From c3537fc251503af18085b8f84126d13743663970 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 1 Oct 2018 12:59:26 -0700 Subject: perf evlist: Move perf_evsel__reset_weak_group into evlist - Move the function from builtin-stat to evlist for reuse - Rename to evlist to match purpose better - Pass the evlist as first argument. - No functional changes Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20181001195927.14211-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 27 +++++++++++++++++++++++++++ tools/perf/util/evlist.h | 3 +++ 2 files changed, 30 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index e88e6f9b1463..668d2a9ef0f4 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1810,3 +1810,30 @@ void perf_evlist__force_leader(struct perf_evlist *evlist) leader->forced_leader = true; } } + +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, + struct perf_evsel *evsel) +{ + struct perf_evsel *c2, *leader; + bool is_open = true; + + leader = evsel->leader; + pr_debug("Weak group for %s/%d failed\n", + leader->name, leader->nr_members); + + /* + * for_each_group_member doesn't work here because it doesn't + * include the first entry. + */ + evlist__for_each_entry(evsel_list, c2) { + if (c2 == evsel) + is_open = false; + if (c2->leader == leader) { + if (is_open) + perf_evsel__close(c2); + c2->leader = c2; + c2->nr_members = 0; + } + } + return leader; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index dc66436add98..9919eed6d15b 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -312,4 +312,7 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); void perf_evlist__force_leader(struct perf_evlist *evlist); +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist, + struct perf_evsel *evsel); + #endif /* __PERF_EVLIST_H */ -- cgit v1.2.3 From ea1fa48c055f833eb25f0c33188feecb7002ada5 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 23 Oct 2018 17:16:16 +0200 Subject: perf stat: Handle different PMU names with common prefix On s390 the CPU Measurement Facility for counters now supports 2 PMUs named cpum_cf (CPU Measurement Facility for counters) and cpum_cf_diag (CPU Measurement Facility for diagnostic counters) for one and the same CPU. Running command [root@s35lp76 perf]# ./perf stat -e tx_c_tend \ -- ~/mytests/cf-tx-events 1 Measuring transactions TX_C_TABORT_NO_SPECIAL: 0 expected:0 TX_C_TABORT_SPECIAL: 0 expected:0 TX_C_TEND: 1 expected:1 TX_NC_TABORT: 11 expected:11 TX_NC_TEND: 1 expected:1 Performance counter stats for '/root/mytests/cf-tx-events 1': 2 tx_c_tend 0.002120091 seconds time elapsed 0.000121000 seconds user 0.002127000 seconds sys [root@s35lp76 perf]# displays output which is unexpected (and wrong): 2 tx_c_tend The test program definitely triggers only one transaction, as shown in line 'TX_C_TEND: 1 expected:1'. This is caused by the following call sequence: pmu_lookup() scans and installs a PMU. +--> pmu_aliases() parses all aliases in directory ...//events/* which are file names. +--> pmu_aliases_parse() Read each file in directory and create an new alias entry. This is done with +--> perf_pmu__new_alias() and +--> __perf_pmu__new_alias() which also check for identical alias names. After pmu_aliases() returns, a complete list of event names for this pmu has been created. Now function pmu_add_cpu_aliases() is called to add the events listed in the json | files to the alias list of the cpu. +--> perf_pmu__find_map() Returns a pointer to the json events. Now function pmu_add_cpu_aliases() scans through all events listed in the JSON files for this CPU. Each json event pmu name is compared with the current PMU being built up and if they mismatch, the json event is added to the current PMUs alias list. To avoid duplicate entries the following comparison is done: if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; if (strncmp(pname, name, strlen(pname))) continue; } The culprit is the strncmp() function. Using current s390 PMU naming, the first PMU is 'cpum_cf' and a long list of events is added, among them 'tx_c_tend' When the second PMU named 'cpum_cf_diag' is added, only one event named 'CF_DIAG' is added by the pmu_aliases() function. Now function pmu_add_cpu_aliases() is invoked for PMU 'cpum_cf_diag'. Since the CPUID string is the same for both PMUs, json file events for PMU named 'cpum_cf' are added to the PMU 'cpm_cf_diag' This happens because the strncmp() actually compares: strncmp("cpum_cf", "cpum_cf_diag", 6); The first parameter is the pmu name taken from the event in the json file. The second parameter is the pmu name of the PMU currently being built. They are different, but the length of the compare only tests the common prefix and this returns 0(true) when it should return false. Now all events for PMU cpum_cf are added to the alias list for pmu cpum_cf_diag. Later on in function parse_events_add_pmu() the event 'tx_c_end' is searched in all available PMUs and found twice, adding it two times to the evsel_list global variable which is the root of all events. This results in a counter value of 2 instead of 1. Output with this patch: [root@s35lp76 perf]# ./perf stat -e tx_c_tend \ -- ~/mytests/cf-tx-events 1 Measuring transactions TX_C_TABORT_NO_SPECIAL: 0 expected:0 TX_C_TABORT_SPECIAL: 0 expected:0 TX_C_TEND: 1 expected:1 