perf lock contention: Skip stack trace from BPF

Currently it collects stack traces to max size then skip entries.
Because we don't have control how to skip perf callchains.  But BPF can
do it with bpf_get_stackid() with a flag.

Say we have max-stack=4 and stack-skip=2, we get these stack traces.

Before:                    After:

     .---> +---+ <--.           .---> +---+ <--.
     |     |   |    |           |     |   |    |
     |     +---+  usable        |     +---+    |
    max    |   |    |          max    |   |    |
   stack   +---+ <--'         stack   +---+  usable
     |     | X |                |     |   |    |
     |     +---+   skip         |     +---+    |
     |     | X |                |     |   |    |
     `---> +---+                `---> +---+ <--'   <=== collection
                                      | X |
                                      +---+   skip
                                      | X |
                                      +---+
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
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: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20220912055314.744552-5-namhyung@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/bpf_lock_contention.c

@@ -93,6 +93,8 @@ int lock_contention_prepare(struct lock_contention *con)
 		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
 	}
 
+	skel->bss->stack_skip = con->stack_skip;
+
 	lock_contention_bpf__attach(skel);
 	return 0;
 }
@@ -127,7 +129,7 @@ int lock_contention_read(struct lock_contention *con)
 	while (!bpf_map_get_next_key(fd, &prev_key, &key)) {
 		struct map *kmap;
 		struct symbol *sym;
-		int idx;
+		int idx = 0;
 
 		bpf_map_lookup_elem(fd, &key, &data);
 		st = zalloc(sizeof(*st));
@@ -146,8 +148,7 @@ int lock_contention_read(struct lock_contention *con)
 
 		bpf_map_lookup_elem(stack, &key, stack_trace);
 
-		/* skip BPF + lock internal functions */
-		idx = con->stack_skip;
+		/* skip lock internal functions */
 		while (is_lock_function(machine, stack_trace[idx]) &&
 		       idx < con->max_stack - 1)
 			idx++;

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

@@ -72,6 +72,7 @@ struct {
 int enabled;
 int has_cpu;
 int has_task;
+int stack_skip;
 
 /* error stat */
 unsigned long lost;
@@ -117,7 +118,7 @@ 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);
+	pelem->stack_id = bpf_get_stackid(ctx, &stacks, BPF_F_FAST_STACK_CMP | stack_skip);
 
 	if (pelem->stack_id < 0)
 		lost++;