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>,
Maxime Coquelin <mcoquelin.stm32@gmail.com>,
Alexandre Torgue <alexandre.torgue@foss.st.com>,
Zhengjun Xing <zhengjun.xing@linux.intel.com>,
Sandipan Das <sandipan.das@amd.com>,
James Clark <james.clark@arm.com>,
Kajol Jain <kjain@linux.ibm.com>,
John Garry <john.g.garry@oracle.com>,
Kan Liang <kan.liang@linux.intel.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Andrii Nakryiko <andrii@kernel.org>,
Eduard Zingerman <eddyz87@gmail.com>,
Suzuki Poulouse <suzuki.poulose@arm.com>,
Leo Yan <leo.yan@linaro.org>,
Florian Fischer <florian.fischer@muhq.space>,
Ravi Bangoria <ravi.bangoria@amd.com>,
Jing Zhang <renyu.zj@linux.alibaba.com>,
Sean Christopherson <seanjc@google.com>,
Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
linux-stm32@st-md-mailman.stormreply.com,
linux-arm-kernel@lists.infradead.org,
Perry Taylor <perry.taylor@intel.com>,
Caleb Biggers <caleb.biggers@intel.com>
Cc: Stephane Eranian <eranian@google.com>, Ian Rogers <irogers@google.com>
Subject: [PATCH v1 07/51] perf expr: Make the online topology accessible globally
Date: Sun, 19 Feb 2023 01:28:04 -0800 [thread overview]
Message-ID: <20230219092848.639226-8-irogers@google.com> (raw)
In-Reply-To: <20230219092848.639226-1-irogers@google.com>
Knowing the topology of online CPUs is useful for more than just expr
literals. Move to a global function that caches the value. An
additional upside is that this may also avoid computing the CPU
topology in some situations.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/tests/expr.c | 7 ++-----
tools/perf/util/cputopo.c | 14 ++++++++++++++
tools/perf/util/cputopo.h | 5 +++++
tools/perf/util/expr.c | 16 ++++++----------
tools/perf/util/smt.c | 11 +++++------
tools/perf/util/smt.h | 12 ++++++------
6 files changed, 38 insertions(+), 27 deletions(-)
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index a9eb1ed6bd63..cbf0e0c74906 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -154,13 +154,10 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
/* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */
{
- struct cpu_topology *topology = cpu_topology__new();
- bool smton = smt_on(topology);
+ bool smton = smt_on();
bool corewide = core_wide(/*system_wide=*/false,
- /*user_requested_cpus=*/false,
- topology);
+ /*user_requested_cpus=*/false);
- cpu_topology__delete(topology);
expr__ctx_clear(ctx);
TEST_ASSERT_VAL("find ids",
expr__find_ids("EVENT1 if #smt_on else EVENT2",
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index e08797c3cdbc..ca1d833a0c26 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -238,6 +238,20 @@ static bool has_die_topology(void)
return true;
}
+const struct cpu_topology *online_topology(void)
+{
+ static const struct cpu_topology *topology;
+
+ if (!topology) {
+ topology = cpu_topology__new();
+ if (!topology) {
+ pr_err("Error creating CPU topology");
+ abort();
+ }
+ }
+ return topology;
+}
+
struct cpu_topology *cpu_topology__new(void)
{
struct cpu_topology *tp = NULL;
diff --git a/tools/perf/util/cputopo.h b/tools/perf/util/cputopo.h
index 969e5920a00e..8d42f6102954 100644
--- a/tools/perf/util/cputopo.h
+++ b/tools/perf/util/cputopo.h
@@ -56,6 +56,11 @@ struct hybrid_topology {
struct hybrid_topology_node nodes[];
};
+/*
+ * The topology for online CPUs, lazily created.
+ */
+const struct cpu_topology *online_topology(void);
+
struct cpu_topology *cpu_topology__new(void);
void cpu_topology__delete(struct cpu_topology *tp);
/* Determine from the core list whether SMT was enabled. */
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index c1da20b868db..d46a1878bc9e 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -402,7 +402,7 @@ double arch_get_tsc_freq(void)
double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx)
{
- static struct cpu_topology *topology;
+ const struct cpu_topology *topology;
double result = NAN;
if (!strcmp("#num_cpus", literal)) {
@@ -421,31 +421,27 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx
* these strings gives an indication of the number of packages, dies,
* etc.
