode 100755 tools/perf/python/task-analyzer.py
create mode 100755 tools/perf/python/wakeup-latency.py
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/Build
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/Context.c
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/README
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/typemap
delete mode 100644 tools/perf/scripts/perl/bin/check-perf-trace-record
delete mode 100644 tools/perf/scripts/perl/bin/failed-syscalls-record
delete mode 100644 tools/perf/scripts/perl/bin/failed-syscalls-report
delete mode 100644 tools/perf/scripts/perl/bin/rw-by-file-record
delete mode 100644 tools/perf/scripts/perl/bin/rw-by-file-report
delete mode 100644 tools/perf/scripts/perl/bin/rw-by-pid-record
delete mode 100644 tools/perf/scripts/perl/bin/rw-by-pid-report
delete mode 100644 tools/perf/scripts/perl/bin/rwtop-record
delete mode 100644 tools/perf/scripts/perl/bin/rwtop-report
delete mode 100644 tools/perf/scripts/perl/bin/wakeup-latency-record
delete mode 100644 tools/perf/scripts/perl/bin/wakeup-latency-report
delete mode 100644 tools/perf/scripts/perl/check-perf-trace.pl
delete mode 100644 tools/perf/scripts/perl/failed-syscalls.pl
delete mode 100644 tools/perf/scripts/perl/rw-by-file.pl
delete mode 100644 tools/perf/scripts/perl/rw-by-pid.pl
delete mode 100644 tools/perf/scripts/perl/rwtop.pl
delete mode 100644 tools/perf/scripts/perl/wakeup-latency.pl
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/Build
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/Context.c
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
delete mode 100755 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
delete mode 100755 tools/perf/scripts/python/arm-cs-trace-disasm.py
delete mode 100644 tools/perf/scripts/python/bin/compaction-times-record
delete mode 100644 tools/perf/scripts/python/bin/compaction-times-report
delete mode 100644 tools/perf/scripts/python/bin/event_analyzing_sample-record
delete mode 100644 tools/perf/scripts/python/bin/event_analyzing_sample-report
delete mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-record
delete mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-report
delete mode 100644 tools/perf/scripts/python/bin/export-to-sqlite-record
delete mode 100644 tools/perf/scripts/python/bin/export-to-sqlite-report
delete mode 100644 tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
delete mode 100644 tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
delete mode 100755 tools/perf/scripts/python/bin/flamegraph-record
delete mode 100755 tools/perf/scripts/python/bin/flamegraph-report
delete mode 100644 tools/perf/scripts/python/bin/futex-contention-record
delete mode 100644 tools/perf/scripts/python/bin/futex-contention-report
delete mode 100644 tools/perf/scripts/python/bin/gecko-record
delete mode 100755 tools/perf/scripts/python/bin/gecko-report
delete mode 100644 tools/perf/scripts/python/bin/intel-pt-events-record
delete mode 100644 tools/perf/scripts/python/bin/intel-pt-events-report
delete mode 100644 tools/perf/scripts/python/bin/mem-phys-addr-record
delete mode 100644 tools/perf/scripts/python/bin/mem-phys-addr-report
delete mode 100755 tools/perf/scripts/python/bin/net_dropmonitor-record
delete mode 100755 tools/perf/scripts/python/bin/net_dropmonitor-report
delete mode 100644 tools/perf/scripts/python/bin/netdev-times-record
delete mode 100644 tools/perf/scripts/python/bin/netdev-times-report
delete mode 100644 tools/perf/scripts/python/bin/powerpc-hcalls-record
delete mode 100644 tools/perf/scripts/python/bin/powerpc-hcalls-report
delete mode 100644 tools/perf/scripts/python/bin/sched-migration-record
delete mode 100644 tools/perf/scripts/python/bin/sched-migration-report
delete mode 100644 tools/perf/scripts/python/bin/sctop-record
delete mode 100644 tools/perf/scripts/python/bin/sctop-report
delete mode 100755 tools/perf/scripts/python/bin/stackcollapse-record
delete mode 100755 tools/perf/scripts/python/bin/stackcollapse-report
delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-by-pid-record
delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-by-pid-report
delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-record
delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-report
delete mode 100755 tools/perf/scripts/python/bin/task-analyzer-record
delete mode 100755 tools/perf/scripts/python/bin/task-analyzer-report
delete mode 100644 tools/perf/scripts/python/check-perf-trace.py
delete mode 100644 tools/perf/scripts/python/compaction-times.py
delete mode 100644 tools/perf/scripts/python/event_analyzing_sample.py
delete mode 100644 tools/perf/scripts/python/export-to-postgresql.py
delete mode 100644 tools/perf/scripts/python/export-to-sqlite.py
delete mode 100644 tools/perf/scripts/python/failed-syscalls-by-pid.py
delete mode 100755 tools/perf/scripts/python/flamegraph.py
delete mode 100644 tools/perf/scripts/python/futex-contention.py
delete mode 100644 tools/perf/scripts/python/gecko.py
delete mode 100644 tools/perf/scripts/python/intel-pt-events.py
delete mode 100644 tools/perf/scripts/python/libxed.py
delete mode 100755 tools/perf/scripts/python/net_dropmonitor.py
delete mode 100644 tools/perf/scripts/python/netdev-times.py
delete mode 100644 tools/perf/scripts/python/powerpc-hcalls.py
delete mode 100644 tools/perf/scripts/python/sched-migration.py
delete mode 100644 tools/perf/scripts/python/sctop.py
delete mode 100755 tools/perf/scripts/python/stackcollapse.py
delete mode 100644 tools/perf/scripts/python/stat-cpi.py
delete mode 100644 tools/perf/scripts/python/syscall-counts-by-pid.py
delete mode 100644 tools/perf/scripts/python/syscall-counts.py
delete mode 100755 tools/perf/scripts/python/task-analyzer.py
create mode 100644 tools/perf/tests/shell/lib/perf_brstack_max.py
delete mode 100755 tools/perf/tests/shell/script_perl.sh
delete mode 100755 tools/perf/tests/shell/script_python.sh
delete mode 100644 tools/perf/util/scripting-engines/Build
delete mode 100644 tools/perf/util/scripting-engines/trace-event-perl.c
delete mode 100644 tools/perf/util/scripting-engines/trace-event-python.c
delete mode 100644 tools/perf/util/trace-event-scripting.c
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply
* [PATCH v8 01/58] perf arch arm: Sort includes and add missed explicit dependencies
From: Ian Rogers @ 2026-04-28 7:18 UTC (permalink / raw)
To: acme, namhyung
Cc: adrian.hunter, alice.mei.rogers, dapeng1.mi, james.clark, leo.yan,
linux-arm-kernel, linux-kernel, linux-perf-users, mingo, peterz,
tmricht, Ian Rogers
In-Reply-To: <20260428071903.1886173-1-irogers@google.com>
Fix missing #includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/arch/arm/util/cs-etm.c | 26 ++++++++++++++------------
1 file changed, 14 insertions(+), 12 deletions(-)
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index b7a839de8707..cdf8e3e60606 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -3,10 +3,13 @@
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
*/
+#include "../../../util/cs-etm.h"
+
+#include <errno.h>
+#include <stdlib.h>
-#include <api/fs/fs.h>
-#include <linux/bits.h>
#include <linux/bitops.h>
+#include <linux/bits.h>
#include <linux/compiler.h>
#include <linux/coresight-pmu.h>
#include <linux/kernel.h>
@@ -14,25 +17,24 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/zalloc.h>
+#include <sys/stat.h>
+
+#include <api/fs/fs.h>
+#include <internal/lib.h> // page_size
-#include "cs-etm.h"
-#include "../../../util/debug.h"
-#include "../../../util/record.h"
#include "../../../util/auxtrace.h"
#include "../../../util/cpumap.h"
+#include "../../../util/debug.h"
#include "../../../util/event.h"
#include "../../../util/evlist.h"
#include "../../../util/evsel.h"
-#include "../../../util/perf_api_probe.h"
#include "../../../util/evsel_config.h"
+#include "../../../util/perf_api_probe.h"
+#include "../../../util/pmu.h"
#include "../../../util/pmus.h"
-#include "../../../util/cs-etm.h"
-#include <internal/lib.h> // page_size
+#include "../../../util/record.h"
#include "../../../util/session.h"
-
-#include <errno.h>
-#include <stdlib.h>
-#include <sys/stat.h>
+#include "cs-etm.h"
struct cs_etm_recording {
struct auxtrace_record itr;
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* Re: [PATCH] ASoC: dt-bindings: mediatek,mt6351: convert to DT schema
From: Krzysztof Kozlowski @ 2026-04-28 7:05 UTC (permalink / raw)
To: Manish Baing
Cc: lgirdwood, broonie, robh, krzk+dt, conor+dt, matthias.bgg,
angelogioacchino.delregno, kaichieh.chuang, linux-sound,
devicetree, linux-kernel, linux-arm-kernel, linux-mediatek
In-Reply-To: <20260424210302.39972-1-manishbaing2789@gmail.com>
On Fri, Apr 24, 2026 at 09:03:02PM +0000, Manish Baing wrote:
> +description:
> + MT6351 Audio CODEC is a part of the MediaTek MT6351 PMIC.
> + It communicates with the SoC through the MediaTek PMIC wrapper(pwrap).
> +
> +allOf:
> + - $ref: dai-common.yaml#
> +
> +properties:
> + compatible:
> + const: mediatek,mt6351-sound
> +
> +required:
> + - compatible
> +
> +additionalProperties: false
This should be unevaluatedProperties and you probably miss here
sound-dai-cells, but this is semi-abandoned incomplete device without
users, so pretty does not matter. Conversion to DT schema also does not
matter that much. :/
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Best regards,
Krzysztof
^ permalink raw reply
* [PATCH net] net: airoha: Do not return err in ndo_stop() callback
From: Lorenzo Bianconi @ 2026-04-28 6:53 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni
Cc: Simon Horman, linux-arm-kernel, linux-mediatek, netdev,
Lorenzo Bianconi
Always complete the airoha_dev_stop() routine regardless of the
airoha_set_vip_for_gdm_port() return value, since errors from
ndo_stop() are ignored by the networking stack and the interface is
always considered down after the call.
Fixes: 23020f049327 ("net: airoha: Introduce ethernet support for EN7581 SoC")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/airoha/airoha_eth.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 5effb4a4ae84..f8b3d53bccad 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1747,13 +1747,10 @@ static int airoha_dev_stop(struct net_device *dev)
{
struct airoha_gdm_port *port = netdev_priv(dev);
struct airoha_qdma *qdma = port->qdma;
- int i, err;
+ int i;
netif_tx_disable(dev);
- err = airoha_set_vip_for_gdm_port(port, false);
- if (err)
- return err;
-
+ airoha_set_vip_for_gdm_port(port, false);
for (i = 0; i < dev->num_tx_queues; i++)
netdev_tx_reset_subqueue(dev, i);
---
base-commit: 3bc179bc7146c26c9dff75d2943d10528274e301
change-id: 20260428-airoha-ndo-stop-not-err-a154a1f72b42
Best regards,
--
Lorenzo Bianconi <lorenzo@kernel.org>
^ permalink raw reply related
* Re: [PATCH v2] dt-bindings: arm-smmu: qcom: Add Hawi compatible for Application processor
From: Krzysztof Kozlowski @ 2026-04-28 6:51 UTC (permalink / raw)
To: Mukesh Ojha
Cc: Will Deacon, Joerg Roedel, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Robin Murphy, linux-arm-kernel, iommu, devicetree,
linux-kernel
In-Reply-To: <20260427174915.3639641-1-mukesh.ojha@oss.qualcomm.com>
On Mon, Apr 27, 2026 at 11:19:15PM +0530, Mukesh Ojha wrote:
> Commit 5e8323c3d528 ("dt-bindings: arm-smmu: qcom: Add compatible for
> Hawi SoC") was intended for the APSS SMMU but was mistakenly placed
Would be nice to see explanation what is APSS. We do ask for that every
couple of months.
> under the Adreno GPU SMMU section. Since that compatible is also valid
> for the Hawi GPU SMMU, keep that commit as-is and add proper
> documentation for the Hawi APSS SMMU here.
>
> Signed-off-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com>
> ---
> Changes in v2: https://lore.kernel.org/lkml/20260422083329.885979-1-mukesh.ojha@oss.qualcomm.com/
> - Not a fix commit after discussion.
> - Not removing the earlier commit change instead add one for APSS
> SMMU.
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Best regards,
Krzysztof
^ permalink raw reply
* Re: [PATCH v8 1/4] coresight: cti: Convert trigger usage fields to dynamic bitmaps and arrays
From: Leo Yan @ 2026-04-28 6:33 UTC (permalink / raw)
To: Yingchao Deng (Consultant)
Cc: Yingchao Deng, Suzuki K Poulose, Mike Leach, James Clark,
Alexander Shishkin, coresight, linux-arm-kernel, linux-kernel,
linux-arm-msm, Jinlong Mao, Tingwei Zhang, Jie Gan
In-Reply-To: <b20a2f7c-4838-408f-94ed-ee9656d451c4@quicinc.com>
On Tue, Apr 28, 2026 at 10:25:11AM +0800, Yingchao Deng (Consultant) wrote:
[...]
> > tg->used_mask = bitmap_zalloc(nr_filter_sigs, GFP_KERNEL);
> "nr_filter_sigs" is the count of entries in the DT property array, if the DT
> property is:
> arm,trig-filters = <22 23>;
> Here nr_filter_sigs=2, so bitmap_zalloc(2) allocates only 1 unsigned long
> (64 bits). set_bit(22/23, used_mask) still fits, but it's logically an OOB,
> and any index >=64 would
> write past the end.
Thanks for explanation. It is correct for me.
^ permalink raw reply
* Re: [RESEND,v2 1/2] dt-bindings: memory-controllers: mtk-smi: Add support for mt8189
From: Krzysztof Kozlowski @ 2026-04-28 6:26 UTC (permalink / raw)
To: mtk20898
Cc: Yong Wu, Rob Herring, Conor Dooley, Matthias Brugger,
AngeloGioacchino Del Regno, linux-mediatek, linux-kernel,
devicetree, linux-arm-kernel,
Project_Global_Chrome_Upstream_Group
In-Reply-To: <20260427070444.20247-2-zhengnan.chen@mediatek.com>
On Mon, Apr 27, 2026 at 03:04:28PM +0800, mtk20898 wrote:
> properties:
> compatible:
> oneOf:
> @@ -40,6 +55,8 @@ properties:
> - mediatek,mt8186-smi-common
> - mediatek,mt8188-smi-common-vdo
> - mediatek,mt8188-smi-common-vpp
> + - mediatek,mt8189-smi-common
> + - mediatek,mt8189-smi-sub-common
> - mediatek,mt8192-smi-common
> - mediatek,mt8195-smi-common-vdo
> - mediatek,mt8195-smi-common-vpp
> @@ -108,19 +125,23 @@ allOf:
> compatible:
> contains:
> enum:
> + - mediatek,mt8189-smi-sub-common
> - mediatek,mt8195-smi-sub-common
> then:
> required:
> - mediatek,smi
> properties:
> clocks:
> - minItems: 3
> + minItems: 2
Same problem as v2 before resend.
Please explain me how mt8195 requires three clocks. You can prove it by
trying a malformed DTS (past here the snippet/diff) and pasting here the
validation error.
Best regards,
Krzysztof
^ permalink raw reply
* Re: [REGRESSION] rseq: refactoring in v6.19 broke everyone on arm64 and tcmalloc everywhere
From: Dmitry Vyukov @ 2026-04-28 6:11 UTC (permalink / raw)
To: Thomas Gleixner
Cc: Peter Zijlstra, Mathias Stearn, Jinjie Ruan, linux-man,
Mark Rutland, Mathieu Desnoyers, Catalin Marinas, Will Deacon,
Boqun Feng, Paul E. McKenney, Chris Kennelly, regressions,
linux-kernel, linux-arm-kernel, Ingo Molnar, Blake Oler,
Florian Weimer, Rich Felker, Matthew Wilcox, Greg Kroah-Hartman,
Linus Torvalds
In-Reply-To: <87jyttz8cf.ffs@tglx>
On Mon, 27 Apr 2026 at 00:04, Thomas Gleixner <tglx@kernel.org> wrote:
>
> On Fri, Apr 24 2026 at 21:44, Thomas Gleixner wrote:
> > On Fri, Apr 24 2026 at 17:03, Peter Zijlstra wrote:
> >> On Fri, Apr 24, 2026 at 04:16:08PM +0200, Thomas Gleixner wrote:
> >>> > I was really hoping that we would only need to do the "redundant"
> >>> > cpu_id_start writes would only be needed on membarrier_rseq IPIs where
> >>> > it really is a pay-for-what-you-use functionality,
> >>>
> >>> That's fine and can be solved without adding this sequence overhead into
> >>> the scheduler hotpath.
> >>
> >> Something like so? (probably needs help for !GENERIC bits)
> >
> > Yes and yes :)
> >
> > Let me stare at that !generic tif bits case.
>
> I stared at it and finally gave up because all of this is in a
> completely FUBAR'ed state and ends up in a horrible pile of hacks and
> duct tape with a way larger than zero probability that we chase the
> nasty corner cases for quite some time just to add more duct tape and
> hacks.
>
> Contrary to that it's rather trivial to cleanly separate the behavioral
> cases and guarantees without a masssive runtime overhead and without a
> pile of hard to maintain TCMalloc specific hacks.
>
> All required code is already available to support the architectures
> which do not utilize the generic entry code and therefore can't neither
> use the optimized mode nor time slice extensions. So instead of letting
> the compiler optimize that code out for the generic entry code users, we
> can keep it around and utilize one or the other depending on the
> requested mode. I managed to get the required run-time conditionals down
> to a minimum so that they are in the noise when analysing it with perf.
>
> The real question is how to differentiate between the legacy and the
> optimized mode. I have two working variants to achieve that:
>
> 1) The fully safe option requires a new flag for RSEQ
> registration. It obviously requires a glibc update. (Suggested by
> PeterZ)
>
> 2) Determine the requirements of the registering task via the size of
> the registered RSEQ area.
>
> The original implementation, which TCMalloc depends on, registers
> a 32 byte region (ORIG_RSEG_SIZE). This region has 32 byte
> alignment requirement.
>
> The extension safe newer variant exposes the kernel RSEQ feature
> size via getauxval(AT_RSEQ_FEATURE_SIZE) and the alignment
> requirement via getauxval(AT_RSEQ_ALIGN). The alignment
> requirement is that the registered rseq region is aligned to the
> next power of two of the feature size. The kernel currently has a
> feature size of 33 bytes, which means the alignment requirement is
> 64 bytes.
>
> The TCMalloc RSEQ region is embedded into a cache line aligned
> data structure starting at offset 32 bytes so that bytes 28-31 and
> the cpu_id_start field at bytes 32-35 form a 64-bit little endian
> pointer with the top-most bit (63 set) to check whether the kernel
> has overwritten cpu_id_start with an actual CPU id value, which is
> guaranteed to not have the top most bit set.
>
> As this is part of their performance tuned magic, it's a pretty
> safe assumption, that TCMalloc won't use a larger RSEQ size, which
> allows to select optimized mode for registrations with a size
> greater than 32 bytes.
>
> That does not require any changes to glibc and works out of the
> box. (Suggested by Mathieu)
>
> In both cases the legacy non-optimized mode exposes the original
> behaviour up to the mm_cid field and does not provide support for time
> slice extensions. Optimized mode restores the performance gains and
> enables support for time slice extensions.
>
> I have no strong preference either way and have working code for both
> variants. Though obviously avoiding to update the libc world has a
> charme. If that unexpectedly would turn out to be not sufficient, then
> disabling that would be a trivial one-liner and as a consequence require
> to add the flag and update the libc world.
>
> Combo patch for the auto-detection based on the registered size below as
> that allows to immediately test without glibc dependencies. It applies
> cleanly on Linus tree and 7.0. 6.19 would need some fixups, but I
> learned today that it's already EOL.
>
> In the final version that's three separate patches plus a set of
> selftest changes which validate legacy behaviour and run the full param
> test suite in both legacy and optimized mode.
>
> Thoughts, preferences?
I like this! This does not create fires, and allows incremental transition.
I've tested the patch with membarrier doing TIF_RSEQ_FORCE_RESTART,
and it did not work with unmodified tcmalloc for subtle reasons
anyway. Tcmalloc can be made to work with that approach with minor
changes, but if the goal is to keep old binaries working, that won't
work.
I've tested this patch with unmodified tcmalloc tests, and it almost works.
I think the recent rseq changes introduced 2 more regressions/bugs.
They are caught by tcmalloc tests, but I think they equally affect
optimized v2 mode.
1. This seems to be broken after rseq unregistration:
"cpu_id_start Optimistic cache of the CPU number on which the
registered thread is running. Its value is guaranteed to always be a
possible CPU number, even when rseq is not registered."
Old kernels used to put cpu_id_start = 0:
https://elixir.bootlin.com/linux/v6.7/source/kernel/rseq.c#L119
But now kernel uses this function which puts cpu_id_start =
RSEQ_CPU_ID_UNINITIALIZED:
https://elixir.bootlin.com/linux/v7.0.1/source/include/linux/rseq_entry.h#L503
2. There are spurious SIGSEGV kills on rseq unregistration (thread exit).
Stress tests that unregister rseq and use membarrier sometimes killed
with SIGSEGV inside of rseq(UNREGISTER) syscall. I suspect there is
some race between ipi_rseq and rseq(UNREGISTER). I saw the same when
tested the
TIF_RSEQ_FORCE_RESTART patch -- kernel tried to update user-space rseq
when the pointer was NULL.
rseq_reset uses memset to clear t->rseq:
memset(&t->rseq, 0, sizeof(t->rseq));
If that uses byte writes, then it will clear sched_switch/ids_changed,
then at this point ipi_rseq still sees has_rseq=1 and sets
sched_switch/ids_changed, which cause update on return from
rseq(UNREGISTER).
Not sure if that's it, or there is something else.
This did not happen on older kernels which used rseq_preempt in ipi_rseq:
https://elixir.bootlin.com/linux/v6.7/source/kernel/sched/membarrier.c#L197
> Thanks,
>
> tglx
> ---
> Documentation/userspace-api/rseq.rst | 77 ++++++++++++++
> include/linux/rseq.h | 20 +++
> include/linux/rseq_entry.h | 110 ++++++++++-----------
> include/linux/rseq_types.h | 3
> kernel/rseq.c | 183 ++++++++++++++++++++++-------------
> kernel/sched/membarrier.c | 11 +-
> 6 files changed, 280 insertions(+), 124 deletions(-)
> ---
> --- a/include/linux/rseq.h
> +++ b/include/linux/rseq.h
> @@ -9,6 +9,11 @@
>
> void __rseq_handle_slowpath(struct pt_regs *regs);
>
> +static __always_inline bool rseq_optimized(struct task_struct *t)
> +{
> + return IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && likely(t->rseq.event.optimized);
> +}
> +
> /* Invoked from resume_user_mode_work() */
> static inline void rseq_handle_slowpath(struct pt_regs *regs)
> {
> @@ -30,7 +35,7 @@ void __rseq_signal_deliver(int sig, stru
> */
> static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs)
> {
> - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) {
> + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && rseq_optimized(current)) {
Just rseq_optimized(t), it already includes the other check.
> /* '&' is intentional to spare one conditional branch */
> if (current->rseq.event.has_rseq & current->rseq.event.user_irq)
> __rseq_signal_deliver(ksig->sig, regs);
> @@ -50,15 +55,21 @@ static __always_inline void rseq_sched_s
> {
> struct rseq_event *ev = &t->rseq.event;
>
> - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) {
> + /*
> + * Only apply the user_irq optimization for RSEQ ABI V2
> + * registrations. Legacy users like TCMalloc rely on the historical ABI
> + * V1 behaviour which updates IDs on every context swtich.
> + */
> + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && rseq_optimized(t)) {
Just rseq_optimized(t), it already includes the other check.
> /*
> * Avoid a boat load of conditionals by using simple logic
> * to determine whether NOTIFY_RESUME needs to be raised.
> *
> * It's required when the CPU or MM CID has changed or
> - * the entry was from user space.
> + * the entry was from user space. ev->has_rseq does not
> + * have to be evaluated because optimized implies has_rseq.
> */
> - bool raise = (ev->user_irq | ev->ids_changed) & ev->has_rseq;
> + bool raise = ev->user_irq | ev->ids_changed;
>
> if (raise) {
> ev->sched_switch = true;
> @@ -66,6 +77,7 @@ static __always_inline void rseq_sched_s
> }
> } else {
> if (ev->has_rseq) {
> + t->rseq.event.ids_changed = true;
> t->rseq.event.sched_switch = true;
> rseq_raise_notify_resume(t);
> }
> --- a/include/linux/rseq_entry.h
> +++ b/include/linux/rseq_entry.h
> @@ -111,6 +111,20 @@ static __always_inline void rseq_slice_c
> t->rseq.slice.state.granted = false;
> }
>
> +/*
> + * Open coded, so it can be invoked within a user access region.
> + *
> + * This clears the user space state of the time slice extensions field only when
> + * the task has registered the optimized RSEQ_ABI V2. Some legacy registrations,
> + * e.g. TCMalloc, have conflicting non-ABI fields in struct RSEQ, which would be
> + * overwritten by an unconditional write.
