Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:4 as permitted sender) client-ip=2620:137:e000::3:4;
Date:   Thu, 12 Oct 2023 10:56:44 -0700
In-Reply-To: <20231012175645.1849503-1-irogers@google.com>
Message-Id: <20231012175645.1849503-7-irogers@google.com>
Mime-Version: 1.0
References: <20231012175645.1849503-1-irogers@google.com>
Subject: [PATCH v2 6/7] perf pmu-events: Remember the perf_events_map for a PMU
From:   Ian Rogers <irogers@google.com>
To:     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>,
        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>,
        Thomas Richter <tmricht@linux.ibm.com>,
        Ravi Bangoria <ravi.bangoria@amd.com>,
        Kajol Jain <kjain@linux.ibm.com>,
        Jing Zhang <renyu.zj@linux.alibaba.com>,
        Kan Liang <kan.liang@linux.intel.com>,
        Yang Jihong <yangjihong1@huawei.com>,
        coresight@lists.linaro.org, linux-arm-kernel@lists.infradead.org,
        linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

strcmp_cpuid_str performs regular expression comparisons and so per
CPUID linear searches over the perf_events_map are expensive. Add a
helper function called map_for_pmu that does the search but also
caches the map specific to a PMU. As the PMU may differ, also cache
the CPUID string so that PMUs with the same CPUID string don't require
the linear search and regular expression comparisons. This speeds
loading PMUs as the search is done once per PMU to find the
appropriate tables.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/pmu-events/jevents.py | 109 ++++++++++++++++++++-----------
 1 file changed, 70 insertions(+), 39 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 96dc74c90b20..3c091ab75305 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -976,68 +976,99 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table,
         return 0;
 }
 
-const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
+static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu)
 {
-        const struct pmu_events_table *table = NULL;
-        char *cpuid = perf_pmu__getcpuid(pmu);
+        static struct {
+                const struct pmu_events_map *map;
+                struct perf_pmu *pmu;
+        } last_result;
+        static struct {
+                const struct pmu_events_map *map;
+                char *cpuid;
+        } last_map_search;
+        static bool has_last_result, has_last_map_search;
+        const struct pmu_events_map *map = NULL;
+        char *cpuid = NULL;
         size_t i;
 
-        /* on some platforms which uses cpus map, cpuid can be NULL for
+        if (has_last_result && last_result.pmu == pmu)
+                return last_result.map;
+
+        cpuid = perf_pmu__getcpuid(pmu);
+
+        /*
+         * On some platforms which uses cpus map, cpuid can be NULL for
          * PMUs other than CORE PMUs.
          */
         if (!cpuid)
-                return NULL;
+                goto out_update_last_result;
+
+        if (has_last_map_search && !strcmp(last_map_search.cpuid, cpuid)) {
+                map = last_map_search.map;
+                free(cpuid);
+        } else {
+                i = 0;
+                for (;;) {
+                        map = &pmu_events_map[i++];
+
+                        if (!map->arch) {
+                                map = NULL;
+                                break;
+                        }
+
+                        if (!strcmp_cpuid_str(map->cpuid, cpuid))
+                                break;
+               }
+               free(last_map_search.cpuid);
+               last_map_search.cpuid = cpuid;
+               last_map_search.map = map;
+               has_last_map_search = true;
+        }
+out_update_last_result:
+        last_result.pmu = pmu;
+        last_result.map = map;
+        has_last_result = true;
+        return map;
+}
 
-        i = 0;
-        for (;;) {
-                const struct pmu_events_map *map = &pmu_events_map[i++];
-                if (!map->arch)
-                        break;
+const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu)
+{
+        const struct pmu_events_map *map = map_for_pmu(pmu);
 
-                if (!strcmp_cpuid_str(map->cpuid, cpuid)) {
-                        table = &map->event_table;
-                        break;
-                }
-        }
-        free(cpuid);
-        if (!pmu || !table)
-                return table;
+        if (!map)
+                return NULL;
 
-        for (i = 0; i < table->num_pmus; i++) {
-                const struct pmu_table_entry *table_pmu = &table->pmus[i];
+        if (!pmu)
+                return &map->event_table;
+
+        for (size_t i = 0; i < map->event_table.num_pmus; i++) {
+                const struct pmu_table_entry *table_pmu = &map->event_table.pmus[i];
                 const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
 
                 if (pmu__name_match(pmu, pmu_name))
-                        return table;
+                         return &map->event_table;
         }
         return NULL;
 }
 
 const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu)
 {
-        const struct pmu_metrics_table *table = NULL;
-        char *cpuid = perf_pmu__getcpuid(pmu);
-        int i;
+        const struct pmu_events_map *map = map_for_pmu(pmu);
 
-        /* on some platforms which uses cpus map, cpuid can be NULL for
-         * PMUs other than CORE PMUs.
-         */
-        if (!cpuid)
+        if (!map)
                 return NULL;
 
-        i = 0;
-        for (;;) {
-                const struct pmu_events_map *map = &pmu_events_map[i++];
-                if (!map->arch)
-                        break;
+        if (!pmu)
+                return &map->metric_table;
 
-                if (!strcmp_cpuid_str(map->cpuid, cpuid)) {
-                        table = &map->metric_table;
-                        break;
-                }
+        for (size_t i = 0; i < map->metric_table.num_pmus; i++) {
+                const struct pmu_table_entry *table_pmu = &map->metric_table.pmus[i];
+                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+
+                if (pmu__name_match(pmu, pmu_name))
+                           return &map->metric_table;
         }
-        free(cpuid);
-        return table;
+        return NULL;
 }
 
 const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid)
-- 
2.42.0.655.g421f12c284-goog