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@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230527034324.2597593-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index c9ddf73689cd6c073579d2130cc2502a76fa29b5..9ab300b6f131fe8a9935c7515141c368bd215f43 100644 (file)
--- 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;
@@ -3595,7 +3595,22 @@ 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,
@@ -3664,6 +3679,9 @@ 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);