From: Ian Rogers <irogers@google.com>
To: "Peter Zijlstra" <peterz@infradead.org>,
"Ingo Molnar" <mingo@redhat.com>,
"Arnaldo Carvalho de Melo" <acme@kernel.org>,
"Mark Rutland" <mark.rutland@arm.com>,
"Alexander Shishkin" <alexander.shishkin@linux.intel.com>,
"Jiri Olsa" <jolsa@kernel.org>,
"Namhyung Kim" <namhyung@kernel.org>,
"Ian Rogers" <irogers@google.com>,
"Adrian Hunter" <adrian.hunter@intel.com>,
"Suzuki K Poulose" <suzuki.poulose@arm.com>,
"Mike Leach" <mike.leach@linaro.org>,
"James Clark" <james.clark@arm.com>,
"Leo Yan" <leo.yan@linaro.org>,
"John Garry" <john.g.garry@oracle.com>,
"Will Deacon" <will@kernel.org>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Darren Hart" <dvhart@infradead.org>,
"Davidlohr Bueso" <dave@stgolabs.net>,
"André Almeida" <andrealmeid@igalia.com>,
"Kan Liang" <kan.liang@linux.intel.com>,
"K Prateek Nayak" <kprateek.nayak@amd.com>,
"Sean Christopherson" <seanjc@google.com>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Kajol Jain" <kjain@linux.ibm.com>,
"Athira Rajeev" <atrajeev@linux.vnet.ibm.com>,
"Andrew Jones" <ajones@ventanamicro.com>,
"Alexandre Ghiti" <alexghiti@rivosinc.com>,
"Atish Patra" <atishp@rivosinc.com>,
"Steinar H. Gunderson" <sesse@google.com>,
"Yang Jihong" <yangjihong1@huawei.com>,
"Yang Li" <yang.lee@linux.alibaba.com>,
"Changbin Du" <changbin.du@huawei.com>,
"Sandipan Das" <sandipan.das@amd.com>,
"Ravi Bangoria" <ravi.bangoria@amd.com>,
"Paran Lee" <p4ranlee@gmail.com>,
"Nick Desaulniers" <ndesaulniers@google.com>,
"Huacai Chen" <chenhuacai@kernel.org>,
"Yanteng Si" <siyanteng@loongson.cn>,
linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
coresight@lists.linaro.org, linux-arm-kernel@lists.infradead.org,
bpf@vger.kernel.org
Subject: [PATCH v1 07/14] perf arm-spe/cs-etm: Directly iterate CPU maps
Date: Tue, 28 Nov 2023 22:02:04 -0800 [thread overview]
Message-ID: <20231129060211.1890454-8-irogers@google.com> (raw)
In-Reply-To: <20231129060211.1890454-1-irogers@google.com>
Rather than iterate all CPUs and see if they are in CPU maps, directly
iterate the CPU map. Similarly make use of the intersect
function. Switch perf_cpu_map__has_any_cpu_or_is_empty to more
appropriate alternatives.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/arch/arm/util/cs-etm.c | 77 ++++++++++++----------------
tools/perf/arch/arm64/util/arm-spe.c | 4 +-
2 files changed, 34 insertions(+), 47 deletions(-)
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 77e6663c1703..a68a72f2f668 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -197,38 +197,32 @@ static int cs_etm_validate_timestamp(struct auxtrace_record *itr,
static int cs_etm_validate_config(struct auxtrace_record *itr,
struct evsel *evsel)
{
- int i, err = -EINVAL;
+ int idx, err = -EINVAL;
struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus;
struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
+ struct perf_cpu_map *intersect_cpus = perf_cpu_map__intersect(event_cpus, online_cpus);
+ struct perf_cpu cpu;
- /* Set option of each CPU we have */
- for (i = 0; i < cpu__max_cpu().cpu; i++) {
- struct perf_cpu cpu = { .cpu = i, };
-
- /*
- * In per-cpu case, do the validation for CPUs to work with.
- * In per-thread case, the CPU map is empty. Since the traced
- * program can run on any CPUs in this case, thus don't skip
- * validation.
- */
- if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus) &&
- !perf_cpu_map__has(event_cpus, cpu))
- continue;
-
- if (!perf_cpu_map__has(online_cpus, cpu))
- continue;
+ perf_cpu_map__put(online_cpus);
- err = cs_etm_validate_context_id(itr, evsel, i);
+ /*
+ * Set option of each CPU we have. In per-cpu case, do the validation
+ * for CPUs to work with. In per-thread case, the CPU map is empty.
+ * Since the traced program can run on any CPUs in this case, thus don't
+ * skip validation.
