| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <E4C04539-9803-4405-A1EA-5D9517682E08@gmail.com>
Date: Sun, 17 Oct 2021 18:03:21 -0300
From: Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>
To: Jiri Olsa <jolsa@...hat.com>, Namhyung Kim <namhyung@...nel.org>
CC: Arnaldo Carvalho de Melo <acme@...nel.org>,
Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
LKML <linux-kernel@...r.kernel.org>,
Andi Kleen <ak@...ux.intel.com>,
Ian Rogers <irogers@...gle.com>,
Stephane Eranian <eranian@...gle.com>
Subject: Re: [PATCH] perf evsel: Fix missing exclude_{host,guest} setting
On October 17, 2021 4:05:46 PM GMT-03:00, Jiri Olsa <jolsa@...hat.com> wrote:
>On Fri, Oct 15, 2021 at 10:12:53PM -0700, Namhyung Kim wrote:
>> The current logic for the perf missing feature has a bug that it can
>> wrongly clear some modifiers like G or H. Actually some PMUs don't
>> support any filtering or exclusion while others do. But we check it
>> as a global feature.
>>
>> For example, the cycles event can have 'G' modifier to enable it only
>> in the guest mode on x86. When you don't run any VMs it'll return 0.
>>
>> # perf stat -a -e cycles:G sleep 1
>>
>> Performance counter stats for 'system wide':
>>
>> 0 cycles:G
>>
>> 1.000721670 seconds time elapsed
>>
>> But when it's used with other pmu events that don't support G modifier,
>> it'll be reset and return non-zero values.
>>
>> # perf stat -a -e cycles:G,msr/tsc/ sleep 1
>>
>> Performance counter stats for 'system wide':
>>
>> 538,029,960 cycles:G
>> 16,924,010,738 msr/tsc/
>>
>> 1.001815327 seconds time elapsed
>>
>> This is because of the missing feature detection logic being global.
>> Add a hashmap to set pmu-specific exclude_host/guest features.
>>
>> Reported-by: Stephane Eranian <eranian@...gle.com>
>> Signed-off-by: Namhyung Kim <namhyung@...nel.org>
>> ---
>> tools/perf/util/evsel.c | 47 +++++++++++++++++++++++++++++++++++------
>> tools/perf/util/evsel.h | 6 ++++++
>> 2 files changed, 47 insertions(+), 6 deletions(-)
>>
>> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
>> index dbfeceb2546c..437a28e769fe 100644
>> --- a/tools/perf/util/evsel.c
>> +++ b/tools/perf/util/evsel.c
>> @@ -1434,6 +1434,10 @@ void evsel__delete(struct evsel *evsel)
>> {
>> evsel__exit(evsel);
>> free(evsel);
>> +
>> + /* just free it for the first evsel */
>> + hashmap__free(perf_missing_features.pmu);
>> + perf_missing_features.pmu = NULL;
>> }
>>
>> void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
>> @@ -1791,6 +1795,23 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
>> return 0;
>> }
>>
>> +#define PMU_HASH_BITS 4
>> +
>> +static size_t pmu_hash(const void *key, void *ctx __maybe_unused)
>> +{
>> + const struct evsel *evsel = key;
>> +
>> + return hash_bits(evsel->core.attr.type, PMU_HASH_BITS);
>> +}
>> +
>> +static bool pmu_equal(const void *key1, const void *key2, void *ctx __maybe_unused)
>> +{
>> + const struct evsel *a = key1;
>> + const struct evsel *b = key2;
>> +
>> + return a->core.attr.type == b->core.attr.type;
>> +}
>> +
>> static void evsel__disable_missing_features(struct evsel *evsel)
>> {
>> if (perf_missing_features.weight_struct) {
>> @@ -1807,8 +1828,14 @@ static void evsel__disable_missing_features(struct evsel *evsel)
>> evsel->open_flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
>> if (perf_missing_features.mmap2)
>> evsel->core.attr.mmap2 = 0;
>> - if (perf_missing_features.exclude_guest)
>> - evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0;
>> + if (perf_missing_features.exclude_guest) {
>> + void *pmu;
>
>could you just pass NULL in here instead of NULL?
ENOPARSE
>
>> +
>> + if (hashmap__find(perf_missing_features.pmu, evsel, &pmu)) {
>> + evsel->core.attr.exclude_guest = 0;
>> + evsel->core.attr.exclude_host = 0;
>> + }
>> + }
>> if (perf_missing_features.lbr_flags)
>> evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
>> PERF_SAMPLE_BRANCH_NO_CYCLES);
>> @@ -1840,6 +1867,9 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
>>
>> bool evsel__detect_missing_features(struct evsel *evsel)
>> {
>> + if (perf_missing_features.pmu == NULL)
>> + perf_missing_features.pmu = hashmap__new(pmu_hash, pmu_equal, NULL);
>> +
>> /*
>> * Must probe features in the order they were added to the
>> * perf_event_attr interface.
>> @@ -1900,10 +1930,15 @@ bool evsel__detect_missing_features(struct evsel *evsel)
>> perf_missing_features.mmap2 = true;
>> pr_debug2_peo("switching off mmap2\n");
>> return true;
>> - } else if (!perf_missing_features.exclude_guest &&
>> - (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) {
>> - perf_missing_features.exclude_guest = true;
>> - pr_debug2_peo("switching off exclude_guest, exclude_host\n");
>> + } else if ((evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) &&
>> + !hashmap__find(perf_missing_features.pmu, evsel, NULL)) {
>> + struct perf_missing_pmu_features pmu_features = { true };
>
>missing new line after declaration
>
>> + hashmap__add(perf_missing_features.pmu, evsel, &pmu_features);
>> +
>> + if (!perf_missing_features.exclude_guest) {
>> + perf_missing_features.exclude_guest = true;
>> + pr_debug2_peo("switching off exclude_guest, exclude_host\n");
>> + }
>> return true;
>> } else if (!perf_missing_features.sample_id_all) {
>> perf_missing_features.sample_id_all = true;
>> diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
>> index 1f7edfa8568a..8dd11c8e022d 100644
>> --- a/tools/perf/util/evsel.h
>> +++ b/tools/perf/util/evsel.h
>> @@ -172,6 +172,12 @@ struct perf_missing_features {
>> bool data_page_size;
>> bool code_page_size;
>> bool weight_struct;
>> +
>> + struct hashmap *pmu;
>> +};
>> +
>> +struct perf_missing_pmu_features {
>> + bool exclude_guest;
>> };
>
>hum, is this really needed? I think you could just pass '1' as value,
>because you care only if the item is hashed, right?
>
>in any case the value is the current stack address of the
> struct perf_missing_pmu_features pmu_features = { true };
>
>so it might as well be just '1' ... I was confused at the beggining
>and looked for the reason of this struct ;-)
>
>we do that already in util/stat.c
>
>jirka
>
>>
>> extern struct perf_missing_features perf_missing_features;
>> --
>> 2.33.0.1079.g6e70778dc9-goog
>>
>
Powered by blists - more mailing lists