perf lock contention: Implement -t/--threads option for BPF

The BPF didn't show the per-thread stat properly.  Use task's thread id (PID)
as a key instead of stack_id and add a task_data map to save task comm names.

  $ sudo ./perf lock con -abt -E 5 sleep 1
   contended   total wait     max wait     avg wait          pid   comm

           1    740.66 ms    740.66 ms    740.66 ms         1950   nv_queue
           3    305.50 ms    298.19 ms    101.83 ms         1884   nvidia-modeset/
           1     25.14 us     25.14 us     25.14 us      2725038   EventManager_De
          12     23.09 us      9.30 us      1.92 us            0   swapper
           1     20.18 us     20.18 us     20.18 us      2725033   EventManager_De

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/20221209190727.759804-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 37 insertions, 4 deletions

diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 64fd1e040ac8..cd405adcd252 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -44,6 +44,13 @@ struct {
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct contention_task_data));
+	__uint(max_entries, MAX_ENTRIES);
+} task_data SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
 	__uint(value_size, sizeof(__u8));
 	__uint(max_entries, 1);
 } cpu_filter SEC(".maps");
@@ -61,6 +68,9 @@ int has_cpu;
 int has_task;
 int stack_skip;
 
+/* determine the key of lock stat */
+int aggr_mode;
+
 /* error stat */
 int lost;
 
@@ -87,6 +97,19 @@ static inline int can_record(void)
 	return 1;
 }
 
+static inline void update_task_data(__u32 pid)
+{
+	struct contention_task_data *p;
+
+	p = bpf_map_lookup_elem(&task_data, &pid);
+	if (p == NULL) {
+		struct contention_task_data data;
+
+		bpf_get_current_comm(data.comm, sizeof(data.comm));
+		bpf_map_update_elem(&task_data, &pid, &data, BPF_NOEXIST);
+	}
+}
+
 SEC("tp_btf/contention_begin")
 int contention_begin(u64 *ctx)
 {
@@ -115,10 +138,14 @@ int contention_begin(u64 *ctx)
 	pelem->timestamp = bpf_ktime_get_ns();
 	pelem->lock = (__u64)ctx[0];
 	pelem->flags = (__u32)ctx[1];
-	pelem->stack_id = bpf_get_stackid(ctx, &stacks, BPF_F_FAST_STACK_CMP | stack_skip);
 
-	if (pelem->stack_id < 0)
-		lost++;
+	if (aggr_mode == LOCK_AGGR_CALLER) {
+		pelem->stack_id = bpf_get_stackid(ctx, &stacks,
+						  BPF_F_FAST_STACK_CMP | stack_skip);
+		if (pelem->stack_id < 0)
+			lost++;
+	}
+
 	return 0;
 }
 
@@ -141,7 +168,13 @@ int contention_end(u64 *ctx)
 
 	duration = bpf_ktime_get_ns() - pelem->timestamp;
 
-	key.stack_or_task_id = pelem->stack_id;
+	if (aggr_mode == LOCK_AGGR_CALLER) {
+		key.stack_or_task_id = pelem->stack_id;
+	} else {
+		key.stack_or_task_id = pid;
+		update_task_data(pid);
+	}
+
 	data = bpf_map_lookup_elem(&lock_stat, &key);
 	if (!data) {
 		struct contention_data first = {