perf lock contention: Add -G/--cgroup-filter option

The -G/--cgroup-filter is to limit lock contention collection on the
tasks in the specific cgroups only.

  $ sudo ./perf lock con -abt -G /user.slice/.../vte-spawn-52221fb8-b33f-4a52-b5c3-e35d1e6fc0e0.scope \
    ./perf bench sched messaging
  # Running 'sched/messaging' benchmark:
  # 20 sender and receiver processes per group
  # 10 groups == 400 processes run

       Total time: 0.174 [sec]
   contended   total wait     max wait     avg wait          pid   comm

           4    114.45 us     60.06 us     28.61 us       214847   sched-messaging
           2    111.40 us     60.84 us     55.70 us       214848   sched-messaging
           2    106.09 us     59.42 us     53.04 us       214837   sched-messaging
           1     81.70 us     81.70 us     81.70 us       214709   sched-messaging
          68     78.44 us      6.83 us      1.15 us       214633   sched-messaging
          69     73.71 us      2.69 us      1.07 us       214632   sched-messaging
           4     72.62 us     60.83 us     18.15 us       214850   sched-messaging
           2     71.75 us     67.60 us     35.88 us       214840   sched-messaging
           2     69.29 us     67.53 us     34.65 us       214804   sched-messaging
           2     69.00 us     68.23 us     34.50 us       214826   sched-messaging
  ...

Export cgroup__new() function as it's needed from outside.

Reviewed-by: Ian Rogers <irogers@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: Hao Luo <haoluo@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230906174903.346486-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 35 insertions, 2 deletions

diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index 42753a0dfdc5..e105245eb905 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -21,7 +21,7 @@ static struct lock_contention_bpf *skel;
 int lock_contention_prepare(struct lock_contention *con)
 {
 	int i, fd;
-	int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1;
+	int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1;
 	struct evlist *evlist = con->evlist;
 	struct target *target = con->target;
 
@@ -51,6 +51,8 @@ int lock_contention_prepare(struct lock_contention *con)
 		ntasks = perf_thread_map__nr(evlist->core.threads);
 	if (con->filters->nr_types)
 		ntypes = con->filters->nr_types;
+	if (con->filters->nr_cgrps)
+		ncgrps = con->filters->nr_cgrps;
 
 	/* resolve lock name filters to addr */
 	if (con->filters->nr_syms) {
@@ -85,6 +87,7 @@ int lock_contention_prepare(struct lock_contention *con)
 	bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
 	bpf_map__set_max_entries(skel->maps.type_filter, ntypes);
 	bpf_map__set_max_entries(skel->maps.addr_filter, naddrs);
+	bpf_map__set_max_entries(skel->maps.cgroup_filter, ncgrps);
 
 	if (lock_contention_bpf__load(skel) < 0) {
 		pr_err("Failed to load lock-contention BPF skeleton\n");
@@ -146,6 +149,16 @@ int lock_contention_prepare(struct lock_contention *con)
 			bpf_map_update_elem(fd, &con->filters->addrs[i], &val, BPF_ANY);
 	}
 
+	if (con->filters->nr_cgrps) {
+		u8 val = 1;
+
+		skel->bss->has_cgroup = 1;
+		fd = bpf_map__fd(skel->maps.cgroup_filter);
+
+		for (i = 0; i < con->filters->nr_cgrps; i++)
+			bpf_map_update_elem(fd, &con->filters->cgrps[i], &val, BPF_ANY);
+	}
+
 	/* these don't work well if in the rodata section */
 	skel->bss->stack_skip = con->stack_skip;
 	skel->bss->aggr_mode = con->aggr_mode;
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 823354999022..4900a5dfb4a4 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -92,6 +92,13 @@ struct {
 	__uint(max_entries, 1);
 } addr_filter SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u64));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} cgroup_filter SEC(".maps");
+
 struct rw_semaphore___old {
 	struct task_struct *owner;
 } __attribute__((preserve_access_index));
@@ -114,6 +121,7 @@ int has_cpu;
 int has_task;
 int has_type;
 int has_addr;
+int has_cgroup;
 int needs_callstack;
 int stack_skip;
 int lock_owner;
@@ -194,6 +202,15 @@ static inline int can_record(u64 *ctx)
 			return 0;
 	}
 
+	if (has_cgroup) {
+		__u8 *ok;
+		__u64 cgrp = get_current_cgroup_id();
+
+		ok = bpf_map_lookup_elem(&cgroup_filter, &cgrp);
+		if (!ok)
+			return 0;
+	}
+
 	return 1;
 }
 
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index d03651098dde..fcb509058499 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -114,7 +114,7 @@ static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str
 	return NULL;
 }
 
-static struct cgroup *cgroup__new(const char *name, bool do_open)
+struct cgroup *cgroup__new(const char *name, bool do_open)
 {
 	struct cgroup *cgroup = zalloc(sizeof(*cgroup));
 
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index beb6fe1012ed..de8882d6e8d3 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -26,6 +26,7 @@ void cgroup__put(struct cgroup *cgroup);
 struct evlist;
 struct rblist;
 
+struct cgroup *cgroup__new(const char *name, bool do_open);
 struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name);
 int evlist__expand_cgroup(struct evlist *evlist, const char *cgroups,
 			  struct rblist *metric_events, bool open_cgroup);
diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h
index a073cc6a82d2..1a7248ff3889 100644
--- a/tools/perf/util/lock-contention.h
+++ b/tools/perf/util/lock-contention.h
@@ -9,9 +9,11 @@ struct lock_filter {
 	int			nr_types;
 	int			nr_addrs;
 	int			nr_syms;
+	int			nr_cgrps;
 	unsigned int		*types;
 	unsigned long		*addrs;
 	char			**syms;
+	u64			*cgrps;
 };
 
 struct lock_stat {