netdev - [PATCH 2/5] perf cpumap: More cpu map reuse by merge.

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220328062414.1893550-3-irogers@google.com>
Date:   Sun, 27 Mar 2022 23:24:11 -0700
From:   Ian Rogers <irogers@...gle.com>
To:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Mathieu Poirier <mathieu.poirier@...aro.org>,
        Suzuki K Poulose <suzuki.poulose@....com>,
        Mike Leach <mike.leach@...aro.org>,
        Leo Yan <leo.yan@...aro.org>,
        John Garry <john.garry@...wei.com>,
        Will Deacon <will@...nel.org>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Andrii Nakryiko <andrii@...nel.org>,
        Martin KaFai Lau <kafai@...com>,
        Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
        John Fastabend <john.fastabend@...il.com>,
        KP Singh <kpsingh@...nel.org>,
        Kajol Jain <kjain@...ux.ibm.com>,
        James Clark <james.clark@....com>,
        German Gomez <german.gomez@....com>,
        Adrian Hunter <adrian.hunter@...el.com>,
        Riccardo Mancini <rickyman7@...il.com>,
        Andi Kleen <ak@...ux.intel.com>,
        Alexey Bayduraev <alexey.v.bayduraev@...ux.intel.com>,
        Alexander Antonov <alexander.antonov@...ux.intel.com>,
        linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
        coresight@...ts.linaro.org, linux-arm-kernel@...ts.infradead.org,
        netdev@...r.kernel.org, bpf@...r.kernel.org
Cc:     Stephane Eranian <eranian@...gle.com>,
        Ian Rogers <irogers@...gle.com>
Subject: [PATCH 2/5] perf cpumap: More cpu map reuse by merge.

perf_cpu_map__merge will reuse one of its arguments if they are equal or
the other argument is NULL. The arguments could be reused if it is known
one set of values is a subset of the other. For example, a map of 0-1
and a map of just 0 when merged yields the map of 0-1. Currently a new
map is created rather than adding a reference count to the original 0-1
map.

Signed-off-by: Ian Rogers <irogers@...gle.com>
---
 tools/lib/perf/cpumap.c | 38 ++++++++++++++++++++++++++++----------
 1 file changed, 28 insertions(+), 10 deletions(-)

diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index ee66760f1e63..953bc50b0e41 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -319,6 +319,29 @@ struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
 	return map->nr > 0 ? map->map[map->nr - 1] : result;
 }
 
+/** Is 'b' a subset of 'a'. */
+static bool perf_cpu_map__is_subset(const struct perf_cpu_map *a,
+				    const struct perf_cpu_map *b)
+{
+	int i, j;
+
+	if (a == b || !b)
+		return true;
+	if (!a || b->nr > a->nr)
+		return false;
+	j = 0;
+	for (i = 0; i < a->nr; i++) {
+		if (a->map[i].cpu > b->map[j].cpu)
+			return false;
+		if (a->map[i].cpu == b->map[j].cpu) {
+			j++;
+			if (j == b->nr)
+				return true;
+		}
+	}
+	return false;
+}
+
 /*
  * Merge two cpumaps
  *
@@ -335,17 +358,12 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 	int i, j, k;
 	struct perf_cpu_map *merged;
 
-	if (!orig && !other)
-		return NULL;
-	if (!orig) {
-		perf_cpu_map__get(other);
-		return other;
-	}
-	if (!other)
-		return orig;
-	if (orig->nr == other->nr &&
-	    !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu)))
+	if (perf_cpu_map__is_subset(orig, other))
 		return orig;
+	if (perf_cpu_map__is_subset(other, orig)) {
+		perf_cpu_map__put(orig);
+		return perf_cpu_map__get(other);
+	}
 
 	tmp_len = orig->nr + other->nr;
 	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
-- 
2.35.1.1021.g381101b075-goog