From 5d680be3b014d5836ad6c2a8bdda70cce89dbfc8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 17 Sep 2020 15:02:19 +0900 Subject: perf parse-event: Fix cpu map refcounting Like evlist cpu map, evsel's cpu map should have a proper refcount. As it's created with a refcount, we don't need to get an extra count. Thanks to Arnaldo for the simpler suggestion. This, together with the following patch, fixes the following ASAN report: Direct leak of 840 byte(s) in 70 object(s) allocated from: #0 0x7fe36703f628 in malloc (/lib/x86_64-linux-gnu/libasan.so.5+0x107628) #1 0x559fbbf611ca in cpu_map__trim_new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:79 #2 0x559fbbf6229c in perf_cpu_map__new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:237 #3 0x559fbbcc6c6d in __add_event util/parse-events.c:357 #4 0x559fbbcc6c6d in add_event_tool util/parse-events.c:408 #5 0x559fbbcc6c6d in parse_events_add_tool util/parse-events.c:1414 #6 0x559fbbd8474d in parse_events_parse util/parse-events.y:439 #7 0x559fbbcc95da in parse_events__scanner util/parse-events.c:2096 #8 0x559fbbcc95da in __parse_events util/parse-events.c:2141 #9 0x559fbbc2788b in check_parse_id tests/pmu-events.c:406 #10 0x559fbbc2788b in check_parse_id tests/pmu-events.c:393 #11 0x559fbbc2788b in check_parse_fake tests/pmu-events.c:436 #12 0x559fbbc2788b in metric_parse_fake tests/pmu-events.c:553 #13 0x559fbbc27e2d in test_parsing_fake tests/pmu-events.c:599 #14 0x559fbbc27e2d in test_parsing_fake tests/pmu-events.c:574 #15 0x559fbbc0109b in run_test tests/builtin-test.c:410 #16 0x559fbbc0109b in test_and_print tests/builtin-test.c:440 #17 0x559fbbc03e69 in __cmd_test tests/builtin-test.c:695 #18 0x559fbbc03e69 in cmd_test tests/builtin-test.c:807 #19 0x559fbbc691f4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:312 #20 0x559fbbb071a8 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:364 #21 0x559fbbb071a8 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:408 #22 0x559fbbb071a8 in main /home/namhyung/project/linux/tools/perf/perf.c:538 #23 0x7fe366b68cc9 in __libc_start_main ../csu/libc-start.c:308 And I've failed which commit introduced this bug as the code was heavily changed since then. ;-/ Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ian Rogers Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20200917060219.1287863-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 667cbca1547a..4c6b3d287d54 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -353,7 +353,7 @@ __add_event(struct list_head *list, int *idx, const char *cpu_list) { struct evsel *evsel; - struct perf_cpu_map *cpus = pmu ? pmu->cpus : + struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) : cpu_list ? perf_cpu_map__new(cpu_list) : NULL; if (init_attr) @@ -364,7 +364,7 @@ __add_event(struct list_head *list, int *idx, return NULL; (*idx)++; - evsel->core.cpus = perf_cpu_map__get(cpus); + evsel->core.cpus = cpus; evsel->core.own_cpus = perf_cpu_map__get(cpus); evsel->core.system_wide = pmu ? pmu->is_uncore : false; evsel->auto_merge_stats = auto_merge_stats; -- cgit v1.2.3 From 0f1b550e29c1f9522f0a7a11ee2cf95d33a98d79 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 17 Sep 2020 15:02:18 +0900 Subject: perf parse-event: Release cpu_map refcount if evsel alloc failed Signed-off-by: Namhyung Kim Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20200917060219.1287863-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4c6b3d287d54..fbe0d3143353 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -360,8 +360,10 @@ __add_event(struct list_head *list, int *idx, event_attr_init(attr); evsel = evsel__new_idx(attr, *idx); - if (!evsel) + if (!evsel) { + perf_cpu_map__put(cpus); return NULL; + } (*idx)++; evsel->core.cpus = cpus; -- cgit v1.2.3 From dcc81be0fc4e66943041e6e19a5faf8f8704a27e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 17 Sep 2020 13:18:07 -0700 Subject: perf metricgroup: Fix uncore metric expressions A metric like DRAM_BW_Use has on SkylakeX events uncore_imc/cas_count_read/ and uncore_imc/case_count_write/. These events open 6 events per socket with pmu names of uncore_imc_[0-5]. The current metric setup code in find_evsel_group assumes one ID will map to 1 event to be recorded in metric_events. For events with multiple matches, the first event is recorded in metric_events (avoiding matching >1 event with the same name) and the evlist_used updated so that duplicate events aren't removed when the evlist has unused events removed. Before this change: $ /tmp/perf/perf stat -M DRAM_BW_Use -a -- sleep 1 Performance counter stats for 'system wide': 41.14 MiB uncore_imc/cas_count_read/ 1,002,614,251 ns duration_time 1.002614251 seconds time elapsed After this change: $ /tmp/perf/perf stat -M DRAM_BW_Use -a -- sleep 1 Performance counter stats for 'system wide': 157.47 MiB uncore_imc/cas_count_read/ # 0.00 DRAM_BW_Use 126.97 MiB uncore_imc/cas_count_write/ 1,003,019,728 ns duration_time Erroneous duplication introduced in: commit 2440689d62e9 ("perf metricgroup: Remove duped metric group events"). Fixes: ded80bda8bc9 ("perf expr: Migrate expr ids table to a hashmap"). Reported-by: Jin Yao Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Andi Kleen Cc: Andrii Nakryiko Cc: Athira Jajeev Cc: Daniel Borkmann Cc: Jiri Olsa Cc: John Fastabend Cc: KP Singh Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Cc: Yonghong Song Cc: bpf@vger.kernel.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20200917201807.4090224-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 75 ++++++++++++++++++++++++++++++++----------- 1 file changed, 56 insertions(+), 19 deletions(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index ab5030fcfed4..d948a7f910cf 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -150,6 +150,18 @@ static void expr_ids__exit(struct expr_ids *ids) free(ids->id[i].id); } +static bool contains_event(struct evsel **metric_events, int num_events, + const char *event_name) +{ + int i; + + for (i = 0; i < num_events; i++) { + if (!strcmp(metric_events[i]->name, event_name)) + return true; + } + return false; +} + /** * Find a group of events in perf_evlist that correpond to those from a parsed * metric expression. Note, as find_evsel_group is called in the same order as @@ -180,7 +192,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, int i = 0, matched_events = 0, events_to_match; const int idnum = (int)hashmap__size(&pctx->ids); - /* duration_time is grouped separately. */ + /* + * duration_time is always grouped separately, when events are grouped + * (ie has_constraint is false) then ignore it in the matching loop and + * add it to metric_events at the end. + */ if (!has_constraint && hashmap__find(&pctx->ids, "duration_time", (void **)&val_ptr)) events_to_match = idnum - 1; @@ -207,23 +223,20 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, sizeof(struct evsel *) * idnum); current_leader = ev->leader; } - if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) { - if (has_constraint) { - /* - * Events aren't grouped, ensure the same event - * isn't matched from two groups. - */ - for (i = 0; i < matched_events; i++) { - if (!strcmp(ev->name, - metric_events[i]->name)) { - break; - } - } - if (i != matched_events) - continue; - } + /* + * Check for duplicate events with the same name. For example, + * uncore_imc/cas_count_read/ will turn into 6 events per socket + * on skylakex. Only the first such event is placed in + * metric_events. If events aren't grouped then this also + * ensures that the same event in different sibling groups + * aren't both added to metric_events. + */ + if (contains_event(metric_events, matched_events, ev->name)) + continue; + /* Does this event belong to the parse context? */ + if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) metric_events[matched_events++] = ev; - } + if (matched_events == events_to_match) break; } @@ -239,7 +252,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, } if (matched_events != idnum) { - /* Not whole match */ + /* Not a whole match */ return NULL; } @@ -247,8 +260,32 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, for (i = 0; i < idnum; i++) { ev = metric_events[i]; - ev->metric_leader = ev; + /* Don't free the used events. */ set_bit(ev->idx, evlist_used); + /* + * The metric leader points to the identically named event in + * metric_events. + */ + ev->metric_leader = ev; + /* + * Mark two events with identical names in the same group (or + * globally) as being in use as uncore events may be duplicated + * for each pmu. Set the metric leader of such events to be the + * event that appears in metric_events. + */ + evlist__for_each_entry_continue(perf_evlist, ev) { + /* + * If events are grouped then the search can terminate + * when then group is left. + */ + if (!has_constraint && + ev->leader != metric_events[i]->leader) + break; + if (!strcmp(metric_events[i]->name, ev->name)) { + set_bit(ev->idx, evlist_used); + ev->metric_leader = metric_events[i]; + } + } } return metric_events[0]; -- cgit v1.2.3 From 6fcd5ddc3b1467b3586972ef785d0d926ae4cdf4 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 28 Sep 2020 22:11:35 +0200 Subject: perf python