*/
- if (!topology) {
- topology = cpu_topology__new();
- if (!topology) {
- pr_err("Error creating CPU topology");
- goto out;
- }
- }
if (!strcasecmp("#smt_on", literal)) {
- result = smt_on(topology) ? 1.0 : 0.0;
+ result = smt_on() ? 1.0 : 0.0;
goto out;
}
if (!strcmp("#core_wide", literal)) {
- result = core_wide(ctx->system_wide, ctx->user_requested_cpu_list, topology)
+ result = core_wide(ctx->system_wide, ctx->user_requested_cpu_list)
? 1.0 : 0.0;
goto out;
}
if (!strcmp("#num_packages", literal)) {
+ topology = online_topology();
result = topology->package_cpus_lists;
goto out;
}
if (!strcmp("#num_dies", literal)) {
+ topology = online_topology();
result = topology->die_cpus_lists;
goto out;
}
if (!strcmp("#num_cores", literal)) {
+ topology = online_topology();
result = topology->core_cpus_lists;
goto out;
}
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 994e9e418227..650e804d0adc 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -4,7 +4,7 @@
#include "cputopo.h"
#include "smt.h"
-bool smt_on(const struct cpu_topology *topology)
+bool smt_on(void)
{
static bool cached;
static bool cached_result;
@@ -16,22 +16,21 @@ bool smt_on(const struct cpu_topology *topology)
if (sysfs__read_int("devices/system/cpu/smt/active", &fs_value) >= 0)
cached_result = (fs_value == 1);
else
- cached_result = cpu_topology__smt_on(topology);
+ cached_result = cpu_topology__smt_on(online_topology());
cached = true;
return cached_result;
}
-bool core_wide(bool system_wide, const char *user_requested_cpu_list,
- const struct cpu_topology *topology)
+bool core_wide(bool system_wide, const char *user_requested_cpu_list)
{
/* If not everything running on a core is being recorded then we can't use core_wide. */
if (!system_wide)
return false;
/* Cheap case that SMT is disabled and therefore we're inherently core_wide. */
- if (!smt_on(topology))
+ if (!smt_on())
return true;
- return cpu_topology__core_wide(topology, user_requested_cpu_list);
+ return cpu_topology__core_wide(online_topology(), user_requested_cpu_list);
}
diff --git a/tools/perf/util/smt.h b/tools/perf/util/smt.h
index ae9095f2c38c..01441fd2c0a2 100644
--- a/tools/perf/util/smt.h
+++ b/tools/perf/util/smt.h
@@ -2,16 +2,16 @@
#ifndef __SMT_H
#define __SMT_H 1
-struct cpu_topology;
-
-/* Returns true if SMT (aka hyperthreading) is enabled. */
-bool smt_on(const struct cpu_topology *topology);
+/*
+ * Returns true if SMT (aka hyperthreading) is enabled. Determined via sysfs or
+ * the online topology.
+ */
+bool smt_on(void);
/*
* Returns true when system wide and all SMT threads for a core are in the
* user_requested_cpus map.
*/
-bool core_wide(bool system_wide, const char *user_requested_cpu_list,
- const struct cpu_topology *topology);
+bool core_wide(bool system_wide, const char *user_requested_cpu_list);
#endif /* __SMT_H */
--
2.39.2.637.g21b0678d19-goog
next prev parent reply other threads:[~2023-02-19 9:30 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-19 9:27 [PATCH v1 00/51] shadow metric clean up and improvements Ian Rogers
2023-02-19 9:27 ` [PATCH v1 01/51] perf tools: Ensure evsel name is initialized Ian Rogers
2023-02-28 12:06 ` kajoljain
2023-02-19 9:27 ` [PATCH v1 02/51] perf metrics: Improve variable names Ian Rogers
2023-02-19 9:28 ` [PATCH v1 03/51] perf pmu-events: Remove aggr_mode from pmu_event Ian Rogers
2023-02-19 9:28 ` [PATCH v1 04/51] perf pmu-events: Change aggr_mode to be an enum Ian Rogers
2023-02-19 9:28 ` [PATCH v1 05/51] perf pmu-events: Change deprecated to be a bool Ian Rogers
2023-02-19 9:28 ` [PATCH v1 06/51] perf pmu-events: Change perpkg " Ian Rogers
2023-02-19 9:28 ` Ian Rogers [this message]
2023-02-19 9:28 ` [PATCH v1 08/51] perf pmu-events: Make the metric_constraint an enum Ian Rogers
2023-02-19 9:28 ` [PATCH v1 09/51] perf pmu-events: Don't '\0' terminate enum values Ian Rogers