+ */
+ perf_cpu_map__for_each_cpu_skip_any(cpu, idx, intersect_cpus) {
+ err = cs_etm_validate_context_id(itr, evsel, cpu.cpu);
if (err)
goto out;
- err = cs_etm_validate_timestamp(itr, evsel, i);
+ err = cs_etm_validate_timestamp(itr, evsel, idx);
if (err)
goto out;
}
err = 0;
out:
- perf_cpu_map__put(online_cpus);
+ perf_cpu_map__put(intersect_cpus);
return err;
}
@@ -435,7 +429,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
* Also the case of per-cpu mmaps, need the contextID in order to be notified
* when a context switch happened.
*/
- if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+ if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
"timestamp", 1);
evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
@@ -461,7 +455,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
evsel->core.attr.sample_period = 1;
/* In per-cpu case, always need the time of mmap events etc */
- if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
+ if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus))
evsel__set_sample_bit(evsel, TIME);
err = cs_etm_validate_config(itr, cs_etm_evsel);
@@ -533,38 +527,32 @@ static size_t
cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
struct evlist *evlist __maybe_unused)
{
- int i;
+ int idx;
int etmv3 = 0, etmv4 = 0, ete = 0;
struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
+ struct perf_cpu cpu;
/* cpu map is not empty, we have specific CPUs to work with */
- if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
- for (i = 0; i < cpu__max_cpu().cpu; i++) {
- struct perf_cpu cpu = { .cpu = i, };
-
- if (!perf_cpu_map__has(event_cpus, cpu) ||
- !perf_cpu_map__has(online_cpus, cpu))
- continue;
+ if (!perf_cpu_map__is_empty(event_cpus)) {
+ struct perf_cpu_map *intersect_cpus =
+ perf_cpu_map__intersect(event_cpus, online_cpus);
- if (cs_etm_is_ete(itr, i))
+ perf_cpu_map__for_each_cpu_skip_any(cpu, idx, intersect_cpus) {
+ if (cs_etm_is_ete(itr, cpu.cpu))
ete++;
- else if (cs_etm_is_etmv4(itr, i))
+ else if (cs_etm_is_etmv4(itr, cpu.cpu))
etmv4++;
else
etmv3++;
}
+ perf_cpu_map__put(intersect_cpus);
} else {
/* get configuration for all CPUs in the system */
- for (i = 0; i < cpu__max_cpu().cpu; i++) {
- struct perf_cpu cpu = { .cpu = i, };
-
- if (!perf_cpu_map__has(online_cpus, cpu))
- continue;
-
- if (cs_etm_is_ete(itr, i))
+ perf_cpu_map__for_each_cpu(cpu, idx, online_cpus) {
+ if (cs_etm_is_ete(itr, cpu.cpu))
ete++;
- else if (cs_etm_is_etmv4(itr, i))
+ else if (cs_etm_is_etmv4(itr, cpu.cpu))
etmv4++;
else
etmv3++;
@@ -814,15 +802,14 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
return -EINVAL;
/* If the cpu_map is empty all online CPUs are involved */
- if (perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
+ if (perf_cpu_map__is_empty(event_cpus)) {
cpu_map = online_cpus;
} else {
/* Make sure all specified CPUs are online */
- for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) {
- struct perf_cpu cpu = { .cpu = i, };
+ struct perf_cpu cpu;
- if (perf_cpu_map__has(event_cpus, cpu) &&
- !perf_cpu_map__has(online_cpus, cpu))
+ perf_cpu_map__for_each_cpu(cpu, i, event_cpus) {
+ if (!perf_cpu_map__has(online_cpus, cpu))
return -EINVAL;
}
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 51ccbfd3d246..0b52e67edb3b 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -232,7 +232,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
* In the case of per-cpu mmaps, sample CPU for AUX event;
* also enable the timestamp tracing for samples correlation.
