perf lock contention: Add -J/--inject-delay option

This is to slow down lock acquistion (on contention locks) deliberately.

A possible use case is to estimate impact on application performance by
optimization of kernel locking behavior.  By delaying the lock it can
simulate the worse condition as a control group, and then compare with
the current behavior as a optimized condition.

The syntax is 'time@function' and the time can have unit suffix like
"us" and "ms".  For example, I ran a simple test like below.

  $ sudo perf lock con -abl -L tasklist_lock -- \
    sh -c 'for i in $(seq 1000); do sleep 1 & done; wait'
   contended   total wait     max wait     avg wait            address   symbol

          92      1.18 ms    199.54 us     12.79 us   ffffffff8a806080   tasklist_lock (rwlock)

The contention count was 92 and the average wait time was around 10 us.
But if I add 100 usec of delay to the tasklist_lock,

  $ sudo perf lock con -abl -L tasklist_lock -J 100us@tasklist_lock -- \
    sh -c 'for i in $(seq 1000); do sleep 1 & done; wait'
   contended   total wait     max wait     avg wait            address   symbol

         190     15.67 ms    230.10 us     82.46 us   ffffffff8a806080   tasklist_lock (rwlock)

The contention count increased and the average wait time was up closed
to 100 usec.  If I increase the delay even more,

  $ sudo perf lock con -abl -L tasklist_lock -J 1ms@tasklist_lock -- \
    sh -c 'for i in $(seq 1000); do sleep 1 & done; wait'
   contended   total wait     max wait     avg wait            address   symbol

        1002      2.80 s       3.01 ms      2.80 ms   ffffffff8a806080   tasklist_lock (rwlock)

Now every sleep process had contention and the wait time was more than 1
msec.  This is on my 4 CPU laptop so I guess one CPU has the lock while
other 3 are waiting for it mostly.

For simplicity, it only supports global locks for now.

Committer testing:

  root@number:~# grep -m1 'model name' /proc/cpuinfo
  model name : AMD Ryzen 9 9950X3D 16-Core Processor
  root@number:~# perf lock con -abl -L tasklist_lock -- sh -c 'for i in $(seq 1000); do sleep 1 & done; wait'
   contended  total wait   max wait  avg wait           address  symbol

         142   453.85 us   25.39 us   3.20 us  ffffffffae808080  tasklist_lock (rwlock)
  root@number:~# perf lock con -abl -L tasklist_lock -J 100us@tasklist_lock -- sh -c 'for i in $(seq 1000); do sleep 1 & done; wait'
   contended  total wait   max wait  avg wait           address  symbol

        1040     2.39 s     3.11 ms   2.30 ms  ffffffffae808080  tasklist_lock (rwlock)
  root@number:~# perf lock con -abl -L tasklist_lock -J 1ms@tasklist_lock -- sh -c 'for i in $(seq 1000); do sleep 1 & done; wait'
   contended  total wait   max wait  avg wait           address  symbol

        1025    24.72 s    31.01 ms  24.12 ms  ffffffffae808080  tasklist_lock (rwlock)
  root@number:~#

Suggested-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20250509171950.183591-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 74 insertions, 0 deletions

diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 05e7bc30488a..41f6f3d2b779 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -62,6 +62,8 @@ static const char *output_name = NULL;
 static FILE *lock_output;
 
 static struct lock_filter filters;
+static struct lock_delay *delays;
+static int nr_delays;
 
 static enum lock_aggr_mode aggr_mode = LOCK_AGGR_ADDR;
 
@@ -2001,6 +2003,8 @@ static int __cmd_contention(int argc, const char **argv)
 		.max_stack = max_stack_depth,
 		.stack_skip = stack_skip,
 		.filters = &filters,
+		.delays = delays,
+		.nr_delays = nr_delays,
 		.save_callstack = needs_callstack(),
 		.owner = show_lock_owner,
 		.cgroups = RB_ROOT,
@@ -2504,6 +2508,74 @@ static int parse_cgroup_filter(const struct option *opt __maybe_unused, const ch
 	return ret;
 }
 
+static bool add_lock_delay(char *spec)
+{
+	char *at, *pos;
+	struct lock_delay *tmp;
+	unsigned long duration;
+
+	at = strchr(spec, '@');
+	if (at == NULL) {
+		pr_err("lock delay should have '@' sign: %s\n", spec);
+		return false;
+	}
+	if (at == spec) {
+		pr_err("lock delay should have time before '@': %s\n", spec);
+		return false;
+	}
+
+	*at = '\0';
+	duration = strtoul(spec, &pos, 0);
+	if (!strcmp(pos, "ns"))
+		duration *= 1;
+	else if (!strcmp(pos, "us"))
+		duration *= 1000;
+	else if (!strcmp(pos, "ms"))
+		duration *= 1000 * 1000;
+	else if (*pos) {
+		pr_err("invalid delay time: %s@%s\n", spec, at + 1);
+		return false;
+	}
+
+	tmp = realloc(delays, (nr_delays + 1) * sizeof(*delays));
+	if (tmp == NULL) {
+		pr_err("Memory allocation failure\n");
+		return false;
+	}
+	delays = tmp;
+
+	delays[nr_delays].sym = strdup(at + 1);
+	if (delays[nr_delays].sym == NULL) {
+		pr_err("Memory allocation failure\n");
+		return false;
+	}
+	delays[nr_delays].time = duration;
+
+	nr_delays++;
+	return true;
+}
+
+static int parse_lock_delay(const struct option *opt __maybe_unused, const char *str,
+			    int unset __maybe_unused)
+{
+	char *s, *tmp, *tok;
+	int ret = 0;
+
+	s = strdup(str);
+	if (s == NULL)
+		return -1;
+
+	for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		if (!add_lock_delay(tok)) {
+			ret = -1;
+			break;
+		}
+	}
+
+	free(s);
+	return ret;
+}
+
 int cmd_lock(int argc, const char **argv)
 {
 	const struct option lock_options[] = {
@@ -2580,6 +2652,8 @@ int cmd_lock(int argc, const char **argv)
 	OPT_BOOLEAN(0, "lock-cgroup", &show_lock_cgroups, "show lock stats by cgroup"),
 	OPT_CALLBACK('G', "cgroup-filter", NULL, "CGROUPS",
 		     "Filter specific cgroups", parse_cgroup_filter),
+	OPT_CALLBACK('J', "inject-delay", NULL, "TIME@FUNC",
+		     "Inject delays to specific locks", parse_lock_delay),
 	OPT_PARENT(lock_options)
 	};