perf lock contention: Support lock type filtering for BPF

Likewise, add type_filter BPF hash map and check it when user gave a
lock type filter.

  $ sudo ./perf lock con -ab -Y rwlock -- ./perf bench sched messaging
  # Running 'sched/messaging' benchmark:
  # 20 sender and receiver processes per group
  # 10 groups == 400 processes run

       Total time: 0.203 [sec]
   contended  total wait  max wait  avg wait       type  caller

          15   156.19 us  19.45 us  10.41 us   rwlock:W  do_exit+0x36d
           1    11.12 us  11.12 us  11.12 us   rwlock:R  do_wait+0x8b
           1     5.09 us   5.09 us   5.09 us   rwlock:W  release_task+0x6e

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Blake Jones <blakejones@google.com>
Cc: Ian Rogers <irogers@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/20221219201732.460111-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-lock.c

@@ -1689,6 +1689,7 @@ static int __cmd_contention(int argc, const char **argv)
 		.map_nr_entries = bpf_map_entries,
 		.max_stack = max_stack_depth,
 		.stack_skip = stack_skip,
+		.filters = &filters,
 	};
 
 	session = perf_session__new(use_bpf ? NULL : &data, &eops);

tools/perf/util/bpf_lock_contention.c

@@ -20,7 +20,7 @@ static struct lock_contention_bpf *skel;
 int lock_contention_prepare(struct lock_contention *con)
 {
 	int i, fd;
-	int ncpus = 1, ntasks = 1;
+	int ncpus = 1, ntasks = 1, ntypes = 1;
 	struct evlist *evlist = con->evlist;
 	struct target *target = con->target;
 
@@ -46,9 +46,12 @@ int lock_contention_prepare(struct lock_contention *con)
 		ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
 	if (target__has_task(target))
 		ntasks = perf_thread_map__nr(evlist->core.threads);
+	if (con->filters->nr_types)
+		ntypes = con->filters->nr_types;
 
 	bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
 	bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
+	bpf_map__set_max_entries(skel->maps.type_filter, ntypes);
 
 	if (lock_contention_bpf__load(skel) < 0) {
 		pr_err("Failed to load lock-contention BPF skeleton\n");
@@ -90,6 +93,16 @@ int lock_contention_prepare(struct lock_contention *con)
 		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
 	}
 
+	if (con->filters->nr_types) {
+		u8 val = 1;
+
+		skel->bss->has_type = 1;
+		fd = bpf_map__fd(skel->maps.type_filter);
+
+		for (i = 0; i < con->filters->nr_types; i++)
+			bpf_map_update_elem(fd, &con->filters->types[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;

tools/perf/util/bpf_skel/lock_contention.bpf.c

@@ -62,10 +62,18 @@ struct {
 	__uint(max_entries, 1);
 } task_filter SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} type_filter SEC(".maps");
+
 /* control flags */
 int enabled;
 int has_cpu;
 int has_task;
+int has_type;
 int stack_skip;
 
 /* determine the key of lock stat */
@@ -74,7 +82,7 @@ int aggr_mode;
 /* error stat */
 int lost;
 
-static inline int can_record(void)
+static inline int can_record(u64 *ctx)
 {
 	if (has_cpu) {
 		__u32 cpu = bpf_get_smp_processor_id();
@@ -94,6 +102,15 @@ static inline int can_record(void)
 			return 0;
 	}
 
+	if (has_type) {
+		__u8 *ok;
+		__u32 flags = (__u32)ctx[1];
+
+		ok = bpf_map_lookup_elem(&type_filter, &flags);
+		if (!ok)
+			return 0;
+	}
+
 	return 1;
 }
 
@@ -116,7 +133,7 @@ int contention_begin(u64 *ctx)
 	__u32 pid;
 	struct tstamp_data *pelem;
 
-	if (!enabled || !can_record())
+	if (!enabled || !can_record(ctx))
 		return 0;
 
 	pid = bpf_get_current_pid_tgid();

tools/perf/util/lock-contention.h

@@ -118,6 +118,7 @@ struct lock_contention {
 	struct target *target;
 	struct machine *machine;
 	struct hlist_head *result;
+	struct lock_filter *filters;
 	unsigned long map_nr_entries;
 	int lost;
 	int max_stack;