*/
- if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+ if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
evsel__set_sample_bit(arm_spe_evsel, CPU);
evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel,
"ts_enable", 1);
@@ -265,7 +265,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
tracking_evsel->core.attr.sample_period = 1;
/* In per-cpu case, always need the time of mmap events etc */
- if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+ if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
evsel__set_sample_bit(tracking_evsel, TIME);
evsel__set_sample_bit(tracking_evsel, CPU);
--
2.43.0.rc1.413.gea7ed67945-goog
next prev parent reply other threads:[~2023-11-29 6:02 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-29 6:01 [PATCH v1 00/14] Clean up libperf cpumap's empty function Ian Rogers
2023-11-29 6:01 ` [PATCH v1 01/14] libperf cpumap: Rename perf_cpu_map__dummy_new Ian Rogers
2023-12-12 11:20 ` James Clark
2023-11-29 6:01 ` [PATCH v1 02/14] libperf cpumap: Rename and prefer sysfs for perf_cpu_map__default_new Ian Rogers
2023-12-12 11:32 ` James Clark
2023-12-12 17:39 ` Arnaldo Carvalho de Melo
2023-12-12 17:52 ` Ian Rogers
2023-11-29 6:02 ` [PATCH v1 03/14] libperf cpumap: Rename perf_cpu_map__empty Ian Rogers
2023-12-12 11:38 ` James Clark
2023-11-29 6:02 ` [PATCH v1 04/14] libperf cpumap: Replace usage of perf_cpu_map__new(NULL) Ian Rogers
2023-12-12 11:44 ` James Clark
2023-11-29 6:02 ` [PATCH v1 05/14] libperf cpumap: Add for_each_cpu that skips the "any CPU" case Ian Rogers
2023-12-12 13:54 ` James Clark
2023-11-29 6:02 ` [PATCH v1 06/14] libperf cpumap: Add any, empty and min helpers Ian Rogers
2023-12-12 14:00 ` James Clark
2023-12-12 14:51 ` James Clark
2023-12-12 20:02 ` Ian Rogers
2023-12-12 15:06 ` James Clark
2023-12-12 20:27 ` Ian Rogers
2023-12-13 13:48 ` James Clark
2023-11-29 6:02 ` Ian Rogers [this message]
2023-12-12 14:17 ` [PATCH v1 07/14] perf arm-spe/cs-etm: Directly iterate CPU maps James Clark
2023-12-12 14:36 ` James Clark
2024-02-01 2:12 ` Ian Rogers
2024-02-01 11:06 ` James Clark
2023-11-29 6:02 ` [PATCH v1 08/14] perf intel-pt/intel-bts: Switch perf_cpu_map__has_any_cpu_or_is_empty use Ian Rogers
2023-11-29 6:02 ` [PATCH v1 09/14] perf cpumap: Clean up use of perf_cpu_map__has_any_cpu_or_is_empty Ian Rogers
2023-12-12 15:10 ` James Clark
2023-11-29 6:02 ` [PATCH v1 10/14] perf top: Avoid repeated function calls Ian Rogers
2023-12-12 15:11 ` James Clark
2023-12-18 20:34 ` Arnaldo Carvalho de Melo
2023-11-29 6:02 ` [PATCH v1 11/14] perf arm64 header: Remove unnecessary CPU map get and put Ian Rogers
2023-12-12 15:13 ` James Clark
2023-11-29 6:02 ` [PATCH v1 12/14] perf stat: Remove duplicate cpus_map_matched function Ian Rogers
2023-12-12 11:28 ` James Clark
2023-11-29 6:02 ` [PATCH v1 13/14] perf cpumap: Use perf_cpu_map__for_each_cpu when possible Ian Rogers
2023-12-12 11:25 ` James Clark
2023-11-29 6:02 ` [PATCH v1 14/14] libperf cpumap: Document perf_cpu_map__nr's behavior Ian Rogers
2023-12-12 15:20 ` James Clark
2023-12-18 20:36 ` Arnaldo Carvalho de Melo
2023-12-11 19:31 ` [PATCH v1 00/14] Clean up libperf cpumap's empty function Ian Rogers
2023-12-12 17:59 ` Arnaldo Carvalho de Melo
2023-12-13 12:48 ` Adrian Hunter
2023-12-14 13:49 ` Arnaldo Carvalho de Melo
2023-12-13 23:29 ` Namhyung Kim
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20231129060211.1890454-8-irogers@google.com \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ajones@ventanamicro.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=alexghiti@rivosinc.com \
--cc=andrealmeid@igalia.com \
--cc=atishp@rivosinc.com \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=bpf@vger.kernel.org \
--cc=changbin.du@huawei.com \
--cc=chenhuacai@kernel.org \
--cc=coresight@lists.linaro.org \
--cc=dave@stgolabs.net \
--cc=dvhart@infradead.org \
--cc=james.clark@arm.com \
--cc=john.g.garry@oracle.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=kjain@linux.ibm.com \
--cc=kprateek.nayak@amd.com \
--cc=leo.yan@linaro.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mike.leach@linaro.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=ndesaulniers@google.com \
--cc=p4ranlee@gmail.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=ravi.bangoria@amd.com \
--cc=sandipan.das@amd.com \
--cc=seanjc@google.com \
--cc=sesse@google.com \
--cc=siyanteng@loongson.cn \
--cc=suzuki.poulose@arm.com \
--cc=tglx@linutronix.de \
--cc=will@kernel.org \
--cc=yang.lee@linux.alibaba.com \
--cc=yangjihong1@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox