linux-kernel - [PATCH v1] perf cpumap: Reduce cpu size from int to int16

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-next>] [day] [month] [year] [list]

Message-Id: <20241207052133.102829-1-irogers@google.com>
Date: Fri,  6 Dec 2024 21:21:33 -0800
From: Ian Rogers <irogers@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>, 
	Arnaldo Carvalho de Melo <acme@...nel.org>, Namhyung Kim <namhyung@...nel.org>, 
	Mark Rutland <mark.rutland@....com>, 
	Alexander Shishkin <alexander.shishkin@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>, 
	Ian Rogers <irogers@...gle.com>, Adrian Hunter <adrian.hunter@...el.com>, 
	Kan Liang <kan.liang@...ux.intel.com>, James Clark <james.clark@...aro.org>, 
	Tim Chen <tim.c.chen@...ux.intel.com>, Yicong Yang <yangyicong@...ilicon.com>, 
	Ravi Bangoria <ravi.bangoria@....com>, linux-perf-users@...r.kernel.org, 
	linux-kernel@...r.kernel.org, Leo Yan <leo.yan@....com>, 
	Kyle Meyer <kyle.meyer@....com>
Subject: [PATCH v1] perf cpumap: Reduce cpu size from int to int16_t

Fewer than 32k CPUs are currently supported by perf. A cpumap stores
an int per CPU, so its size is 4 times the number of CPUs in the
cpumap. We can reduce the size of the int to an int16_t, saving 2
bytes per CPU in the map.

Signed-off-by: Ian Rogers <irogers@...gle.com>
---
This change is on top of:
https://lore.kernel.org/lkml/20241206044035.1062032-1-irogers@google.com/
---
 tools/lib/perf/include/perf/cpumap.h |  3 ++-
 tools/perf/util/cpumap.c             | 13 ++++++++-----
 tools/perf/util/env.c                |  2 +-
 3 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index cbb65e55fc67..760a9aae9884 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -4,10 +4,11 @@
 
 #include <perf/core.h>
 #include <stdbool.h>
+#include <stdint.h>
 
 /** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
 struct perf_cpu {
-	int cpu;
+	int16_t cpu;
 };
 
 struct perf_cache {
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 27094211edd8..85e224d8631b 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -427,7 +427,7 @@ static void set_max_cpu_num(void)
 {
 	const char *mnt;
 	char path[PATH_MAX];
-	int ret = -1;
+	int max, ret = -1;
 
 	/* set up default */
 	max_cpu_num.cpu = 4096;
@@ -444,10 +444,12 @@ static void set_max_cpu_num(void)
 		goto out;
 	}
 
-	ret = get_max_num(path, &max_cpu_num.cpu);
+	ret = get_max_num(path, &max);
 	if (ret)
 		goto out;
 
+	max_cpu_num.cpu = max;
+
 	/* get the highest present cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt);
 	if (ret >= PATH_MAX) {
@@ -455,8 +457,9 @@ static void set_max_cpu_num(void)
 		goto out;
 	}
 
-	ret = get_max_num(path, &max_present_cpu_num.cpu);
-
+	ret = get_max_num(path, &max);
+	if (!ret)
+		max_present_cpu_num.cpu = max;
 out:
 	if (ret)
 		pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu);
@@ -606,7 +609,7 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size)
 #define COMMA first ? "" : ","
 
 	for (i = 0; i < perf_cpu_map__nr(map) + 1; i++) {
-		struct perf_cpu cpu = { .cpu = INT_MAX };
+		struct perf_cpu cpu = { .cpu = INT16_MAX };
 		bool last = i == perf_cpu_map__nr(map);
 
 		if (!last)
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index e2843ca2edd9..f1d7d22e7e98 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -531,7 +531,7 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
 
 		for (i = 0; i < env->nr_numa_nodes; i++) {
 			nn = &env->numa_nodes[i];
-			nr = max(nr, perf_cpu_map__max(nn->map).cpu);
+			nr = max(nr, (int)perf_cpu_map__max(nn->map).cpu);
 		}
 
 		nr++;
-- 
2.47.0.338.g60cca15819-goog