> + */
> +#define rseq_slice_clear_user(rseq, efault) \
> +do { \
> + if (rseq_slice_extension_enabled()) \
> + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); \
> +} while (0)
> +
> static __always_inline bool __rseq_grant_slice_extension(bool work_pending)
> {
> struct task_struct *curr = current;
> @@ -230,10 +244,10 @@ static __always_inline bool rseq_slice_e
> static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; }
> static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { }
> static __always_inline bool rseq_grant_slice_extension(unsigned long ti_work, unsigned long mask) { return false; }
> +#define rseq_slice_clear_user(rseq, efault) do { } while (0)
> #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */
>
> bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr);
> -bool rseq_debug_validate_ids(struct task_struct *t);
>
> static __always_inline void rseq_note_user_irq_entry(void)
> {
> @@ -353,43 +367,6 @@ bool rseq_debug_update_user_cs(struct ta
> return false;
> }
>
> -/*
> - * On debug kernels validate that user space did not mess with it if the
> - * debug branch is enabled.
> - */
> -bool rseq_debug_validate_ids(struct task_struct *t)
> -{
> - struct rseq __user *rseq = t->rseq.usrptr;
> - u32 cpu_id, uval, node_id;
> -
> - /*
> - * On the first exit after registering the rseq region CPU ID is
> - * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0!
> - */
> - node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ?
> - cpu_to_node(t->rseq.ids.cpu_id) : 0;
> -
> - scoped_user_read_access(rseq, efault) {
> - unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault);
> - if (cpu_id != t->rseq.ids.cpu_id)
> - goto die;
> - unsafe_get_user(uval, &rseq->cpu_id, efault);
> - if (uval != cpu_id)
> - goto die;
> - unsafe_get_user(uval, &rseq->node_id, efault);
> - if (uval != node_id)
> - goto die;
> - unsafe_get_user(uval, &rseq->mm_cid, efault);
> - if (uval != t->rseq.ids.mm_cid)
> - goto die;
> - }
> - return true;
> -die:
> - t->rseq.event.fatal = true;
> -efault:
> - return false;
> -}
> -
> #endif /* RSEQ_BUILD_SLOW_PATH */
>
> /*
> @@ -504,12 +481,32 @@ bool rseq_set_ids_get_csaddr(struct task
> {
> struct rseq __user *rseq = t->rseq.usrptr;
>
> - if (static_branch_unlikely(&rseq_debug_enabled)) {
> - if (!rseq_debug_validate_ids(t))
> - return false;
> - }
> -
> scoped_user_rw_access(rseq, efault) {
> + /* Validate the R/O fields for debug and optimized mode */
> + if (static_branch_unlikely(&rseq_debug_enabled) || rseq_optimized(t)) {
> + u32 cpu_id, uval, node_id;
> +
> + /*
> + * On the first exit after registering the rseq region CPU ID is
> + * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0!
> + */
> + node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ?
> + cpu_to_node(t->rseq.ids.cpu_id) : 0;
> +
> + unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault);
> + if (cpu_id != t->rseq.ids.cpu_id)
> + goto die;
> + unsafe_get_user(uval, &rseq->cpu_id, efault);
> + if (uval != cpu_id)
> + goto die;
> + unsafe_get_user(uval, &rseq->node_id, efault);
> + if (uval != node_id)
> + goto die;
> + unsafe_get_user(uval, &rseq->mm_cid, efault);
> + if (uval != t->rseq.ids.mm_cid)
> + goto die;
> + }
> +
> unsafe_put_user(ids->cpu_id, &rseq->cpu_id_start, efault);
> unsafe_put_user(ids->cpu_id, &rseq->cpu_id, efault);
> unsafe_put_user(node_id, &rseq->node_id, efault);
> @@ -517,11 +514,9 @@ bool rseq_set_ids_get_csaddr(struct task
> if (csaddr)
> unsafe_get_user(*csaddr, &rseq->rseq_cs, efault);
>
> - /* Open coded, so it's in the same user access region */
> - if (rseq_slice_extension_enabled()) {
> - /* Unconditionally clear it, no point in conditionals */
> - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
> - }
> + /* RSEQ ABI V2 only operations */
> + if (rseq_optimized(t))
> + rseq_slice_clear_user(rseq, efault);
> }
>
> rseq_slice_clear_grant(t);
> @@ -530,6 +525,9 @@ bool rseq_set_ids_get_csaddr(struct task
> rseq_stat_inc(rseq_stats.ids);
> rseq_trace_update(t, ids);
> return true;
> +
> +die:
> + t->rseq.event.fatal = true;
> efault:
> return false;
> }
> @@ -612,6 +610,14 @@ static __always_inline bool rseq_exit_us
> * interrupts disabled
> */
> guard(pagefault)();
> + /*
> + * This optimization is only valid when the task registered for the
> + * optimized RSEQ_ABI_V2 variant. Some legacy users rely on the original
> + * RSEQ implementation behaviour which unconditionally updated the IDs.
> + * rseq_sched_switch_event() ensures that legacy registrations always
> + * have both sched_switch and ids_changed set, which is compatible with
> + * the historical TIF_NOTIFY_RESUME behaviour.
> + */
> if (likely(!t->rseq.event.ids_changed)) {
> struct rseq __user *rseq = t->rseq.usrptr;
> /*
> @@ -623,11 +629,9 @@ static __always_inline bool rseq_exit_us
> scoped_user_rw_access(rseq, efault) {
> unsafe_get_user(csaddr, &rseq->rseq_cs, efault);
>
> - /* Open coded, so it's in the same user access region */
> - if (rseq_slice_extension_enabled()) {
> - /* Unconditionally clear it, no point in conditionals */
> - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
> - }
> + /* RSEQ ABI V2 only operations */
> + if (rseq_optimized(t))
> + rseq_slice_clear_user(rseq, efault);
> }
>
> rseq_slice_clear_grant(t);
> --- a/include/linux/rseq_types.h
> +++ b/include/linux/rseq_types.h
> @@ -18,6 +18,7 @@ struct rseq;
> * @ids_changed: Indicator that IDs need to be updated
> * @user_irq: True on interrupt entry from user mode
> * @has_rseq: True if the task has a rseq pointer installed
> + * @optimized: RSEQ ABI V2 optimized mode
> * @error: Compound error code for the slow path to analyze
> * @fatal: User space data corrupted or invalid
> * @slowpath: Indicator that slow path processing via TIF_NOTIFY_RESUME
> @@ -41,7 +42,7 @@ struct rseq_event {
> };
>
> u8 has_rseq;
> - u8 __pad;
> + u8 optimized;
> union {
> u16 error;
> struct {
> --- a/kernel/rseq.c
> +++ b/kernel/rseq.c
> @@ -258,11 +258,15 @@ static bool rseq_handle_cs(struct task_s
> static void rseq_slowpath_update_usr(struct pt_regs *regs)
> {
> /*
> - * Preserve rseq state and user_irq state. The generic entry code
> - * clears user_irq on the way out, the non-generic entry
> - * architectures are not having user_irq.
