linux-kernel - [PATCH v1 1/4] perf sched: Avoid large stack allocations

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]

Date:   Fri, 26 May 2023 20:43:19 -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>,
        Ian Rogers <irogers@...gle.com>,
        Adrian Hunter <adrian.hunter@...el.com>,
        linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH v1 1/4] perf sched: Avoid large stack allocations

Commit 5ded57ac1bdb ("perf inject: Remove static variables") moved
static variables to local, however, in this case 3 MAX_CPUS (4096)
sized arrays were moved onto the stack making the stack frame quite
large. Avoid the stack usage by dynamically allocating the arrays.

Signed-off-by: Ian Rogers <irogers@...gle.com>
---
 tools/perf/builtin-sched.c | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index cc4ba506e119..2aeb3c8ac396 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -193,8 +193,8 @@ struct perf_sched {
  * weird events, such as a task being switched away that is not current.
  */
 	struct perf_cpu	 max_cpu;
-	u32		 curr_pid[MAX_CPUS];
-	struct thread	 *curr_thread[MAX_CPUS];
+	u32		 *curr_pid;
+	struct thread	 **curr_thread;
 	char		 next_shortname1;
 	char		 next_shortname2;
 	unsigned int	 replay_repeat;
@@ -224,7 +224,7 @@ struct perf_sched {
 	u64		 run_avg;
 	u64		 all_runtime;
 	u64		 all_count;
-	u64		 cpu_last_switched[MAX_CPUS];
+	u64		 *cpu_last_switched;
 	struct rb_root_cached atom_root, sorted_atom_root, merged_atom_root;
 	struct list_head sort_list, cmp_pid;
 	bool force;
@@ -3599,7 +3599,22 @@ int cmd_sched(int argc, const char **argv)
 
 	mutex_init(&sched.start_work_mutex);
 	mutex_init(&sched.work_done_wait_mutex);
-	for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++)
+	sched.curr_thread = calloc(MAX_CPUS, sizeof(*sched.curr_thread));
+	if (!sched.curr_thread) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	sched.cpu_last_switched = calloc(MAX_CPUS, sizeof(*sched.cpu_last_switched));
+	if (!sched.cpu_last_switched) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	sched.curr_pid = malloc(MAX_CPUS * sizeof(*sched.curr_pid));
+	if (!sched.curr_pid) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	for (i = 0; i < MAX_CPUS; i++)
 		sched.curr_pid[i] = -1;
 
 	argc = parse_options_subcommand(argc, argv, sched_options, sched_subcommands,
@@ -3668,6 +3683,9 @@ int cmd_sched(int argc, const char **argv)
 	}
 
 out:
+	free(sched.curr_pid);
+	free(sched.cpu_last_switched);
+	free(sched.curr_thread);
 	mutex_destroy(&sched.start_work_mutex);
 	mutex_destroy(&sched.work_done_wait_mutex);
 
-- 
2.41.0.rc0.172.g3f132b7071-goog