perf lock contention: Add data failure stat

It's possible to fail to update the data when the lock_stat map is full.
We should check that case and show the number at the end.

  $ sudo ./perf lock con -ablv -E3 -- ./perf bench sched messaging
  ...
   contended   total wait     max wait     avg wait            address   symbol

        6157    208.48 ms     69.29 us     33.86 us   ffff934c001c1f00    (spinlock)
        4030     72.04 ms     61.84 us     17.88 us   ffff934c000415c0    (spinlock)
        3201     50.30 ms     47.73 us     15.71 us   ffff934c2eead850    (spinlock)

  === output for debug ===

  bad: 0, total: 13388
  bad rate: 0.00 %
  histogram of failure reasons
         task: 0
        stack: 0
         time: 0
         data: 0      <----- added
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Ian Rogers <irogers@google.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: Juri Lelli <juri.lelli@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230406210611.1622492-2-namhyung@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-lock.c

@@ -1626,7 +1626,7 @@ static void sort_contention_result(void)
 static void print_bpf_events(int total, struct lock_contention_fails *fails)
 {
 	/* Output for debug, this have to be removed */
-	int broken = fails->task + fails->stack + fails->time;
+	int broken = fails->task + fails->stack + fails->time + fails->data;
 
 	if (quiet || total == 0 || (broken == 0 && verbose <= 0))
 		return;
@@ -1640,7 +1640,9 @@ static void print_bpf_events(int total, struct lock_contention_fails *fails)
 	pr_info(" %10s: %d\n", "task", fails->task);
 	pr_info(" %10s: %d\n", "stack", fails->stack);
 	pr_info(" %10s: %d\n", "time", fails->time);
+	pr_info(" %10s: %d\n", "data", fails->data);
 }
+
 static void print_contention_result(struct lock_contention *con)
 {
 	struct lock_stat *st;

tools/perf/util/bpf_lock_contention.c

@@ -262,6 +262,7 @@ int lock_contention_read(struct lock_contention *con)
 	con->fails.task = skel->bss->task_fail;
 	con->fails.stack = skel->bss->stack_fail;
 	con->fails.time = skel->bss->time_fail;
+	con->fails.data = skel->bss->data_fail;
 
 	stack_trace = zalloc(stack_size);
 	if (stack_trace == NULL)

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

@@ -124,6 +124,7 @@ int aggr_mode;
 int task_fail;
 int stack_fail;
 int time_fail;
+int data_fail;
 
 static inline int can_record(u64 *ctx)
 {
@@ -380,7 +381,8 @@ int contention_end(u64 *ctx)
 		if (aggr_mode == LOCK_AGGR_ADDR)
 			first.flags |= check_lock_type(pelem->lock, pelem->flags);
 
-		bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST);
+		if (bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST) < 0)
+			__sync_fetch_and_add(&data_fail, 1);
 		bpf_map_delete_elem(&tstamp, &pid);
 		return 0;
 	}

tools/perf/util/lock-contention.h

@@ -126,6 +126,7 @@ struct lock_contention_fails {
 	int task;
 	int stack;
 	int time;
+	int data;
 };
 
 struct lock_contention {