> - */
> - const struct rseq_event evt_mask = { .has_rseq = true, .user_irq = true, };
> + * Preserve has_rseq, optimized and user_irq state. The generic entry
> + * code clears user_irq on the way out, the non-generic entry
> + * architectures are not setting user_irq.
> + */
> + const struct rseq_event evt_mask = {
> + .has_rseq = true,
> + .user_irq = true,
> + .optimized = true,
> + };
> struct task_struct *t = current;
> struct rseq_ids ids;
> u32 node_id;
> @@ -335,8 +339,9 @@ void __rseq_handle_slowpath(struct pt_re
> void __rseq_signal_deliver(int sig, struct pt_regs *regs)
> {
> rseq_stat_inc(rseq_stats.signal);
> +
> /*
> - * Don't update IDs, they are handled on exit to user if
> + * Don't update IDs yet, they are handled on exit to user if
> * necessary. The important thing is to abort a critical section of
> * the interrupted context as after this point the instruction
> * pointer in @regs points to the signal handler.
> @@ -349,6 +354,13 @@ void __rseq_signal_deliver(int sig, stru
> current->rseq.event.error = 0;
> force_sigsegv(sig);
> }
> +
> + /*
> + * In legacy mode, force the update of IDs before returning to user
> + * space to stay compatible.
> + */
> + if (!rseq_optimized(current))
> + rseq_force_update();
> }
>
> /*
> @@ -404,66 +416,19 @@ static bool rseq_reset_ids(void)
> /* The original rseq structure size (including padding) is 32 bytes. */
> #define ORIG_RSEQ_SIZE 32
>
> -/*
> - * sys_rseq - setup restartable sequences for caller thread.
> - */
> -SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig)
> +static long rseq_register(struct rseq __user * rseq, u32 rseq_len, int flags, u32 sig)
> {
> + bool optimized = IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && rseq_len > ORIG_RSEQ_SIZE;
> u32 rseqfl = 0;
>
> - if (flags & RSEQ_FLAG_UNREGISTER) {
> - if (flags & ~RSEQ_FLAG_UNREGISTER)
> - return -EINVAL;
> - /* Unregister rseq for current thread. */
> - if (current->rseq.usrptr != rseq || !current->rseq.usrptr)
> - return -EINVAL;
> - if (rseq_len != current->rseq.len)
> - return -EINVAL;
> - if (current->rseq.sig != sig)
> - return -EPERM;
> - if (!rseq_reset_ids())
> - return -EFAULT;
> - rseq_reset(current);
> - return 0;
> - }
> -
> - if (unlikely(flags & ~(RSEQ_FLAG_SLICE_EXT_DEFAULT_ON)))
> - return -EINVAL;
> -
> - if (current->rseq.usrptr) {
> - /*
> - * If rseq is already registered, check whether
> - * the provided address differs from the prior
> - * one.
> - */
> - if (current->rseq.usrptr != rseq || rseq_len != current->rseq.len)
> - return -EINVAL;
> - if (current->rseq.sig != sig)
> - return -EPERM;
> - /* Already registered. */
> - return -EBUSY;
> - }
> -
> - /*
> - * If there was no rseq previously registered, ensure the provided rseq
> - * is properly aligned, as communcated to user-space through the ELF
> - * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq
> - * size, the required alignment is the original struct rseq alignment.
> - *
> - * The rseq_len is required to be greater or equal to the original rseq
> - * size. In order to be valid, rseq_len is either the original rseq size,
> - * or large enough to contain all supported fields, as communicated to
> - * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE.
> - */
> - if (rseq_len < ORIG_RSEQ_SIZE ||
> - (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) ||
> - (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) ||
> - rseq_len < offsetof(struct rseq, end))))
> - return -EINVAL;
> if (!access_ok(rseq, rseq_len))
> return -EFAULT;
>
> - if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) {
> + /*
> + * The optimized check disables time slice extensions for legacy
> + * registrations.
> + */
> + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION) && optimized) {
> rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE;
> if (rseq_slice_extension_enabled() &&
> (flags & RSEQ_FLAG_SLICE_EXT_DEFAULT_ON))
> @@ -485,7 +450,15 @@ SYSCALL_DEFINE4(rseq, struct rseq __user
> unsafe_put_user(RSEQ_CPU_ID_UNINITIALIZED, &rseq->cpu_id, efault);
> unsafe_put_user(0U, &rseq->node_id, efault);
> unsafe_put_user(0U, &rseq->mm_cid, efault);
> - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
> +
> + /*
> + * All fields past mm_cid are only valid for non-legacy registrations
> + * which register with rseq_len > ORIG_RSEQ_SIZE.
> + */
> + if (optimized) {
> + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION))
> + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
> + }
> }
>
> /*
> @@ -501,11 +474,11 @@ SYSCALL_DEFINE4(rseq, struct rseq __user
> #endif
>
> /*
> - * If rseq was previously inactive, and has just been
> - * registered, ensure the cpu_id_start and cpu_id fields
> - * are updated before returning to user-space.
> + * Ensure the cpu_id_start and cpu_id fields are updated before
> + * returning to user-space.
> */
> current->rseq.event.has_rseq = true;
> + current->rseq.event.optimized = optimized;
> rseq_force_update();
> return 0;
>
> @@ -513,6 +486,86 @@ SYSCALL_DEFINE4(rseq, struct rseq __user
> return -EFAULT;
> }
>
> +static long rseq_unregister(struct rseq __user * rseq, u32 rseq_len, int flags, u32 sig)
> +{
> + if (flags & ~RSEQ_FLAG_UNREGISTER)
> + return -EINVAL;
> + if (current->rseq.usrptr != rseq || !current->rseq.usrptr)
> + return -EINVAL;
> + if (rseq_len != current->rseq.len)
> + return -EINVAL;
> + if (current->rseq.sig != sig)
> + return -EPERM;
> + if (!rseq_reset_ids())
> + return -EFAULT;
> + rseq_reset(current);
> + return 0;
> +}
> +
> +static long rseq_reregister(struct rseq __user * rseq, u32 rseq_len, u32 sig)
> +{
> + /*
> + * If rseq is already registered, check whether the provided address
> + * differs from the prior one.