2023-02-19 9:28 ` [PATCH v1 11/51] perf vendor events intel: Refresh alderlake-n metrics Ian Rogers
2023-02-19 9:28 ` [PATCH v1 16/51] perf vendor events intel: Add graniterapids events Ian Rogers
2023-02-19 9:28 ` [PATCH v1 24/51] perf vendor events intel: Refresh knightslanding events Ian Rogers
2023-02-19 9:28 ` [PATCH v1 25/51] perf vendor events intel: Refresh sandybridge events Ian Rogers
2023-02-19 9:28 ` [PATCH v1 27/51] perf vendor events intel: Refresh silvermont events Ian Rogers
2023-02-19 9:28 ` [PATCH v1 31/51] perf vendor events intel: Refresh westmereep-dp events Ian Rogers
2023-02-19 9:28 ` [PATCH v1 32/51] perf jevents: Add rand support to metrics Ian Rogers
2023-02-19 9:28 ` [PATCH v1 33/51] perf jevent: Parse metric thresholds Ian Rogers
2023-02-19 9:28 ` [PATCH v1 34/51] perf pmu-events: Test parsing metric thresholds with the fake PMU Ian Rogers
2023-02-19 9:28 ` [PATCH v1 35/51] perf list: Support for printing metric thresholds Ian Rogers
2023-02-19 9:28 ` [PATCH v1 36/51] perf metric: Compute and print threshold values Ian Rogers
2023-02-19 9:28 ` [PATCH v1 37/51] perf expr: More explicit NAN handling Ian Rogers
2023-02-19 9:28 ` [PATCH v1 38/51] perf metric: Add --metric-no-threshold option Ian Rogers
2023-02-19 9:28 ` [PATCH v1 39/51] perf stat: Add TopdownL1 metric as a default if present Ian Rogers
2023-02-27 19:12 ` Liang, Kan
2023-02-27 19:33 ` Ian Rogers
2023-02-27 20:12 ` Liang, Kan
2023-02-28 6:27 ` Ian Rogers
2023-02-28 14:15 ` Liang, Kan
2023-02-19 9:28 ` [PATCH v1 40/51] perf stat: Implement --topdown using json metrics Ian Rogers
2023-02-19 9:28 ` [PATCH v1 41/51] perf stat: Remove topdown event special handling Ian Rogers
2023-02-19 9:28 ` [PATCH v1 42/51] perf doc: Refresh topdown documentation Ian Rogers
2023-02-19 9:28 ` [PATCH v1 43/51] perf stat: Remove hard coded transaction events Ian Rogers
2023-02-19 9:28 ` [PATCH v1 44/51] perf stat: Use metrics for --smi-cost Ian Rogers
2023-02-19 9:28 ` [PATCH v1 45/51] perf stat: Remove perf_stat_evsel_id Ian Rogers
2023-02-19 9:28 ` [PATCH v1 46/51] perf stat: Move enums from header Ian Rogers
2023-02-19 9:28 ` [PATCH v1 47/51] perf stat: Hide runtime_stat Ian Rogers
2023-02-19 9:28 ` [PATCH v1 48/51] perf stat: Add cpu_aggr_map for loop Ian Rogers
2023-02-19 9:28 ` [PATCH v1 49/51] perf metric: Directly use counts rather than saved_value Ian Rogers
2023-02-19 9:28 ` [PATCH v1 50/51] perf stat: Use " Ian Rogers
2023-02-24 22:48 ` Namhyung Kim
2023-02-25 5:47 ` Ian Rogers
2023-02-19 9:28 ` [PATCH v1 51/51] perf stat: Remove saved_value/runtime_stat Ian Rogers
2023-02-19 11:17 ` [PATCH v1 00/51] shadow metric clean up and improvements Arnaldo Carvalho de Melo
2023-02-19 15:43 ` Ian Rogers
2023-02-21 17:44 ` Ian Rogers
2023-02-22 13:47 ` Arnaldo Carvalho de Melo
2023-02-27 22:04 ` Liang, Kan
2023-02-28 6:21 ` Ian Rogers
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=20230219092848.639226-8-irogers@google.com \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=alexandre.torgue@foss.st.com \
--cc=andrii@kernel.org \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=caleb.biggers@intel.com \
--cc=eddyz87@gmail.com \
--cc=eranian@google.com \
--cc=florian.fischer@muhq.space \
--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=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=linux-stm32@st-md-mailman.stormreply.com \
--cc=mark.rutland@arm.com \
--cc=mcoquelin.stm32@gmail.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=perry.taylor@intel.com \
--cc=peterz@infradead.org \
--cc=ravi.bangoria@amd.com \
--cc=renyu.zj@linux.alibaba.com \
--cc=sandipan.das@amd.com \
--cc=seanjc@google.com \
--cc=suzuki.poulose@arm.com \
--cc=zhengjun.xing@linux.intel.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;
as well as URLs for NNTP newsgroup(s).