From fc705fecf3a0c9128933cc6db59159c050aaca33 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 21 Jan 2021 14:54:46 +0200 Subject: [PATCH 1/4] perf evlist: Fix id index for heterogeneous systems perf_evlist__set_sid_idx() updates perf_sample_id with the evlist map index, CPU number and TID. It is passed indexes to the evsel's cpu and thread maps, but references the evlist's maps instead. That results in using incorrect CPU numbers on heterogeneous systems. Fix it by using evsel maps. The id index (PERF_RECORD_ID_INDEX) is used by AUX area tracing when in sampling mode. Having an incorrect CPU number causes the trace data to be attributed to the wrong CPU, and can result in decoder errors because the trace data is then associated with the wrong process. Committer notes: Keep the class prefix convention in the function name, switching from perf_evlist__set_sid_idx() to perf_evsel__set_sid_idx(). Fixes: 3c659eedada2fbf9 ("perf tools: Add id index") Signed-off-by: Adrian Hunter Cc: Jin Yao Cc: Jiri Olsa Link: http://lore.kernel.org/lkml/20210121125446.11287-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/evlist.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index cfcdbd7be066..17465d454a0e 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -367,21 +367,13 @@ static struct perf_mmap* perf_evlist__alloc_mmap(struct perf_evlist *evlist, boo return map; } -static void perf_evlist__set_sid_idx(struct perf_evlist *evlist, - struct perf_evsel *evsel, int idx, int cpu, - int thread) +static void perf_evsel__set_sid_idx(struct perf_evsel *evsel, int idx, int cpu, int thread) { struct perf_sample_id *sid = SID(evsel, cpu, thread); sid->idx = idx; - if (evlist->cpus && cpu >= 0) - sid->cpu = evlist->cpus->map[cpu]; - else - sid->cpu = -1; - if (!evsel->system_wide && evlist->threads && thread >= 0) - sid->tid = perf_thread_map__pid(evlist->threads, thread); - else - sid->tid = -1; + sid->cpu = perf_cpu_map__cpu(evsel->cpus, cpu); + sid->tid = perf_thread_map__pid(evsel->threads, thread); } static struct perf_mmap* @@ -500,8 +492,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) return -1; - perf_evlist__set_sid_idx(evlist, evsel, idx, cpu, - thread); + perf_evsel__set_sid_idx(evsel, idx, cpu, thread); } } From 9c880c24cb0db49d6e62e6d882df1470b0be8038 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 21 Jan 2021 00:18:38 +0800 Subject: [PATCH 2/4] perf metricgroup: Fix for metrics containing duration_time Metrics containing duration_time cause a segfault: $ perf stat -v -M L1D_Cache_Fill_BW sleep 1 Using CPUID GenuineIntel-6-3D-4 metric expr 64 * l1d.replacement / 1000000000 / duration_time for L1D_Cache_Fill_BW found event duration_time found event l1d.replacement adding {l1d.replacement}:W,duration_time l1d.replacement -> cpu/umask=0x1,(null)=0x1e8483,event=0x51/ Segmentation fault $ In commit c2337d67199a1ea1 ("perf metricgroup: Fix metrics using aliases covering multiple PMUs"), the logic in find_evsel_group() when iter'ing events was changed to not only select events in same group, but also for aliased PMUs. Checking whether events were for aliased PMUs was done by comparing the event PMU name. This was not safe for duration_time event, which has no associated PMU (and no PMU name), so fix by checking if the event PMU name is set also. Committer testing: Reproduced the bug, then, on a: $ grep -m1 ^'model name' /proc/cpuinfo model name : Intel(R) Core(TM) i7-8650U CPU @ 1.90GHz $ We now get: $ perf stat -M L1D_Cache_Fill_BW sleep 1 Performance counter stats for 'sleep 1': 4,141 l1d.replacement:u 1,001,285,107 ns duration_time:u 1.001285107 seconds time elapsed 0.000000000 seconds user 0.001119000 seconds sys $ Detais from -v: Using CPUID GenuineIntel-6-8E-A metric expr 64 * l1d.replacement / 1000000000 / duration_time for L1D_Cache_Fill_BW found event duration_time found event l1d.replacement adding {l1d.replacement}:W,duration_time l1d.replacement -> cpu/(null)=0x1e8483,umask=0x1,event=0x51/ Control descriptor is not initialized Warning: kernel.perf_event_paranoid=2, trying to fall back to excluding kernel and hypervisor samples Warning: kernel.perf_event_paranoid=2, trying to fall back to excluding kernel and hypervisor samples l1d.replacement:u: 4592 612201 612201 duration_time:u: 1001478621 1001478621 1001478621 Fixes: c2337d67199a1ea1 ("perf metricgroup: Fix metrics using aliases covering multiple PMUs") Reported-by: Joakim Zhang Signed-off-by: John Garry Tested-by: Arnaldo Carvalho de Melo Tested-by: Jiri Olsa Acked-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linuxarm@openeuler.org Link: https://lore.kernel.org/r/1611159518-226883-1-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index ee94d3e8dd65..8cb164ad06c1 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -162,6 +162,14 @@ static bool contains_event(struct evsel **metric_events, int num_events, return false; } +static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2) +{ + if (!ev1->pmu_name || !ev2->pmu_name) + return false; + + return !strcmp(ev1->pmu_name, ev2->pmu_name); +} + /** * Find a group of events in perf_evlist that correspond to those from a parsed * metric expression. Note, as find_evsel_group is called in the same order as @@ -280,8 +288,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, */ if (!has_constraint && ev->leader != metric_events[i]->leader && - !strcmp(ev->leader->pmu_name, - metric_events[i]->leader->pmu_name)) + evsel_same_pmu(ev->leader, metric_events[i]->leader)) break; if (!strcmp(metric_events[i]->name, ev->name)) { set_bit(ev->idx, evlist_used); From 3d6e79ee9e8f8c6604312382c2be1d1bd1cffc9e Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 19 Jan 2021 18:04:15 +0800 Subject: [PATCH 3/4] perf metricgroup: Fix system PMU metrics Joakim reports that getting "perf stat" for multiple system PMU metrics segfaults: $ perf stat -a -I 1000 -M imx8mm_ddr_write.all,imx8mm_ddr_write.all Segmentation fault $ While the same works without issue for a single metric. The logic in metricgroup__add_metric_sys_event_iter() is broken, in that add_metric() @m argument should be NULL for each new metric. Fix by not passing a holder for that, and rather make local in metricgroup__add_metric_sys_event_iter(). Fixes: be335ec28efa ("perf metricgroup: Support adding metrics for system PMUs") Reported-by: Joakim Zhang Signed-off-by: John Garry Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linuxarm@openeuler.org Link: https://lore.kernel.org/r/1611050655-44020-1-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 8cb164ad06c1..e6d3452031e5 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -773,7 +773,6 @@ int __weak arch_get_runtimeparam(struct pmu_event *pe __maybe_unused) struct metricgroup_add_iter_data { struct list_head *metric_list; const char *metric; - struct metric **m; struct expr_ids *ids; int *ret; bool *has_match; @@ -1065,12 +1064,13 @@ static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe, void *data) { struct metricgroup_add_iter_data *d = data; + struct metric *m = NULL; int ret; if (!match_pe_metric(pe, d->metric)) return 0; - ret = add_metric(d->metric_list, pe, d->metric_no_group, d->m, NULL, d->ids); + ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids); if (ret) return ret; @@ -1121,7 +1121,6 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group, .metric_list = &list, .metric = metric, .metric_no_group = metric_no_group, - .m = &m, .ids = &ids, .has_match = &has_match, .ret = &ret, From 8adc0a06d68a2e433b960377e515e7a6b19b429f Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Wed, 9 Dec 2020 08:58:28 +0800 Subject: [PATCH 4/4] perf script: Fix overrun issue for dynamically-allocated PMU type number When unpacking the event which is from dynamic PMU, the array output[OUTPUT_TYPE_MAX] may be overrun. For example, type number of SKL uncore_imc is 10, but OUTPUT_TYPE_MAX is 7 now (OUTPUT_TYPE_MAX = PERF_TYPE_MAX + 1). /* In builtin-script.c */ process_event() { unsigned int type = output_type(attr->type); if (output[type].fields == 0) return; } output[10] is overrun. Create a type OUTPUT_TYPE_OTHER for dynamic PMU events, then output_type(attr->type) will return OUTPUT_TYPE_OTHER here. Note that if PERF_TYPE_MAX ever changed, then there would be a conflict between old perf.data files that had a dynamicaliy allocated PMU number that would then be the same as a fixed PERF_TYPE. Example: # perf record --switch-events -C 0 -e "{cpu-clock,uncore_imc/data_reads/,uncore_imc/data_writes/}:SD" -a -- sleep 1 # perf script Before: swapper 0 [000] 1479253.987551: 277766 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1479253.987797: 246709 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1479253.988127: 329883 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1479253.988273: 146393 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1479253.988523: 249977 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1479253.988877: 354090 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1479253.989023: 145940 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1479253.989383: 359856 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1479253.989523: 140082 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) After: swapper 0 [000] 1397040.402011: 272384 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1397040.402011: 5396 uncore_imc/data_reads/: swapper 0 [000] 1397040.402011: 967 uncore_imc/data_writes/: swapper 0 [000] 1397040.402259: 249153 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1397040.402259: 7231 uncore_imc/data_reads/: swapper 0 [000] 1397040.402259: 1297 uncore_imc/data_writes/: swapper 0 [000] 1397040.402508: 249108 cpu-clock: ffffffff9d4ddb6f cpuidle_enter_state+0xdf ([kernel.kallsyms]) swapper 0 [000] 1397040.402508: 5333 uncore_imc/data_reads/: swapper 0 [000] 1397040.402508: 1008 uncore_imc/data_writes/: Signed-off-by: Jin Yao Acked-by: Adrian Hunter Acked-by: Jiri Olsa Cc: Peter Zijlstra Cc: Kan Liang Cc: Andi Kleen Cc: Alexander Shishkin Cc: Ingo Molnar Link: https://lore.kernel.org/r/20201209005828.21302-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index edacfa98d073..42dad4a0f8cf 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -186,6 +186,7 @@ struct output_option { enum { OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX, + OUTPUT_TYPE_OTHER, OUTPUT_TYPE_MAX }; @@ -283,6 +284,18 @@ static struct { .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, + + [OUTPUT_TYPE_OTHER] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, }; struct evsel_script { @@ -343,8 +356,11 @@ static inline int output_type(unsigned int type) case PERF_TYPE_SYNTH: return OUTPUT_TYPE_SYNTH; default: - return type; + if (type < PERF_TYPE_MAX) + return type; } + + return OUTPUT_TYPE_OTHER; } static inline unsigned int attr_type(unsigned int type)