scripting: Fix printable strings in python3 scripts Hagen reported broken strings in python3 tracepoint scripts: make PYTHON=python3 perf record -e sched:sched_switch -a -- sleep 5 perf script --gen-script py perf script -s ./perf-script.py [..] sched__sched_switch 7 563231.759525792 0 swapper prev_comm=bytearray(b'swapper/7\x00\x00\x00\x00\x00\x00\x00'), prev_pid=0, prev_prio=120, prev_state=, next_comm=bytearray(b'mutex-thread-co\x00'), The problem is in the is_printable_array function that does not take the zero byte into account and claim such string as not printable, so the code will create byte array instead of string. Committer testing: After this fix: sched__sched_switch 3 484522.497072626 1158680 kworker/3:0-eve prev_comm=kworker/3:0, prev_pid=1158680, prev_prio=120, prev_state=I, next_comm=swapper/3, next_pid=0, next_prio=120 Sample: {addr=0, cpu=3, datasrc=84410401, datasrc_decode=N/A|SNP N/A|TLB N/A|LCK N/A, ip=18446744071841817196, period=1, phys_addr=0, pid=1158680, tid=1158680, time=484522497072626, transaction=0, values=[(0, 0)], weight=0} sched__sched_switch 4 484522.497085610 1225814 perf prev_comm=perf, prev_pid=1225814, prev_prio=120, prev_state=, next_comm=migration/4, next_pid=30, next_prio=0 Sample: {addr=0, cpu=4, datasrc=84410401, datasrc_decode=N/A|SNP N/A|TLB N/A|LCK N/A, ip=18446744071841817196, period=1, phys_addr=0, pid=1225814, tid=1225814, time=484522497085610, transaction=0, values=[(0, 0)], weight=0} Fixes: 249de6e07458 ("perf script python: Fix string vs byte array resolving") Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Tested-by: Hagen Paul Pfeifer Cc: Alexander Shishkin Cc: Mark Rutland Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20200928201135.3633850-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/print_binary.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c index 599a1543871d..13fdc51c61d9 100644 --- a/tools/perf/util/print_binary.c +++ b/tools/perf/util/print_binary.c @@ -50,7 +50,7 @@ int is_printable_array(char *p, unsigned int len) len--; - for (i = 0; i < len; i++) { + for (i = 0; i < len && p[i]; i++) { if (!isprint(p[i]) && !isspace(p[i])) return 0; } -- cgit v1.2.3 From bef69bd7cfc363ab94b84ea29102f3e913ed3c6c Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 7 Oct 2020 17:13:11 +0900 Subject: perf stat: Fix out of bounds CPU map access when handling armv8_pmu events It was reported that 'perf stat' crashed when using with armv8_pmu (CPU) events with the task mode. As 'perf stat' uses an empty cpu map for task mode but armv8_pmu has its own cpu mask, it has confused which map it should use when accessing file descriptors and this causes segfaults: (gdb) bt #0 0x0000000000603fc8 in perf_evsel__close_fd_cpu (evsel=, cpu=) at evsel.c:122 #1 perf_evsel__close_cpu (evsel=evsel@entry=0x716e950, cpu=7) at evsel.c:156 #2 0x00000000004d4718 in evlist__close (evlist=0x70a7cb0) at util/evlist.c:1242 #3 0x0000000000453404 in __run_perf_stat (argc=3, argc@entry=1, argv=0x30, argv@entry=0xfffffaea2f90, run_idx=119, run_idx@entry=1701998435) at builtin-stat.c:929 #4 0x0000000000455058 in run_perf_stat (run_idx=1701998435, argv=0xfffffaea2f90, argc=1) at builtin-stat.c:947 #5 cmd_stat (argc=1, argv=0xfffffaea2f90) at builtin-stat.c:2357 #6 0x00000000004bb888 in run_builtin (p=p@entry=0x9764b8 , argc=argc@entry=4, argv=argv@entry=0xfffffaea2f90) at perf.c:312 #7 0x00000000004bbb54 in handle_internal_command (argc=argc@entry=4, argv=argv@entry=0xfffffaea2f90) at perf.c:364 #8 0x0000000000435378 in run_argv (argcp=, argv=) at perf.c:408 #9 main (argc=4, argv=0xfffffaea2f90) at perf.c:538 To fix this, I simply used the given cpu map unless the evsel actually is not a system-wide event (like uncore events). Fixes: 7736627b865d ("perf stat: Use affinity for closing file descriptors") Reported-by: Wei Li Signed-off-by: Namhyung Kim Tested-by: Barry Song Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20201007081311.1831003-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/evlist.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 2208444ecb44..cfcdbd7be066 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -45,6 +45,9 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, if (!evsel->own_cpus || evlist->has_user_cpus) { perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evlist->cpus); + } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->cpus)) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evlist->cpus); } else if (evsel->cpus != evsel->own_cpus) { perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evsel->own_cpus); -- cgit v1.2.3