TX_NC_TABORT: 11 expected:11 TX_NC_TEND: 1 expected:1 Performance counter stats for '/root/mytests/cf-tx-events 1': 1 tx_c_tend 0.001815365 seconds time elapsed 0.000123000 seconds user 0.001756000 seconds sys [root@s35lp76 perf]# Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Reviewed-by: Sebastien Boisvert Cc: Heiko Carstens Cc: Kan Liang Cc: Martin Schwidefsky Cc: stable@vger.kernel.org Fixes: 292c34c10249 ("perf pmu: Fix core PMU alias list for X86 platform") Link: http://lkml.kernel.org/r/20181023151616.78193-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 7799788f662f..7e49baad304d 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -773,7 +773,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; - if (strncmp(pname, name, strlen(pname))) + if (strcmp(pname, name)) continue; } -- cgit v1.2.3 From 93f8be2799515e01647c5a9b0d17a90a00ebcf82 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 5 Nov 2018 09:35:04 +0200 Subject: perf intel-pt: Add more event information to debug log More event information is useful for debugging, especially MMAP events. Signed-off-by: Adrian Hunter Link: http://lkml.kernel.org/r/20181105073505.8129-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt-decoder/intel-pt-log.c | 5 +++++ tools/perf/util/intel-pt-decoder/intel-pt-log.h | 1 + tools/perf/util/intel-pt.c | 16 +++++++++++++--- 3 files changed, 19 insertions(+), 3 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c index e02bc7b166a0..5e64da270f97 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c @@ -31,6 +31,11 @@ static FILE *f; static char log_name[MAX_LOG_NAME]; bool intel_pt_enable_logging; +void *intel_pt_log_fp(void) +{ + return f; +} + void intel_pt_log_enable(void) { intel_pt_enable_logging = true; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h index 45b64f93f358..cc084937f701 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h @@ -22,6 +22,7 @@ struct intel_pt_pkt; +void *intel_pt_log_fp(void); void intel_pt_log_enable(void); void intel_pt_log_disable(void); void intel_pt_log_set_name(const char *name); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 86cc9a64e982..149ff361ca78 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf, intel_pt_dump(pt, buf, len); } +static void intel_pt_log_event(union perf_event *event) +{ + FILE *f = intel_pt_log_fp(); + + if (!intel_pt_enable_logging || !f) + return; + + perf_event__fprintf(event, f); +} + static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { @@ -2010,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session, event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) err = intel_pt_context_switch(pt, event, sample); - intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n", - perf_event__name(event->header.type), event->header.type, - sample->cpu, sample->time, timestamp); + intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ", + event->header.type, sample->cpu, sample->time, timestamp); + intel_pt_log_event(event); return err; } -- cgit v1.2.3 From f6c23e3b55cb93f32a724f41af8d38888bc2ab6b Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 5 Nov 2018 09:35:05 +0200 Subject: perf intel-pt: Add MTC and CYC timestamps to debug log One cause of decoding errors is un-synchronized side-band data. Timestamps are needed to debug such cases. TSC packet timestamps are logged. Log also MTC and CYC timestamps. Signed-off-by: Adrian Hunter Link: http://lkml.kernel.org/r/20181105073505.8129-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools/perf/util') diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 58f6a9ceb590..4503f3ca45ab 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1474,6 +1474,8 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) decoder->have_calc_cyc_to_tsc = false; intel_pt_calc_cyc_to_tsc(decoder, true); } + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) @@ -1514,6 +1516,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder) decoder->timestamp = timestamp; decoder->timestamp_insn_cnt = 0; + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } /* Walk PSB+ packets when already in sync. */ -- cgit v1.2.3 From 8e88c29b351ed4e09dd63f825f1c8260b0cb0ab3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 23 Sep 2018 17:04:20 +0200 Subject: perf tools: Do not zero sample_id_all for group members Andi reported following malfunction: # perf record -e '{ref-cycles,cycles}:S' -a sleep 1 # perf script non matching sample_id_all That's because we disable sample_id_all bit for non-sampling group members. We can't do that, because it needs to be the same over the whole event list. This patch keeps it untouched again. Reported-by: Andi Kleen Tested-by: Andi Kleen Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180923150420.27327-1-jolsa@kernel.org Fixes: e9add8bac6c6 ("perf evsel: Disable write_backward for leader sampling group events") Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 1 - 1 file changed, 1 deletion(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 6d187059a373..d37bb1566cd9 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -956,7 +956,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->sample_freq = 0; attr->sample_period = 0; attr->write_backward = 0; - attr->sample_id_all = 0; } if (opts->no_samples) -- cgit v1.2.3