From 05673c42f73965c6381ab986b4dd2145700e6a0c Mon Sep 17 00:00:00 2001 From: Zixian Cai Date: Fri, 9 Aug 2024 08:01:36 +0000 Subject: perf script python: Add the 'ins_lat' field to event handler For example, when using the Alder Lake PMU memory load event, the instruction latency is stored in 'ins_lat', while the cache latency is stored in 'weight'. This patch reports the 'ins_lat' field for Python scripting. Committer testing: On a Rocket Lake Refresh Intel machine (14th gen): root@number:~# grep -m1 'model name' /proc/cpuinfo model name : Intel(R) Core(TM) i7-14700K root@number:~# perf mem record -a sleep 5 Memory events are enabled on a subset of CPUs: 16-27 [ perf record: Woken up 85 times to write data ] [ perf record: Captured and wrote 41.236 MB perf.data (191390 samples) ] root@number:~# perf evlist -v cpu_atom/mem-loads,ldlat=30/P: type: 10 (cpu_atom), size: 136, config: 0x5d0 (mem-loads), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ADDR|CPU|PERIOD|IDENTIFIER|DATA_SRC|WEIGHT_STRUCT, read_format: ID|LOST, disabled: 1, inherit: 1, freq: 1, precise_ip: 3, sample_id_all: 1, { bp_addr, config1 }: 0x1f cpu_atom/mem-stores/P: type: 10 (cpu_atom), size: 136, config: 0x6d0 (mem-stores), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ADDR|CPU|PERIOD|IDENTIFIER|DATA_SRC|WEIGHT_STRUCT, read_format: ID|LOST, disabled: 1, inherit: 1, freq: 1, precise_ip: 3, sample_id_all: 1 dummy:u: type: 1 (software), size: 136, config: 0x9 (PERF_COUNT_SW_DUMMY), { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|ADDR|CPU|IDENTIFIER|DATA_SRC|WEIGHT_STRUCT, read_format: ID|LOST, inherit: 1, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, mmap_data: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1 root@number:~# Now generate a python script to then dump the dictionary that now needs to have that 'ins_lat' field: root@number:~# perf script --gen python generated Python script: perf-script.py root@number:~# vim perf-script.py root@number:~# perf script -s perf-script.py | head -40 in trace_begin in trace_end root@number:~# vim perf-script.py Reviewed-by: Adrian Hunter Signed-off-by: Zixian Cai Cc: Alexander Shishkin Cc: Ben Gainey Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Paran Lee Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240809080137.3590148-1-fzczx123@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/scripting-engines/trace-event-python.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'tools/perf/util/scripting-engines/trace-event-python.c') diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index fb00f3ad6815..6971dd6c231f 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -888,6 +888,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, set_sample_read_in_dict(dict_sample, sample, evsel); pydict_set_item_string_decref(dict_sample, "weight", PyLong_FromUnsignedLongLong(sample->weight)); + pydict_set_item_string_decref(dict_sample, "ins_lat", + PyLong_FromUnsignedLong(sample->ins_lat)); pydict_set_item_string_decref(dict_sample, "transaction", PyLong_FromUnsignedLongLong(sample->transaction)); set_sample_datasrc_in_dict(dict_sample, sample); @@ -1317,7 +1319,7 @@ static void python_export_sample_table(struct db_export *dbe, struct tables *tables = container_of(dbe, struct tables, dbe); PyObject *t; - t = tuple_new(27); + t = tuple_new(28); tuple_set_d64(t, 0, es->db_id); tuple_set_d64(t, 1, es->evsel->db_id); @@ -1346,6 +1348,7 @@ static void python_export_sample_table(struct db_export *dbe, tuple_set_s32(t, 24, es->sample->flags); tuple_set_d64(t, 25, es->sample->id); tuple_set_d64(t, 26, es->sample->stream_id); + tuple_set_u32(t, 27, es->sample->ins_lat); call_object(tables->sample_handler, t, "sample_table"); -- cgit From 4bef6168c145852cebefe2f0bd78f9aaeba52843 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 5 Sep 2024 08:07:55 -0700 Subject: perf script python: Avoid buffer overflow in python PEBS register interface Running a script that processes PEBS records gives buffer overflows in valgrind. The problem is that the allocation of the register string doesn't include the terminating 0 byte. Fix this. I also replaced the very magic "28" with a more reasonable larger buffer that should fit all registers. There's no need to conserve memory here. ==2106591== Memcheck, a memory error detector ==2106591== Copyright (C) 2002-2022, and GNU GPL'd, by Julian Seward et al. ==2106591== Using Valgrind-3.22.0 and LibVEX; rerun with -h for copyright info ==2106591== Command: ../perf script -i tcall.data gcov.py tcall.gcov ==2106591== ==2106591== Invalid write of size 1 ==2106591== at 0x713354: regs_map (trace-event-python.c:748) ==2106591== by 0x7134EB: set_regs_in_dict (trace-event-python.c:784) ==2106591== by 0x713E58: get_perf_sample_dict (trace-event-python.c:940) ==2106591== by 0x716327: python_process_general_event (trace-event-python.c:1499) ==2106591== by 0x7164E1: python_process_event (trace-event-python.c:1531) ==2106591== by 0x44F9AF: process_sample_event (builtin-script.c:2549) ==2106591== by 0x6294DC: evlist__deliver_sample (session.c:1534) ==2106591== by 0x6296D0: machines__deliver_event (session.c:1573) ==2106591== by 0x629C39: perf_session__deliver_event (session.c:1655) ==2106591== by 0x625830: ordered_events__deliver_event (session.c:193) ==2106591== by 0x630B23: do_flush (ordered-events.c:245) ==2106591== by 0x630E7A: __ordered_events__flush (ordered-events.c:324) ==2106591== Address 0x7186fe0 is 0 bytes after a block of size 0 alloc'd ==2106591== at 0x484280F: malloc (vg_replace_malloc.c:442) ==2106591== by 0x7134AD: set_regs_in_dict (trace-event-python.c:780) ==2106591== by 0x713E58: get_perf_sample_dict (trace-event-python.c:940) ==2106591== by 0x716327: python_process_general_event (trace-event-python.c:1499) ==2106591== by 0x7164E1: python_process_event (trace-event-python.c:1531) ==2106591== by 0x44F9AF: process_sample_event (builtin-script.c:2549) ==2106591== by 0x6294DC: evlist__deliver_sample (session.c:1534) ==2106591== by 0x6296D0: machines__deliver_event (session.c:1573) ==2106591== by 0x629C39: perf_session__deliver_event (session.c:1655) ==2106591== by 0x625830: ordered_events__deliver_event (session.c:193) ==2106591== by 0x630B23: do_flush (ordered-events.c:245) ==2106591== by 0x630E7A: __ordered_events__flush (ordered-events.c:324) ==2106591== ==2106591== Invalid read of size 1 ==2106591== at 0x484B6C6: strlen (vg_replace_strmem.c:502) ==2106591== by 0x555D494: PyUnicode_FromString (unicodeobject.c:1899) ==2106591== by 0x7134F7: set_regs_in_dict (trace-event-python.c:786) ==2106591== by 0x713E58: get_perf_sample_dict (trace-event-python.c:940) ==2106591== by 0x716327: python_process_general_event (trace-event-python.c:1499) ==2106591== by 0x7164E1: python_process_event (trace-event-python.c:1531) ==2106591== by 0x44F9AF: process_sample_event (builtin-script.c:2549) ==2106591== by 0x6294DC: evlist__deliver_sample (session.c:1534) ==2106591== by 0x6296D0: machines__deliver_event (session.c:1573) ==2106591== by 0x629C39: perf_session__deliver_event (session.c:1655) ==2106591== by 0x625830: ordered_events__deliver_event (session.c:193) ==2106591== by 0x630B23: do_flush (ordered-events.c:245) ==2106591== Address 0x7186fe0 is 0 bytes after a block of size 0 alloc'd ==2106591== at 0x484280F: malloc (vg_replace_malloc.c:442) ==2106591== by 0x7134AD: set_regs_in_dict (trace-event-python.c:780) ==2106591== by 0x713E58: get_perf_sample_dict (trace-event-python.c:940) ==2106591== by 0x716327: python_process_general_event (trace-event-python.c:1499) ==2106591== by 0x7164E1: python_process_event (trace-event-python.c:1531) ==2106591== by 0x44F9AF: process_sample_event (builtin-script.c:2549) ==2106591== by 0x6294DC: evlist__deliver_sample (session.c:1534) ==2106591== by 0x6296D0: machines__deliver_event (session.c:1573) ==2106591== by 0x629C39: perf_session__deliver_event (session.c:1655) ==2106591== by 0x625830: ordered_events__deliver_event (session.c:193) ==2106591== by 0x630B23: do_flush (ordered-events.c:245) ==2106591== by 0x630E7A: __ordered_events__flush (ordered-events.c:324) ==2106591== ==2106591== Invalid write of size 1 ==2106591== at 0x713354: regs_map (trace-event-python.c:748) ==2106591== by 0x713539: set_regs_in_dict (trace-event-python.c:789) ==2106591== by 0x713E58: get_perf_sample_dict (trace-event-python.c:940) ==2106591== by 0x716327: python_process_general_event (trace-event-python.c:1499) ==2106591== by 0x7164E1: python_process_event (trace-event-python.c:1531) ==2106591== by 0x44F9AF: process_sample_event (builtin-script.c:2549) ==2106591== by 0x6294DC: evlist__deliver_sample (session.c:1534) ==2106591== by 0x6296D0: machines__deliver_event (session.c:1573) ==2106591== by 0x629C39: perf_session__deliver_event (session.c:1655) ==2106591== by 0x625830: ordered_events__deliver_event (session.c:193) ==2106591== by 0x630B23: do_flush (ordered-events.c:245) ==2106591== by 0x630E7A: __ordered_events__flush (ordered-events.c:324) ==2106591== Address 0x7186fe0 is 0 bytes after a block of size 0 alloc'd ==2106591== at 0x484280F: malloc (vg_replace_malloc.c:442) ==2106591== by 0x7134AD: set_regs_in_dict (trace-event-python.c:780) ==2106591== by 0x713E58: get_perf_sample_dict (trace-event-python.c:940) ==2106591== by 0x716327: python_process_general_event (trace-event-python.c:1499) ==2106591== by 0x7164E1: python_process_event (trace-event-python.c:1531) ==2106591== by 0x44F9AF: process_sample_event (builtin-script.c:2549) ==2106591== by 0x6294DC: evlist__deliver_sample (session.c:1534) ==2106591== by 0x6296D0: machines__deliver_event (session.c:1573) ==2106591== by 0x629C39: perf_session__deliver_event (session.c:1655) ==2106591== by 0x625830: ordered_events__deliver_event (session.c:193) ==2106591== by 0x630B23: do_flush (ordered-events.c:245) ==2106591== by 0x630E7A: __ordered_events__flush (ordered-events.c:324) ==2106591== ==2106591== Invalid read of size 1 ==2106591== at 0x484B6C6: strlen (vg_replace_strmem.c:502) ==2106591== by 0x555D494: PyUnicode_FromString (unicodeobject.c:1899) ==2106591== by 0x713545: set_regs_in_dict (trace-event-python.c:791) ==2106591== by 0x713E58: get_perf_sample_dict (trace-event-python.c:940) ==2106591== by 0x716327: python_process_general_event (trace-event-python.c:1499) ==2106591== by 0x7164E1: python_process_event (trace-event-python.c:1531) ==2106591== by 0x44F9AF: process_sample_event (builtin-script.c:2549) ==2106591== by 0x6294DC: evlist__deliver_sample (session.c:1534) ==2106591== by 0x6296D0: machines__deliver_event (session.c:1573) ==2106591== by 0x629C39: perf_session__deliver_event (session.c:1655) ==2106591== by 0x625830: ordered_events__deliver_event (session.c:193) ==2106591== by 0x630B23: do_flush (ordered-events.c:245) ==2106591== Address 0x7186fe0 is 0 bytes after a block of size 0 alloc'd ==2106591== at 0x484280F: malloc (vg_replace_malloc.c:442) ==2106591== by 0x7134AD: set_regs_in_dict (trace-event-python.c:780) ==2106591== by 0x713E58: get_perf_sample_dict (trace-event-python.c:940) ==2106591== by 0x716327: python_process_general_event (trace-event-python.c:1499) ==2106591== by 0x7164E1: python_process_event (trace-event-python.c:1531) ==2106591== by 0x44F9AF: process_sample_event (builtin-script.c:2549) ==2106591== by 0x6294DC: evlist__deliver_sample (session.c:1534) ==2106591== by 0x6296D0: machines__deliver_event (session.c:1573) ==2106591== by 0x629C39: perf_session__deliver_event (session.c:1655) ==2106591== by 0x625830: ordered_events__deliver_event (session.c:193) ==2106591== by 0x630B23: do_flush (ordered-events.c:245) ==2106591== by 0x630E7A: __ordered_events__flush (ordered-events.c:324) ==2106591== 73056 total, 29 ignored Signed-off-by: Andi Kleen Cc: Adrian Hunter Cc: Namhyung Kim Link: https://lore.kernel.org/r/20240905151058.2127122-2-ak@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/scripting-engines/trace-event-python.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'tools/perf/util/scripting-engines/trace-event-python.c') diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 6971dd6c231f..d7183134b669 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -762,6 +762,8 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, ch } } +#define MAX_REG_SIZE 128 + static int set_regs_in_dict(PyObject *dict, struct perf_sample *sample, struct evsel *evsel) @@ -769,14 +771,7 @@ static int set_regs_in_dict(PyObject *dict, struct perf_event_attr *attr = &evsel->core.attr; const char *arch = perf_env__arch(evsel__env(evsel)); - /* - * Here value 28 is a constant size which can be used to print - * one register value and its corresponds to: - * 16 chars is to specify 64 bit register in hexadecimal. - * 2 chars is for appending "0x" to the hexadecimal value and - * 10 chars is for register name. - */ - int size = __sw_hweight64(attr->sample_regs_intr) * 28; + int size = (__sw_hweight64(attr->sample_regs_intr) * MAX_REG_SIZE) + 1; char *bf = malloc(size); if (!bf) return -1; -- cgit