> + */
> + if (current->rseq.usrptr != rseq || rseq_len != current->rseq.len)
> + return -EINVAL;
> + if (current->rseq.sig != sig)
> + return -EPERM;
> + /* Already registered. */
> + return -EBUSY;
> +}
> +
> +static bool rseq_length_valid(struct rseq __user *rseq, unsigned int rseq_len)
> +{
> + if (rseq_len < ORIG_RSEQ_SIZE)
> + return false;
> +
> + /*
> + * Ensure the provided rseq is properly aligned, as communicated to
> + * user-space through the ELF auxiliary vector AT_RSEQ_ALIGN. If
> + * rseq_len is the original rseq size, the required alignment is the
> + * original struct rseq alignment.
> + *
> + * The rseq_len is required to be greater or equal than the original
> + * rseq size.
> + *
> + * In order to be valid, rseq_len is either the original rseq size, or
> + * large enough to contain all supported fields, as communicated to
> + * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE.
> + */
> + if (rseq_len < ORIG_RSEQ_SIZE)
> + return false;
> +
> + if (rseq_len == ORIG_RSEQ_SIZE)
> + return IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE);
> +
> + return IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) &&
> + rseq_len >= offsetof(struct rseq, end);
> +}
> +
> +#define RSEQ_FLAGS_SUPPORTED (RSEQ_FLAG_SLICE_EXT_DEFAULT_ON)
> +
> +/*
> + * sys_rseq - Register or unregister restartable sequences for the caller thread.
> + */
> +SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig)
> +{
> + if (flags & RSEQ_FLAG_UNREGISTER)
> + return rseq_unregister(rseq, rseq_len, flags, sig);
> +
> + if (unlikely(flags & ~RSEQ_FLAGS_SUPPORTED))
> + return -EINVAL;
> +
> + if (current->rseq.usrptr)
> + return rseq_reregister(rseq, rseq_len, sig);
> +
> + if (!rseq_length_valid(rseq, rseq_len))
> + return -EINVAL;
> +
> + return rseq_register(rseq, rseq_len, flags, sig);
> +}
> +
> #ifdef CONFIG_RSEQ_SLICE_EXTENSION
> struct slice_timer {
> struct hrtimer timer;
> @@ -713,6 +766,8 @@ int rseq_slice_extension_prctl(unsigned
> return -ENOTSUPP;
> if (!current->rseq.usrptr)
> return -ENXIO;
> + if (!current->rseq.event.optimized)
> + return -ENOTSUPP;
>
> /* No change? */
> if (enable == !!current->rseq.slice.state.enabled)
> --- a/kernel/sched/membarrier.c
> +++ b/kernel/sched/membarrier.c
> @@ -199,7 +199,16 @@ static void ipi_rseq(void *info)
> * is negligible.
> */
> smp_mb();
> - rseq_sched_switch_event(current);
> + /*
> + * Legacy mode requires that IDs are written and the critical section is
> + * evaluated. Optimized mode handles the critical section and IDs are
> + * only updated if they change as a consequence of preemption after
> + * return from this IPI.
> + */
> + if (rseq_optimized(current))
> + rseq_sched_switch_event(current);
> + else
> + rseq_force_update();
> }
>
> static void ipi_sync_rq_state(void *info)
> --- a/Documentation/userspace-api/rseq.rst
> +++ b/Documentation/userspace-api/rseq.rst
> @@ -24,6 +24,80 @@ Quick access to CPU number, node ID
> Allows to implement per CPU data efficiently. Documentation is in code and
> selftests. :(
>
> +Optimized RSEQ V2
> +-----------------
> +
> +On architectures which utilize the generic entry code and generic TIF bits
> +the kernel supports runtime optimizations for RSEQ, which also enable
> +enhanced features like scheduler time slice extensions.
> +
> +To enable them a task has to register the RSEQ region with at least the
> +length advertised by getauxval(AT_RSEQ_FEATURE_SIZE).
> +
> +If existing binaries register with RSEQ_ORIG_SIZE (32 bytes), the kernel
> +keeps the legacy low performance mode enabled to fulfil the expectations
> +existing users regarding the original RSEQ implementation behaviour.
> +
> +The following table documents the ABI and behavioral guarantees of the
> +legacy and the optimized V2 mode.
> +
> +.. list-table:: RSEQ modes
> + :header-rows: 1
> +
> + * - Nr
> + - What
> + - Legacy
> + - Optimized V2
> + * - 1
> + - The cpu_id_start, cpu_id, node_id and mm_cid fields (User mode read
> + only)
> + - Updated by the kernel unconditionally after each context switch and
> + before signal delivery
> + - Updated by the kernel if and only if they change, i.e. if the task
> + is migrated or mm_cid changes
> + * - 2
> + - The rseq_cs critical section field
> + - Evaluated and handled unconditionally after each context switch and
> + before signal delivery
> + - Evaluated and handled conditionally only when user space was
> + interrupted. Either after being preempted or before signal delivery
> + in the interrupted context.
> + * - 3
> + - Read only fields
> + - No strict enforcement except in debug mode
> + - Strict enforcement
> + * - 4
> + - membarrier(...RSEQ)
> + - All running threads of the process are interrupted and the ID fields
> + are rewritten and eventually active critical sections are aborted
> + before they return to user space. All threads which are scheduled
> + out whether voluntary or not are covered by #1/#2 above.
> + - All running threads of the process are interrupted and eventually
> + active critical sections are aborted before these threads return to
> + user space. The ID fields are only updated if changed as a
> + consequence of the interrupt. All threads which are scheduled out
> + whether voluntary not are covered by #1/#2 above.
> + * - 5
> + - Time slice extensions
> + - Not supported
> + - Supported
> +
> +The legacy mode is obviously less performant as it does unconditional
> +updates and critical section checks even if not strictly required by the
> +ABI contract. That can't be changed anymore as some users depend on that
> +observed behavior, which in turn enables them to violate the ABI and
> +overwrite the cpu_id_start field for their own purposes. This is obviously
> +discouraged as it renders RSEQ incompatible with the intended usage and
> +breaks the expectation of other libraries in the same application.
> +
> +The ABI compliant optimized mode, which respects the read only fields, does
> +not require unconditional updates and therefore is way more performant. The
> +kernel validates the read only fields for compliance. If user space
> +modifies them, the process is killed. Compliant usage allows multiple
> +libraries in the same application to benefit from the RSEQ functionality
> +without disturbing each other.
> +
> +
> Scheduler time slice extensions
> -------------------------------
>
> @@ -37,7 +111,8 @@ scheduled out inside of the critical sec
>
> * Enabled at boot time (default is enabled)
>
> - * A rseq userspace pointer has been registered for the thread
> + * A rseq userspace pointer has been registered for the thread in
> + optimized V2 mode
>
> The thread has to enable the functionality via prctl(2)::
>
^ permalink raw reply
* Re: [PATCH] crypto: atmel-sha204a - drop hwrng quality reduction for ATSHA204A
From: Ard Biesheuvel @ 2026-04-28 5:58 UTC (permalink / raw)
To: Thorsten Blum, Herbert Xu, David S. Miller, Nicolas Ferre,
Alexandre Belloni, Claudiu Beznea, Marek Behún,
Linus Walleij
Cc: stable, linux-crypto, linux-arm-kernel, linux-kernel
In-Reply-To: <20260427124030.315590-3-thorsten.blum@linux.dev>
Hi Thorsten,
On Mon, 27 Apr 2026, at 14:40, Thorsten Blum wrote:
> Commit 8006aff15516 ("crypto: atmel-sha204a - Set hwrng quality to
> lowest possible") reduced the hwrng quality to 1 based on a review by
> Bill Cox [1]. However, despite its title, the review only tested the
> ATSHA204, not the ATSHA204A.
>
> In the same thread, Atmel engineer Landon Cox wrote "this behavior has
> been eliminated entirely"[2] in the ATSHA204A and "this problem does not
> affect the ATECC108 or the ATECC108A (or the ATSHA204A)"[3].
>
> According to the official ATSHA204A datasheet [4], the device contains a
> high-quality hardware RNG that combines its output with an internal seed
> value stored in EEPROM or SRAM to generate random numbers. The device
> also implements all security functions using SHA-256, and the driver
> uses the chip's Random command in seed-update mode.
>
> Keep 'quality = 1' for ATSHA204, but drop the explicit hwrng quality
> reduction for ATSHA204A and fall back to the hwrng core default.
>
Interesting! Thanks for digging this up.
> [1]
> https://www.metzdowd.com/pipermail/cryptography/2014-December/023858.html
> [2]
> https://www.metzdowd.com/pipermail/cryptography/2014-December/023852.html
> [3]
> https://www.metzdowd.com/pipermail/cryptography/2014-December/023886.html
> [4]
> https://ww1.microchip.com/downloads/en/DeviceDoc/ATSHA204A-Data-Sheet-40002025A.pdf
>
> Fixes: 8006aff15516 ("crypto: atmel-sha204a - Set hwrng quality to
> lowest possible")
> Cc: stable@vger.kernel.org
> Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
> ---
> drivers/crypto/atmel-sha204a.c | 40 ++++++++++++++++++----------------
> 1 file changed, 21 insertions(+), 19 deletions(-)
>
> diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
> index dbb39ed0cea1..df69fb190e52 100644
> --- a/drivers/crypto/atmel-sha204a.c
> +++ b/drivers/crypto/atmel-sha204a.c
> @@ -19,6 +19,25 @@
> #include <linux/workqueue.h>
> #include "atmel-i2c.h"
>
> +enum atmel_sha204a_variant {
> + ATSHA204 = 1,
> + ATSHA204A,
> +};
> +
I agree that setting quality to '1' is only appropriate for the ATSHA204
but this looks a bit clunky to me.
Can we retain the comment here that you deleted below, and add
something like
static const unsigned short atsha204_quality = 1;
> +static const struct of_device_id atmel_sha204a_dt_ids[] __maybe_unused = {
> + { .compatible = "atmel,atsha204", .data = (void *)ATSHA204 },
> + { .compatible = "atmel,atsha204a", .data = (void *)ATSHA204A },
> + { /* sentinel */ }
> +};
> +MODULE_DEVICE_TABLE(of, atmel_sha204a_dt_ids);
> +
> +static const struct i2c_device_id atmel_sha204a_id[] = {
> + { .name = "atsha204", .driver_data = ATSHA204 },
> + { .name = "atsha204a", .driver_data = ATSHA204A },
> + { /* sentinel */ }
> +};
> +MODULE_DEVICE_TABLE(i2c, atmel_sha204a_id);
> +
Then, move these back to the old location, and point .data /
.driver_data to &atsha204_quality for atsha204 only.
> static void atmel_sha204a_rng_done(struct atmel_i2c_work_data *work_data,
> void *areq, int status)
> {
> @@ -171,11 +190,8 @@ static int atmel_sha204a_probe(struct i2c_client *client)
> i2c_priv->hwrng.name = dev_name(&client->dev);
> i2c_priv->hwrng.read = atmel_sha204a_rng_read;
>
> - /*
> - * According to review by Bill Cox [1], this HWRNG has very low
> entropy.
> - * [1]
> https://www.metzdowd.com/pipermail/cryptography/2014-December/023858.html
> - */
> - i2c_priv->hwrng.quality = 1;
> + if ((uintptr_t)i2c_get_match_data(client) == ATSHA204)
> + i2c_priv->hwrng.quality = 1;
>
Here you can override the field by dereferencing the match data if it
is non-NULL.
Alternatively, you could store the quality in the device_id structs
directly, but I think this is slightly more idiomatic.
> ret = devm_hwrng_register(&client->dev, &i2c_priv->hwrng);
> if (ret)
> @@ -202,20 +218,6 @@ static void atmel_sha204a_remove(struct i2c_client *client)
> kfree((void *)i2c_priv->hwrng.priv);
> }
>
> -static const struct of_device_id atmel_sha204a_dt_ids[] __maybe_unused = {
> - { .compatible = "atmel,atsha204", },
> - { .compatible = "atmel,atsha204a", },
> - { /* sentinel */ }
> -};
> -MODULE_DEVICE_TABLE(of, atmel_sha204a_dt_ids);
> -
> -static const struct i2c_device_id atmel_sha204a_id[] = {
> - { "atsha204" },
> - { "atsha204a" },
> - { /* sentinel */ }
> -};
> -MODULE_DEVICE_TABLE(i2c, atmel_sha204a_id);
> -
> static struct i2c_driver atmel_sha204a_driver = {
> .probe = atmel_sha204a_probe,
> .remove = atmel_sha204a_remove,
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox